Journal of Intelligent & Fuzzy Systems - Volume 45, issue 6

Authors: Gao, Danna | Zhang, Yin | Qiu, Hongjun

Article Type: Research Article

Abstract: Due to the large number of frames and low video resolution, tennis match videos cannot accurately identify and extract effective data, which reduces the level of fine analysis of tennis matches. In order to solve the problem of poor detection effect of small targets in tennis video, an automatic detection method of small targets in tennis video based on deep learning is proposed. Non-maximum suppression algorithm is used to determine the position of the target between different adjacent video image sequences, and SVM classifier is used to train a large number of target behaviors. According to the hierarchical structure of …dataset annotation, the hierarchical structure of tennis video for deep learning is optimized. The reconstruction algorithm is used to enhance the video image in the input VOC data set and improve the fine segmentation effect of the image. The difference video image is binarized to complete the automatic detection of small targets in tennis video. The experimental results show that the proposed method has high integrity of tennis video information collection, high recognition accuracy and short detection time. Show more

Keywords: Deep learning, tennis match, automatic target detection

DOI: 10.3233/JIFS-231167

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9199-9209, 2023

Authors: Chang, Jingjing | Zhao, Hui

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-231778

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9211-9221, 2023

Authors: Liu, Yang | Yi, Fulong | Ma, Yuhua | Wang, Yongfu

Article Type: Research Article

Abstract: To solve the problem that the existing semantic segmentation method is challenging to balance the two indicators of reasoning speed and accuracy under low-light conditions, a lightweight real-time semantic segmentation method that can run on embedded vehicle terminals under low-light conditions, namely, LCG-BiSeNetV2 is proposed. Firstly, the Zero-DCE++ method is introduced to preprocess the low-light video frames; Secondly, by improving the module of the BiSeNetV2 method and optimizing the downsampling convolution in the encoder structure, the semantic feature extraction ability of the BiSeNetV2 method has been significantly improved; Finally, the self-made road scene semantic segmentation dataset and the CAMVID dataset …were used for training and testing, the mIoU coefficient reaches 72.37% and 76.73%, and the reasoning speed reaches 148.91 Frames Per Second (FPS) and 136.75 FPS, which shows that the LCG-BiSeNetV2 method has achieved fast reasoning and precise semantic segmentation. Show more

Keywords: End-to-end, real-time, semantic segmentation, autonomous driving system, image enhancement

DOI: 10.3233/JIFS-230643

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9223-9237, 2023

Authors: Xie, Zhixin | Wang, Xiaofeng | Yang, Lan | Pang, Lichao | Zhao, Xingyu | Yang, Yi

Article Type: Research Article

Abstract: The survey propagation algorithm is the most effective information propagation algorithm for solving the 3-SAT problem. It can effectively solve the satisfiability problem when it converges. However, when the factor graph structure is complex, the algorithm often does not converge and the solution fails. In order to give a theoretical explanation to this phenomenon and to analyze the convergence of the survey propagation algorithm effectively, a connected treewidth model of the propositional formula was constructed by using the connected tree decomposition method, and the connected treewidth of the factor graph was calculated. The relationship between the connected treewidth and the …convergence of the survey propagation algorithm is established, and the convergence judgment condition of the survey propagation algorithm based on the connected tree width is given. Through experimental analysis, the results show that the method is effective, which is of great significance for analyzing the convergence analysis of other information propagation algorithms. Show more

Keywords: Survey propagation algorithm, convergence, connected treewidth, propositional formula, satisfiability problem

DOI: 10.3233/JIFS-223779

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9239-9252, 2023

Authors: Zhang, Ning | Jung, Kwansue

Article Type: Research Article

Abstract: High-quality development of socio-economic, ecological environment, tourism industry and natural resources in the Yellow River Basin is a major strategic task for national development. High-quality development in the Yellow River Basin still has a lot of room for improvement, so it is important for the coupled and coordinated development of water resources-socio-economic-ecological environment-tourism industry in the Yellow River Basin region. In this study, we focus on the major strategic issues of high quality development in the Yellow River Basin in the context of the above-mentioned background and the current forms and policies of sustainable development in China, and conduct research …on the theory and methods of assessing the sustainable development of regional water resources-socio-economic-ecological environment-tourism industry. However, by analyzing the existing research literature on sustainable development assessment, we find that most of them focus on a single area or two combinations of modal development studies, and focus on exploring micro-coupling mechanisms, so the generality of macro policy support is rather mediocre, which we fill this gap through this study. The study relies on an innovative macroscopic research perspective that draws pioneeringly on the quality function deployment (QFD) theory in the field of product quality management in marketing, which, it is worth stating, allows for a framework of research perspectives from a systematic and holistic perspective. In this framework, we will propose a G1-entropy value method for indicator importance (weight) assessment. It is worth stating that the G1 method used in this paper is different from the traditional G1 method in that we will introduce the identity information weights of experts to improve the reliability of the subjective assignment method. We will also construct an indicator system for studying the regional sustainable development issues in the Yellow River Basin on this basis, so as to complete the ranking and analysis of the nine provinces and the importance of indicators in the Yellow River Basin. This study will provide a comprehensive theoretical basis for Chinese government and related departments to formulate policies for the high-quality development of water resources, socio-economic, ecological environment and tourism industry in the Yellow River Basin, and also provide theoretical and empirical references for the analysis and assessment of similar international regional sustainability cases. Show more

Keywords: Analytical theory of sustainable development, quality function deployment, G1-entropy method, yellow river basin

DOI: 10.3233/JIFS-230920

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9253-9276, 2023

Authors: Nguyen, Phu Xuan-Vinh | Nguyen, Thu Hoang-Thien | Van Nguyen, Kiet | Nguyen, Ngan Luu-Thuy

Article Type: Research Article

Abstract: Multilingual pre-trained language models have achieved impressive results on most natural language processing tasks. However, the performance is inhibited due to capacity limitations and their under-representation of pre-training data, especially for languages with limited resources. This has led to the creation of tailored pre-trained language models, in which the models are pre-trained on large amounts of monolingual data or domain specific corpus. Nevertheless, compared to relying on multiple monolingual models, utilizing multilingual models offers the advantage of multilinguality, such as generalization on cross-lingual resources. To combine the advantages of both multilingual and monolingual models, we propose KDDA - a framework …that leverages monolingual models to a single multilingual model with the aim to improve sentence representation for Vietnamese. KDDA employs teacher-student framework and cross-lingual transfer that aims to adopt knowledge from two monolingual models (teachers) and transfers them into a unified multilingual model (student). Since the representations from the teachers and the student lie on disparate semantic spaces, we measure discrepancy between their distributions by using Sinkhorn Divergence - an optimal transport distance. We conduct experiments on two Vietnamese natural language understanding tasks, including machine reading comprehension and natural language inference. Experimental results show that our model outperforms other state-of-the-art models and yields competitive performances. Show more

Keywords: Natural language understanding, machine reading comprehension, natural language inference, knowledge distillation, optimal transport

DOI: 10.3233/JIFS-231485

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9277-9288, 2023

Authors: He, Xiaoquan | Dong, Fang

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-233020

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9289-9302, 2023

Authors: Ma, Qian | Jiang, Shuhao | Yang, Dandan | Cheng, Guangtao

Article Type: Research Article

Abstract: In recent years, the problem of influential spreader identification in complex networks has attracted extensive attention as its fundamental role in social network analysis, rumor controlling, viral marketing and other related fields. Centrality measures that consider different scales of neighborhood are commonly utilized for ranking node influence. The 2-hop neighborhood of the target node is deemed a suitable evaluation metric. However, as the network scale expands, only considering 2-hop neighborhood is overly restrictive. Furthermore, the interconnections among nodes are often disregarded. In this article, a new method named Limited Spreading Domain (LSD) is proposed to identify influential spreaders. LSD defines …the target node’s 2-hop neighborhood as basic domain and takes the neighbors who are 3–6 hops away from target node as extended domain. The influence of target node is modeled as diffusion along the paths with limited length in basic domain and extended domain. A series of experiments are conducted in eight real complex networks and results demonstrate that LSD outperforms common centralities in terms of accuracy, stability,distinguishability and scalability. Show more

Keywords: Complex network, influential spreaders, SIR model, centrality measure

DOI: 10.3233/JIFS-230258

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9303-9314, 2023

Authors: Xinyi, Zhang

Article Type: Research Article

Abstract: Visual art was originally measured by viewing and appreciating graphic works, and there was no previous research into ways to improve the quality of visual art. With the rapid development of visual arts and technology, the question of how to improve quality has become an urgent one. As the most cutting-edge and hottest concept in the international arena today, the development and application of metaverse technology has widely drawn the close attention of various industries, including management, economy, education, and art. However, there is no in-depth and clear research on the concept of metaverse in the field of art, especially …in the field of visual art. We believe that the creation of visual art in the context of metaverse will be an important direction for art development in the future, and can also greatly contribute to the improvement of the quality of metaverse visual art presentation. Therefore, we focus on the issue of visual art quality assessment in our research, and propose a theory and method of metaverse-oriented future visual art quality assessment. The method focuses on the G1-entropy value method to calculate the weights in visual arts, combines qualitative research with quantitative research, and proposes the improvement path and countermeasures for visual arts. In summary, our research aims to address the theoretical approaches to the design of the metaverse field architecture and the assessment of art quality for the future introduction of the metaverse. The main contributions of our research are focused on the following three aspects: 1. The construction of the visual art field architecture draws on the functional requirements analysis method of system science simulation, considering that the entire visual art metaverse field architecture is constructed at three levels: the bottom data support layer, the middle technical support layer and the upper technical application layer. 2. The G1-entropy combination weighting method is used to derive the importance ranking of visual art quality indicators and identify key factors, and to derive suggestions for quality improvement based on the key indicator factors. More importantly, we also build a field architecture for future-oriented visual arts in this study, which bridges the gap in the structural design of visual arts after the introduction of the future concept. Our present study makes a great contribution to the application of visual art quality enhancement, focusing on the analysis of new concepts and the improvement of old methods, building a new scene of organic combination of new technologies and traditional visual art, with practical research theoretical support for the promotion and progress of the disciplinary field. Show more

Keywords: Visual art, metaverse, field structure, G1 entropy method, index weights

DOI: 10.3233/JIFS-224571

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9315-9333, 2023

Authors: Liu, Shaohua | Xia, Caichu | Ye, Jun

Article Type: Research Article

Abstract: In large-section tunnel engineering, there is uncertain and inconsistent information in risk factors, due to complex geological, irregular hydrological conditions, limited survey technology, and inexperience of construction technicians. However, it is difficult for existing risk assessment methods to consider and express this uncertain information comprehensively, which will affect the accuracy of tunnel risk assessment. Hence, this paper develops a method of neutrosophic numbers similarity measure based on arcsine function to address the expression of uncertain information in the risk factors of large-section tunnel. The uncertain information in risk factors is considered comprehensively and the comprehensive weight of tunnel risk factors …is calculated by the analytic hierarchy process and the entropy weight method in this method, in order to provide a reference for similar tunnels. Show more

Keywords: Large-section tunnel, risk assessment, neutrosophic numbers, similarity measure, arcsine function

DOI: 10.3233/JIFS-231475

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9335-9345, 2023

Authors: Janakiraman, Bhavithra | Prabu, S. | Senthil Vadivu, M. | Krishnan, Dhineshkumar

Article Type: Research Article

Abstract: Having one’s life threatened by a disease like ovarian cancer is the single most crucial thing in the whole world. It is difficult to achieve high performance without sacrificing computational efficiency; the results of the denoising process are not as good as they could be; the proposed models are nonconvex and involve several manually chosen parameters, which provides some leeway to boost denoising performance; the methods generally involve a complex optimisation problem in the testing stage; Here at DnCNN, we’ve developed our own version of the deep ii learning model, a discriminative learning technique. The goal was to eliminate the …need for the iterative optimisation technique at the time it was being evaluated. The goal was to avoid having to go through testing altogether, thus this was done. It is highly advised to use a Deep CNN model, the efficacy of which can be evaluated by comparing it to that of more traditional filters and pre-trained DnCNN. The Deep CNN strategy has been shown to be the best solution to minimise noise when an image is destroyed by Gaussian or speckle noise with known or unknown noise levels. This is because Deep CNN uses convolutional neural networks, which are trained using data. This is because convolutional neural networks, which are the foundation of Deep CNN, are designed to learn from data and then use that learning to make predictions. Deep CNN achieves a 98.45% accuracy rate during testing, with an error rate of just 0.002%. Show more

Keywords: Ovarian follicles, cancer, deep learning, hybrid optimization, noise levels, magnetic resonance imaging

DOI: 10.3233/JIFS-231322

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9347-9362, 2023

Authors: Noor, Mah | Jamil, Muhammad Kamran | Ullah, Kifayat | Azeem, Muhammad | Pamucar, Dragan | Almohsen, Bandar

Article Type: Research Article

Abstract: A T-spherical fuzzy set (TSFS) is an extended and logical algebraic representation to handle uncertainty, with the help of four functions describing four possible aspects of uncertain information. Aczel-Alsina triangular norm (TN) and conorm (TCN) are novel and proved to be more efficient than other existing TNs and TCNs. In our article, we establish the concept of a T-spherical fuzzy Aczel-Alsina graph (TSFAAG). We described the energy of TSFAAG along with the splitting and shadow energy of TSFAAG. Furthermore, we figured out the Randić energy of TSFAAG and obtained some useful results. Moreover, we give the notion of the Aczel-Alsina …digraph (TSFAADG). To see the significance of the proposed TSFAADGs, we employed the energy and Randić energy of TSFAADGs for solving the problem of selecting the best investing company by using a decision-making algorithm. The sensitivity analysis of the variable parameters is also discussed and where the effect on ranking results is studied. To see the effectiveness of the proposed work, we did a comparative study and established some remarks. Show more

Keywords: T-spherical fuzzy sets, T-spherical fuzzy Aczel-Alsina graph, energy, splitting graph, shadow graph, randić energy, decision making

DOI: 10.3233/JIFS-231086

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9363-9385, 2023

Authors: Lang, Liping | Thuente, David | Ma, Xiao

Article Type: Research Article

Abstract: In order to better evaluate and promote human health, this paper analyzes the influence of different inertial-measurement-unit signals, different sensor locations, different activity intensities and different signal fusion schemes on the accuracy of physical strength consumption estimation during walking and running activities. Different pattern recognition methods, such as the Counts-based linear regression model, the typical non-linear model based on decision tree and artificial neural network, and the end-to-end convolutional neural network model, are analyzed and compared. Our findings are as follows: 1) For the locations of sensors during walking and running activities, the physical strength consumption prediction accuracy at the …ankle location is higher than that at the hip location. Therefore, wearing an inertial-measurement-unit at the ankle can improve the accuracy of the model. 2) Regarding the types of activity signals during walking and running activities, the impact of accelerometer signals on hip and ankle prediction accuracy is not significantly different, while the gyroscope model is more sensitive to the location, with higher prediction accuracy at the ankle than at the hip. In addition, the physical strength consumption prediction accuracy of accelerometer signals is higher than that of gyroscope signals, and fusion of accelerometer and gyroscope signals can improve the accuracy of physical strength consumption prediction. 3) For different data analysis models during walking and running activities, the artificial neural network model that integrates different sensor locations and inertial-measurement-unit signals with different activity intensities has the lowest mean squared error for the measurement of physical strength consumption. The non-linear models based on decision tree and artificial neural network have better physical strength consumption prediction capabilities than the Counts-based linear regression model, especially for high-intensity activity energy consumption prediction. In addition, feature engineering models are generally better than convolutional neural network model in terms of overall performance and prediction results under the three different activity intensities. Furthermore, as the activity intensity increases, the performance of all physical strength consumption calculation models decreases. We recommend using the artificial neural network model based on multi-signal fusion to estimate physical strength consumption during walking and running activities because this model exhibits strong generalization ability in cross-validation and test results, and its stability under different activity intensities is better than that of the other three models. To the best of our knowledge, this paper is the first to delve deeply and in detail into methods for estimating physical strength consumption. Undoubtedly, our paper will have an impact on research related to topics such as intelligent wearable devices and subsequent methods for estimating physical strength consumption, which are directly related to physical health. Show more

Keywords: Human health, intelligent wearable devices, strength consumption estimation, pattern recognition

DOI: 10.3233/JIFS-231691

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9387-9402, 2023

Authors: Li, Dongjie | Wang, Mingrui | Zhang, Yu | Zhai, Changhe

Article Type: Research Article

Abstract: Although various automatic or semi-automatic recognition algorithms have been proposed for tiny part recognition, most of them are limited to expert knowledge base-based target recognition techniques, which have high false detection rates, low recognition accuracy and low efficiency, which largely limit the quality as well as efficiency of tiny part assembly. Therefore, this paper proposes a precision part image preprocessing method based on histogram equalization algorithm and an improved convolutional neural network (i.e. Region Proposal Network(RPN), Visual Geometry Group(VGG)) model for precision recognition of tiny parts. Firstly, the image is restricted to adaptive histogram equalization for the problem of poor …contrast between part features and the image background. Second, a custom central loss function is added to the recommended frame extraction RPN network to reduce problems such as excessive intra-class spacing during classification. Finally, the local response normalization function is added after the nonlinear activation function and pooling layer in the VGG network, and the original activation function is replaced by the Relu function to overcome the problems such as high nonlinearity and serious overfitting of the original model. Experiments show that the improved VGG model achieves 95.8% accuracy in precision part recognition and has a faster recognition speed than most existing convolutional networks trained on the same test set. Show more

Keywords: Precision parts, histogram equalization, image recognition, VGG, RPN

DOI: 10.3233/JIFS-231730

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9403-9419, 2023

Authors: Zhang, Longji | zhao, Hui

Article Type: Research Article

Abstract: Traditional graph convolutional neural networks (GCN) utilizing linear feature combination methods have limited capacity to capture the interaction between complex features. While current research has extensively investigated various syntactic dependency tree structures, the optimization of GCN algorithms has often been overlooked, leading to suboptimal efficiency in practical applications. To address this issue, this paper proposes a cross-feature method that utilizes feature vector multiplication to construct non-linear combinations of GCN features and enhance the model’s capability to extract complex feature correlations. Experimental results demonstrate the superiority of the proposed method, with our models outperforming state-of-the-art methods and achieving significant improvements on …three standard benchmark datasets. These results suggest that the cross-feature method can effectively extract potential connections between features, highlighting its potential for improving the performance of GCN-based models in real-world applications. Show more

Keywords: Aspect-based sentiment analysis, syntactic dependency tree, graph convolutional neural networks, cross-feature

DOI: 10.3233/JIFS-221687

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9421-9432, 2023

Authors: Zhou, Chunrong | Jiang, Zhenghong

Article Type: Research Article

Abstract: Load balancing in cloud computing refers to dividing computing characteristics and workloads. Distributing resources among servers, networks, or computers enables enterprises to manage workload demands. This paper proposes a novel load-balancing method based on the Two-Level Particle Swarm Optimization (TLPSO). The proposed TLPSO-based load-balancing method can effectively solve the problem of dynamic load-balancing in cloud computing, as it can quickly and accurately adjust the computing resource distribution in order to optimize the system performance. The upper level aims to improve the population’s diversity and escape from the local optimum. The lower level enhances the rate of population convergence to the …global optimum while obtaining feasible solutions. Moreover, the lower level optimizes the solution search process by increasing the convergence speed and improving the quality of solutions. According to the simulation results, TLPSO beats other methods regarding resource utilization, makespan, and average waiting time. Show more

Keywords: Load balancing, cloud computing, virtualization, particle swarm optimization algorithm

DOI: 10.3233/JIFS-230828

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9433-9444, 2023

Authors: Yu, Ying | Yu, Jiamao | Qian, Jin | Zhu, Zhiliang | Han, Xing

Article Type: Research Article

Abstract: Crowd counting aims to estimate the number, density, and distribution of crowds in an image. The current mainstream approach, based on CNN, has been highly successful. However, CNN is not without its flaws. Its limited receptive field hampers the modeling of global contextual information, and it struggles to effectively handle scale variation and background complexity. In this paper, we propose a Multi-scale Hybrid Attention Network called MHANet to solve crowd counting challenges more effectively. To address the issue of scale variation, we have developed a Multi-scale Aware Module (MAM) that incorporates multiple sets of dilated convolutions with varying dilation rates. …The MAM significantly improves the network’s ability to extract information at multiple scales. To tackle the problem of background complexity, we have introduced a Hybrid Attention Module (HAM) that combines spatial attention and channel attention. The HAM effectively directs attention to the crowd region while suppressing background interference, resulting in more accurate counting. MHANet has been extensively experimented on four benchmark datasets and compared against state-of-the-art algorithms. It consistently achieves superior performance in terms of the MAE evaluation metric. MHANet outperforms the current state-of-the-art methods by margins of 1.9%, 5.4%, 0.4%, and 0.8% on the ShanghaiTech Part_A, ShanghaiTech Part_B, UCF-QNRF, and UCF_CC_50 datasets, respectively. Furthermore, a series of ablation experiments targeting MAM and HAM were conducted in this paper, and the experimental results fully demonstrate that MAM and HAM can effectively address the challenges of scale variation and background complexity, ultimately enhancing the accuracy and robustness of the network. Show more

Keywords: CNN, crowd counting, multi-scale, hybrid attention

DOI: 10.3233/JIFS-232065

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9445-9455, 2023

Authors: Jiang, Zhuo | Huang, Xiao | Wang, Rongbin

Article Type: Research Article

Abstract: Aiming at anomaly detection upon a high-dimensional space, this paper proposed a novel autoencoder-support vector machine. The key thought is that using the autoencoder extracts the features from high-dimensional data, and then the support vector machine achieves the separation of abnormal features and normal features. To increase the precision of identifying anomalies, Chebyshev’s theorem was used to estimate the upper of the number of abnormal features. Meanwhile, the dot product operation was implemented in order to strengthen the learning of the model for class labels. Experiment results show that the detected accuracy of the proposed method is 0.766 when the …data dimensionality is 5408, and also wins over competitors in detected performance for the considered cases. We also demonstrate that the strengthened learning of class labels can improve the ability of the model to detect anomalies. In terms of noise resistance and overcoming the curse of dimensionality, the former can carry out more efforts than the latter. Show more

Keywords: Anomaly detection, Chebyshev’s theorem, high-dimensional data

DOI: 10.3233/JIFS-231735

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9457-9469, 2023

Authors: Liang, Xingzhu | Liu, Wen | Bi, Feilong | Yan, Xinyun | Zhang, Chunjiong

Article Type: Research Article

Abstract: Online knowledge distillation breaks the pre-determined strong and weak teacher-student models, it provides a new way of thinking about knowledge distillation. However, the current online methods often use the Logits-based prediction distribution, and the features containing rich semantic information are rarely used. Even if the feature-based methods are used, they only operate on the last layer of the network, without further exploring the representation knowledge of the middle layer feature map. To address the above issues, we propose an innovative feature early fusion and reconstruction (FEFR) method for online knowledge distillation which entails four essential components: multi-scale feature extraction and …intermediate layer feature early fusion, reconstruction of features, dual-attention and overall fusion module in this paper. We propose early fusion by “sum” operation for feature matrices between different layers and advance fusion to improve the feature map representation. In order to enhance the communication ability between groups to obtain features, the features were reconstructed. We create a dual-attention to enhance the critical channel and spatial regions adaptively in order to collect more accurate information. The previously processed feature maps are combined and fused using feature fusion, which also aids in student models training. A study of the network architectures of CIFAR-10, CIFAR-100, CINIC-10 and ImageNet 2012 shows that FEFR provides more useful characterization knowledge for refinement and improves accuracy by about 0.5% compared to other methods. Show more

Keywords: Online knowledge distillation, teacher-student models, multi-scale, feature early fusion

DOI: 10.3233/JIFS-232626

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9471-9482, 2023

Authors: Mihi, Soukaina | Ait Benali, Brahim | Laachfoubi, Nabil

Article Type: Research Article

Abstract: Sentiment analysis has become a prevalent issue in the research community, with researchers employing data mining and artificial intelligence approaches to extract insights from textual data. Sentiment analysis has progressed from simply classifying evaluations as positive or negative to a sophisticated task requiring a fine-grained multimodal analysis of emotions, manifestations of sarcasm, aggression, hatred, and racism. Sarcasm occurs when the intended message differs from the literal meaning of the words employed. Generally, the content of the utterance is the opposite of the context. Sentiment analysis tasks are hampered when a sarcastic tone is recognized in user-generated content. Thus, automatic sarcasm …detection in textual data dramatically impacts the performance of sentiment analysis models. This study aims to explain the basic architecture of a sarcasm detection system and the most effective techniques for extracting sarcasm. Then, for the Arabic language, determining the gap and challenges. Show more

Keywords: Sarcasm, NLP, sentiment analysis, Arabic, deep learning, machine learning

DOI: 10.3233/JIFS-224514

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9483-9497, 2023

Authors: Thirugnanam, G. | Sahul Hameed, Jennathu Beevi | Bharathidasan, B.

Article Type: Research Article

Abstract: In addition to existing cryptographic systems, watermarking technologies have been developed to add extra security. Digital watermarking utilizes embedding or hiding techniques to protect multimedia files from copyright violations. Fundamental procedures of digital watermarking techniques are embedding and extraction. Singular value decomposition (SVD) based Image watermarking schemes become popular owing to its better trade-off among robustness and imperceptibility. Nevertheless, false positive problem (FPP) is a major issue of SVD-based watermarking schemes. The singular value that is a fixed value and does not contain structural information about image is the primary cause of FPP problem. Therefore, Message Digest algorithm image watermarking …scheme based on Funk Singular Value Decomposition and Fractional-Order Polar Harmonic Transform (FSVD-FOPHT) is proposed in this paper to address this problem. The MD-5 algorithm is used to extract data from the host and watermark imageries and then create secret key. The FSVD-FOPHT method is utilized to hide watermark information in host image. The secret keys are extracted from hided image using inverse process of Fractional-Order Polar Harmonic Transforms with Funk Singular Value Decomposition algorithm. By using the extraction procedure, watermark image is extracted, and then reconstructs original watermarked image. During extraction procedure, the secret key is used for authentication to address FPP. Then, the proposed method is implemented in MATLAB and performance is analyzed with evaluation metrics, such as Embedding capacity, MSE, PSNR, and NC. The proposed method provide 14.6%, 17.34%, 19.53%, 21.46% and 23.89% high PSNR for cold-snow-landscape-water test image, 14.29%, 16.47%, 18.39%, 20.16% and 21.93% high PSNR for landscape-nature-sky-blue Test image, 16.85%, 19.99%, 22.70%, 27.22% and 29.16% high Embedding Capacity for cold-snow-landscape-water test image 22.83%, 24.64%, 27.92%, 29.60% and 31.77% high Embedding Capacity for landscape-nature-sky-blue Test image 35.38%, 32.63%, 30.95%, 28.61% and 26.08% low extraction time compared with existing methods SVD-CMSF-SIW, FE-IWS-DNN, AR-IWS-DNN, BBET-SHA1-SIW and LSB-DWT-SIW respectively. Show more

Keywords: Fractional-order polar harmonic transforms funk singular value decomposition embedding and extraction, message digest algorithm, secure image watermarking

DOI: 10.3233/JIFS-222182

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9499-9521, 2023

Authors: Liu, Hong | Wang, Gaihua | Li, Qi | Wang, Nengyuan

Article Type: Research Article

Abstract: The detection of magnetic tile quality is an essential link before the assembly of permanent magnet motor. In order to meet the high standard of magnetic tile surface defect detection and realize the rapid and automatic segmentation of magnetic tile defects, a magnetic tile surface defect segmentation algorithm based on cross self-attention model (CSAM) is proposed. It adopts high-low level semantic feature fusion method to build the dependency relationship between the deep and shallow features. Multiple auxiliary loss functions are used to constrain the network and reduce the noise in the deep features. In addition, an image enhancement method is …also designed to solve the problem of insufficient annotated data. The experimental results show that the network can achieve 79.6% mIoU and 98.5% PA, which can meet the high standard requirements of magnetic tile manufacturing. Show more

Keywords: Defect detection, data enhancement, cross self-attention, multiple auxiliary loss, semantic segmentation

DOI: 10.3233/JIFS-232366

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9523-9532, 2023

Authors: Xiao, Yanjun | Zhao, Yue | Li, ShiFang | Song, Weihan | Wan, Feng

Article Type: Research Article

Abstract: The foundation of textile machinery digitization and intelligence is condition monitoring and identification. Online condition monitoring of looms is of great significance to ensure their long-term stable operation and improve their digital management level. However, the existing loom condition monitoring methods have problems such as insufficient depth of information mining, low condition recognition rate and poor system versatility. As a result, the loom on-board condition monitoring technology based on fuzzy rough set and improved DSmT theory is studied. To begin, we examine the loom operation mechanism, loom state characterization, and loom state feature data composition. Then, using the fuzzy rough …set method, we analyze and make decisions on the loom state feature data, apply the theory of uncertainty and importance improvement DSmT fusion to solve the uncertainty problem of the rough set method’s decision rules, and build the loom state feature decision network on the embedded terminal using the decision rules. Meanwhile, to collect, communicate, display, and alarm loom characteristic data, this paper employs the STM32F407ZET6 microcontroller and designs a loom system status data collection platform with the AD7730 as the core, as well as tests loom status monitoring data collection and loom status data analysis and decision method based on this platform. The experimental findings show the usefulness of attribute data gathering as well as data analysis and decision-making processes. The technology enhances the precision of loom condition identification and decision making, as well as the safety and quality of manufacturing. It is critical for carrying out applications like as problem detection, remote monitoring, efficiency optimization, and intelligent weaving machine management. Show more

Keywords: Keywords: Rapier loom, dezert-Smarandache, fuzzy rough sets, condition monitoring, attribute reduction

DOI: 10.3233/JIFS-230950

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9533-9553, 2023

Authors: Dong, Yingda | He, Chunguang | Qin, Yanping | Yuan, Yunmei | Gao, Fan | Duo, Huaqiong | Wang, Ximing

Article Type: Research Article

Abstract: A novel enhancement method to improve resolution and contrast has been proposed to address the issues of blurring and distortion commonly encountered in traditional patterns. Initially, a discrete wavelet transform, a stationary wavelet transform, and an interpolation algorithm are used to obtain high-resolution images of traditional patterns. Subsequently, improved singular value matrix coefficients and reconstructed gamma function are used to enhance the image contrast to obtain high-resolution and contrast-enhanced patterns. Experimental results demonstrate the efficacy of this method, as evidenced by improved evaluation indexes, such as mean square error, peak signal-to-noise ratio, and structural similarity, in comparison to other existing …methods. The proposed method effectively improves the quality of traditional patterns and offers significant contributions to research on the restoration and protection of traditional patterns. Show more

Keywords: Traditional pattern enhancement, stationary wavelet transform, discrete wavelet transform, singular value matrix, gamma function

DOI: 10.3233/JIFS-232169

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9555-9569, 2023

Authors: Shenbagavalli, S.T. | Shanthi, D.

Article Type: Research Article

Abstract: Due to the vast amount of patient health data, automated healthcare systems still struggle to classify and diagnose various ailments. Learning redundant data also reduces categorization accuracy. A Deep Belief Network (DBN) has been used to precisely extract the most important aspects from clinical data by ignoring irrelevant/redundant features. Due of many learning variables, training is complicated. Similarly, the hybrid model has been employed by ensemble Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to categorize diseases. But, its efficiency depends on the proper choice of kernels and hyper-parameters. Therefore, this paper develops an efficient …feature extraction and classification model for healthcare systems. First, several medical data related to the patient’s health are collected. Then, an Optimized DBN (ODBN) model is presented for maximizing the accurateness of DBN by optimizing the learning variables depends on the Ant Lion Optimization (ALO) algorithm. With learning ODBN, the most relevant features are extracted with reduced computational complexity. After that, the CNN-LSTM with Unsupervised Fine-tuned Deep Self-Organizing Map (UFDSOM)-based classifier model is designed to categorize the extracted features into categories of illnesses. In this novel classifier, dropout normalization and parameter tuning processes are applied to avoid overfitting and optimize the hyper-parameters, which results in a less training period. In the end, studies utilizing publically accessible datasets show that the ODBN with CNN-LSTM-UFDSOM system outperforms classical models by 98.23%. Show more

Keywords: Medical data classification, DBN, CNN-LSTM, SVM, Ant lion optimizer

DOI: 10.3233/JIFS-224370

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9571-9589, 2023

Authors: Su, Jiafu | Wang, Dan | Xu, Baojian | Zhang, Fengting | Ling, Xu

Article Type: Research Article

Abstract: A crucial step for agricultural product merchants to achieve profitable and sustainable development in the live-streaming e-commerce age is evaluating the risk of the agricultural products live-streaming e-commerce platform. However, there isn’t much reliable research available right now on the risk evaluation of platforms. Therefore, this study suggests an improved risk evaluation method based on interval-valued intuitionistic fuzzy multi-criteria group decision-making (MCGDM). This method determines the decision-maker weight for the risk criterion according to the levels of professionalism of the decision-makers in the risk criterion and uses the VIse Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method to rate the risk …of the alternative agricultural products live-streaming e-commerce platforms. The viability and dependability of the approach described in this work are demonstrated using a case study. The strengths and weaknesses of this approach are illustrated by a comparative analysis. With the help of this paper, agricultural product merchants will be able to identify the live-streaming e-commerce platform that carries the least amount of overall risk and work toward the paper’s stated objectives of sustainable development in addition to developing and enhancing theoretical research findings in the field. Show more

Keywords: Live-streaming e-commerce platform, risk assessment, MCGDM, interval-valued intuitionistic fuzzy number, professionalism of decision makers

DOI: 10.3233/JIFS-231403

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9591-9604, 2023

Authors: Chen, Liang-Ching | Chang, Kuei-Hu

Article Type: Research Article

Abstract: Within the new era of artificial intelligence (AI), education industry should develop in the direction of intelligence and digitalization. For evaluating learners’ academic performances, English high-stakes test is not only a mere means for measuring what English as a Foreign Language (EFL) stakeholders know or do not know but also likely to bring life-changing consequences. Hence, effective test preparation for English high-stakes test is crucial for those who futures depend on attaining a particular score. However, traditional corpus-based approaches cannot simultaneously take words’ frequency and range variables into consideration when evaluating their importance level, which makes the word sorting results …inaccurate. Thus, to effectively and accurately extract critical words among English high-stakes test for enhancing EFL stakeholders’ test performance, this paper integrates a corpus-based approach and a revised Importance-Performance Analysis (IPA) method to develop a novel frequency-range analysis (FRA) method. Taiwan College Entrance Exam of English Subject (TCEEES) from the year of 2001 to 2022 are adopted as an empirical case of English high stake test and the target corpus for verification. Results indicate that the critical words evaluated by FRA method are concentrated on Quadrant I including 1,576 word types that account for over 60% running words of TCEEES corpus. After compared with the three traditional corpus-based approaches and the Term Frequency-Inverse Document Frequency (TF-IDF) method, the significant contributions include: (1) the FRA method can use a machine-based function words elimination technique to enhance the efficiency; (2) the FRA method can simultaneously take words’ frequency and range variables into consideration; (3) the FRA method can effectively conduct cluster analysis by categorizing the words into the four quadrants that based on their relative importance level. The results will give EFL stakeholders a clearer picture of how to allocate their learning time and education resources into critical words acquisition. Show more

Keywords: Artificial intelligence (AI), English high-stakes test, corpus-based approach, Importance-Performance Analysis (IPA) method, Term Frequency-Inverse Document Frequency (TF-IDF) method, frequency-range analysis (FRA) method

DOI: 10.3233/JIFS-231539

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9605-9620, 2023

Authors: Hussain, Abrar | Ullah, Kifayat | Al-Quran, Ashraf | Garg, Harish

Article Type: Research Article

Abstract: Renewable energy sources play an influential role in the world’s climate and reduce the rate of harmful gasses such as carbon dioxide, methane, nitrous oxide, and many other greenhouse gasses that contribute to global warming. The theoretical concept of the T-spherical fuzzy (T-SF) set (T-SFS) is the most suitable model to evaluate energy resources under uncertainty. This article illustrates appropriate operations based on Dombi triangular norm and t-conorm. We derived a series of new aggregation approaches, such as T-SF Dombi Hamy mean (T-SFDHM) and T-SF weighted Dombi Hamy Mean (T-SFDWHM) operators. Further authors illustrated a list of new approaches such …as T-SF Dual Dombi Hamy mean (T-SFDDHM), and T-SF Dombi weighted Dual Hamy mean (T-SFDWDHM) operators. Some exceptional cases and desirable properties of our derived approaches are also studied. We illustrate an application of renewable energy resources to be evaluated using a multi-attribute group decision-making (MAGDM) method. A case study was also studied to choose appropriate energy resources using our proposed methodology of the T-SFDWHM and T-SFDWDHM operators. To show the effectiveness and validity of our current methods, we compared the existing results with currently developed aggregation operators (AOs). Show more

Keywords: T-Spherical fuzzy values, aggregation operators, Dombi aggregation models, and multi-attribute decision-making method

DOI: 10.3233/JIFS-232505

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9621-9641, 2023

Authors: Wang, Qingling | Zheng, Jian | Zhang, Wenjing

Article Type: Research Article

Abstract: Majority classes are easily to be found in imbalance datasets, instead, minority classes are hard to be paid attention to due to the number of is rare. However, most existing classifiers are better at exploring majority classes, resulting in that classification results are unfair. To address this issue of binary classification for imbalance data, this paper proposes a novel fuzzy support vector machine. The thought is that we trained two support vector machines to learn the majority class and the minority class, respectively. Then, the proposed fuzzy is used to estimate the assistance provided by instance points for the training …of the support vector machines. Finally, it can be judged for unknown instance points through evaluating that they provided the assistance to the training of the support vector machines. Results on the ten UCI datasets show that the class accuracy of the proposed method is 0.747 when the imbalanced ratio between the classes reaches 87.8. Compare with the competitors, the proposed method wins over them in classification performance. We find that aiming at the classification of imbalanced data, the complexity of data distribution has negative effects on classification results, while fuzzy can resist these negative effects. Moreover, fuzzy can assist those classifiers to gain superior classification boundaries. Show more

Keywords: Binary classification, fuzzy, imbalanced data, support vector machines

DOI: 10.3233/JIFS-232414

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9643-9653, 2023

Authors: Moghaddam Teymourlu, Sohrab Abdollahzadeh | Amini, Amir

Article Type: Research Article

Abstract: In the current study, a new approach to assess and select food suppliers in hospitals is presented using integrated group evaluation method of fuzzy best- worst method (FBWM) and fuzzy gray relational analysis (FGRA). Evaluation criteria are selected by experts and weighed by the fuzzy best-worst method. After that, suppliers are rated using FGRA method. The proposed approach was implemented with seven criteria in one of the Iranian hospitals, and the results showed that quality, delivery time and trust criteria had the highest and skilled manpower and lack of surplus production criteria had the lowest score. Using FGRA, existing suppliers …were ranked and the appropriate supplier was identified. In order to evaluate the reliability of the results, sensitivity analysis was performed on the criteria changes. The results showed that the supplier’s selection is greatly influenced by the criteria estimation values by the experts. Show more

Keywords: Food supply chain, supplier evaluation and selection, fuzzy best-worst method, fuzzy gray relational analysis, health and medical centers

DOI: 10.3233/JIFS-231845

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9655-9668, 2023

Authors: Xu, Dongsheng | Sun, Yuhuan | He, Xinyang

Article Type: Research Article

Abstract: This paper provides a novel target threat assessment model that utilizes TOPSIS and three-way decision-making under a single-valued neutrosophic environment. The presented model provides theoretical support for combat decision-making in complex battlefield environments with uncertain information. The model employs single-valued neutrosophic sets to handle uncertain data, which enhances the descriptive ability of information. The maximum deviation method is used to calculate attribute weight factors, which highlights the importance of each attribute. The final target threat ranking is obtained based on the relative closeness coefficient of each target. Furthermore, the proposed model constructs a multi-attribute aggregation loss function matrix for each …target, sets the risk avoidance coefficient under the knowledge of the battlefield condition, and calculates the decision threshold of each target using three-way decision theory. This method produces the classification of the target choice. The numerical examples and comparison analysis demonstrate that the suggested model can handle ambiguous scenario information effectively and reasonably, transform traditional decision-making ranking results into three-way classification findings, and provide a rationale for choosing an attacking target. Show more

Keywords: Threat assessment, three-way decision, TOPSIS, single-valued neutrosophic

DOI: 10.3233/JIFS-232267

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9669-9680, 2023

Authors: Ramyasree, Kummari | Kumar, Chennupati Sumanth

Article Type: Research Article

Abstract: At present, the local appearance-based texture descriptors in Facial Expression Recognition have limited accuracy due to the inability to encode the discriminative edges. The major cause is the presence of distorted and weak edges due to noise. Hence, this paper proposes new Expression Descriptor called as Weighted Edge Local Directional Pattern (WELDP) which can discriminate the weak and strong edges. Unlike the conventional local descriptors, WELDP searches for the support of neighbor pixels in the determination of Facial expression attributes such as Edges, Corners, Lines, and Curved Edges. WELDP encodes only Strong edge responses and discards weaker edge responses after …extracting them through edge detection masks. This work adapted two masks for edge detection: they are Robinson Compass Mask and Kirsch Compass Mask. Moreover, the WELDP aims at code redundancy and encode each pixel only with seven bits (one sign bit and six directional bits). Then the WELDP image is described by a histogram and then processed through SVM (Support Vector Machine) for expression identification. From the simulation experiments, the proposed WELDP is found as better than several existing methods. Show more

Keywords: Face expression recognition, edge detection, gaussian weight, compass mask, directional encoding, and accuracy

DOI: 10.3233/JIFS-232985

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9681-9696, 2023

Authors: Priya Varshini, A.G. | Anitha Kumari, K.

Article Type: Research Article

Abstract: As the size and complexity of projects grows, estimates are increasingly used, especially in the agile community. Software development cannot begin without first conducting thorough planning and estimation. Estimating how much work a project will take is a common first step in the software development life cycle. By employing ensemble techniques, we integrate multiple learning algorithms to build a more accurate predictive model. The core elements of our proposed stacked ensemble strategy include Decision Tree, Principal Components Regression, Random Forest, NeuralNet, GLMNET, XGBoost, Earth, and Support Vector Machine. Moreover, we augment the model’s performance by incorporating a blend of these …foundational algorithms with other ensemble regression methods. Extensive testing in the suggested research work with a number of Super Learners demonstrates that Regression is the best technique for judging effort. The evaluation of the different estimators involved the use of various metrics, including Mean Absolute Error, Root Mean Squared Error, Mean Squared Error, Percentage of Close Approximations within 25% of the True Values (PRED (25)), R-Squared Coefficients, Precision, Recall, and F1-Score. The proposed method yields more trustworthy predicted performance than either single-model approaches or stacked ensembles. Effort estimation serves as the foundation for the rest of the project management process. Show more

Keywords: Software effort estimations, stacked ensemble method, super learner, principal components regression

DOI: 10.3233/JIFS-230676

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9697-9713, 2023

Authors: Patidar, Neelam | Makrariya, Akshara

Article Type: Research Article

Abstract: The human body is a complex system that can be disrupted by various types of infections and viruses, and body temperature is a major contributor to these problems. To prevent this, doctors recommend comfortable clothing made from good fabric. This paper proposes a model that can be used to analyze how different types of fabric impact the thermal profile of skin layers during and after physical activity. The information gained from this model could be useful in designing exercise apparel for different climates and in generating thermal stress protocols for treating infections and providing physical activity guidelines for healthy living. …The model uses Pennes’ bio-heat equation and finite difference method to examine the temperature distribution in skin layers while accounting for both physiological and clothing parameters. The numerical findings were compared to existing studies, and the model’s accuracy was found to be in good agreement with previous research. The proposed model can be used to predict how much rest and acclimation are needed to cope with thermal stress and could also be modified to obtain thermal information for patients with skin diseases. Additionally, the thermal profile obtained from this model could be helpful in designing exercise clothes for patients with skin diseases. Show more

Keywords: Finite difference method (FDM), exercise, skin layers, clothing, temperature distribution, mathematical modeling, one dimensional (1D)

DOI: 10.3233/JIFS-231524

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9715-9728, 2023

Authors: Naveen Kmuar, M. | Godfrey Winster, S.

Article Type: Research Article

Abstract: Investigation of human face images forms an important facet in affective analysis. The work, a DL-based ensemble is proposed for this purpose. Seven pre-trained models namely Facenet, Facenet2018, VGG16, Resnet-50, Senet-50, Arcface and Openface that have been developed for face verification have been exploited and customized for emotion identification. To each of these models, each all over interaction with softmax method to classification groups are augmented and entire network is then trained completely for emotion recognition. After training all the models individually, the probabilities for each of the class by each of the model are summed to derive at the …final value. The class that holds the highest of this value is finalized as the predicted emotion. Thus, the proposed methodology involves image collection, image pre-processing comprising of contrast enhancement, face detection and extraction, face alignment, image augmentation facilitating rotation, shifting, flipping and zooming transformations and appropriate resizing and rescaling, feature extraction and classification through ensemble of customized afore-mentioned pre-trained convolutional neural networks, evaluation and evolving of best weights for emotion recognition from face images with enhanced accuracy. The proposed methodology is evaluated on the well-established FER-2013 dataset. The methodology achieves a validation accuracy of 74.67% and test accuracy of 76.23%. Further, similar images of another dataset (Face Expression Recogniton dataset) are included for training the models and the impact of extra training is assessed to see if there is improvement in performance. The experiments reveal marked improvement in face emotion identification performance reaching values of 94.98% for both validation and test set of FER-2013 dataset and 94.99% on validation set of Face Expression Recognition dataset. Show more

Keywords: Emotion identification, transfer learning, ensemble, pre-trained models, CNN, DNN, DL, multi-class classification, image classification, human faces

DOI: 10.3233/JIFS-231199

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9729-9752, 2023

Authors: Ge, Yilin | Sun, Liping | Wang, Di

Article Type: Research Article

Abstract: Veneer is the critical raw material for manufacturing man-made board products, therefore the quality of the veneer determines the level of the man-made board. However, defects in the veneer may significantly lower its grade. Currently, identifying veneer defects requires manual inspection and subsequent inpainting using a veneer digging machine. Unfortunately, this method only removes the defects of the veneer but ignore the consistency of its texture. To address this issue, we propose a feasible veneer defect reconstruction method that utilizes a texture-aware-multiscale-GAN architecture. Our method performs texture reconstruction of veneer defects to increase the texture information of the reconstructed image …while improving the model efficiency, so that generates natural-looking textures in the reconstructed defect areas. The model is trained by end-to-end updating of four cascades of efficient generators and discriminators. We also employed a loss function based on local binary patterns (LBP) to ensure that the restored images contain sufficient texture information. Finally, region normalization is used in the model to enhance the accuracy of the model. Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) are used to evaluate the effectiveness of image restoration, the results show that PSNR of the method reacheds 35.32 and SSIM reaches 0.971. By minimizing the difference between the generated texture and that of the original image, our model produces high-quality results. Show more

Keywords: Image reconstruction, deep learning, veneer defect, LBP, texture aware multiscale

DOI: 10.3233/JIFS-231692

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9753-9769, 2023

Authors: Chen, Wei | Tang, Hong | Yan, Tingting

Article Type: Research Article

Abstract: The energy consumption of mechanical products in China is enormous, and the energy utilization rate is low, which is increasingly receiving people’s attention. Conducting product design for energy optimization is of great significance for improving energy utilization efficiency. The scheme design of a product is the key to achieving innovation in product design, and the evaluation and decision-making of the design scheme directly affect the results of the later stage of the design. Therefore, correctly evaluating and making reliable decisions on product design schemes that are oriented towards fuzzy decision optimization is an important aspect of product innovation conceptual design. …The product modeling design quality evaluation is a multiple attribute group decision making (MAGDM) problems. Recently, the Combined Compromise Solution (CoCoSo) method and information entropy method has been employed to cope with MAGDM issues. The interval neutrosophic sets (INSs) are employed as a tool for portraying uncertain information during the product modeling design quality evaluation. In this paper, the CoCoSo method is designed for MAGDM under INSs. Then, the interval neutrosophic numbers CoCoSo (INN-CoCoSo) method based on the Hamming distance and Euclidean distance is built for MAGDM. The information Entropy method is employed to produce the weight information based on the Hamming distance and Euclidean distance under INNSs. Finally, a practical numerical example for product modeling design quality evaluation is supplied to show the INN-CoCoSo method. The main contributions of this paper are constructed: (1) This paper builds the novel MAGDM based on CoCoSo model under INSs; (2) The information Entropy method is employed to produce the weight information based on the Hamming distance and Euclidean distance under INNSs; (3) The new MAGDM method is proposed for product modeling design quality evaluation based on INN-CoCoSo. Show more

Keywords: Multiple attribute group decision making (MAGDM), interval neutrosophic sets (INSs), CoCoSo method, information entropy, informationization teaching ability evaluation

DOI: 10.3233/JIFS-233825

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9771-9783, 2023

Authors: Gupta, Shivani | Patel, Nileshkumar | Kumar, Ajay | Jain, Neelesh Kumar | Dass, Pranav | Hegde, Rajalaxmi | Rajaram, A.

Article Type: Research Article

Abstract: Due to resource constraints and the diverse nature of the devices involved, energy efficiency and scalability enhancement are important challenges in the Internet of Things (IoT) ecosystem. It is difficult to manage the edge resources in a consistent way that promotes cooperation and sharing of resources across the devices because of the heterogeneity of the Internet of Things devices and the dynamic nature of the surroundings in which edge computing takes place. In this research, we offer Intelligent techniques for resource optimization for Internet of Things devices. This is a full-stack system architecture to support across heterogeneous Internet of Things …devices that have limited resources. The paradigm that is being suggested is made up of several edge servers, and Internet of Things (IoT) devices have the qualities of being heterogeneity-compatible, high performing, and intelligently adaptable. In order to do this, a clustered environment is generated in heterogeneous Internet of Things devices, and a routing method called Search and Rescue Optimization is used to set up connections between the CH nodes. After that, the edge nodes that are closest to the source of the data are chosen for transmission. Overall, what was suggested Multi-Edge-IoT accomplishes superior efficiency in terms of consumption of energy, latency, communication overhead, and packet loss rate than existing approaches to attaining energy efficiency in the Internet of Things. Show more

Keywords: Multi-edge-IoT, EDGE load balancing, heterogeneous network, Bi-fuzzy vikor, search & rescue optimization algorithm

DOI: 10.3233/JIFS-233819

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9785-9801, 2023

Authors: Xia, Jing | Zhang, Shiya

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-234976

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9803-9813, 2023

Authors: Niu, Guocheng | Hu, Dongmei | Zhao, Yang | Eladdad, M.E.

Article Type: Research Article

Abstract: To solve the problem that the operation state of transformer is difficult to quantify, a method of quantitative evaluation and prediction of transformer operating state is proposed, which combines the information entropy of matter element and Support Vector Machine. In the evaluation, various hydrogen gases in the transformer operation are taken as the evaluation indexes and the three-dimensional cross compound element is constructed. The analytic hierarchy process (AHP) is used to determine the theoretical weight of the evaluation index, and the entropy method is used to determine the objective weight of the evaluation index, and the final weight is the …joint weight of the theoretical weight and the objective weight. Transformer Health index is calculated by using complex element correlation entropy. In prediction, the grid search, genetic algorithm (GA) and particle swarm optimization (PSO) are used to optimize the parameters of Support Vector Machine. and the prediction model of Health index is established by SVM. Experiment results show that the Support Vector Machine based on Gauss kernel function and genetic algorithm has a prominent effect on the prediction of health index. Show more

Keywords: Transformer, health index, analytic hierarchy process (AHP), matter element information entropy, support vector machine (SVM)

DOI: 10.3233/JIFS-182785

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9815-9825, 2023

Authors: Majumder, Saibal | Kutum, Rintu | Khatua, Debnarayan | Sekh, Arif Ahmed | Kar, Samarjit | Mukerji, Mitali | Prasher, Bhavana

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-220990

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9827-9844, 2023

Authors: Cheng, Yafei | Zhao, Bin

Article Type: Research Article

Abstract: In recent years, there are many works about conditional distributivity for aggregation functions, which is closely related to integration theory and utility theory. In this paper, our main idea is to solve conditional distributivity equations from left and right for semi-t-operators over uninorms. One part focuses on these equations involving semi-t-operators over t-norms and obtains some complete characterizations. The other part gives the necessary and sufficient conditions of conditional distributivity for semi-t-operators over uninorms in U max and U min under the condition 0 < U  (x , y ) <1, …which transforms it into the conditional distributivity between t-norms and t-conorms (semi-t-norms and t-conorms, semi-t-conorms and t-norms). Show more

Keywords: Semi-t-operators, t-norms, uninorms, conditional distributivity

DOI: 10.3233/JIFS-230966

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9845-9860, 2023

Authors: Ragu, G. | Ramamoorthy, S.

Article Type: Research Article

Abstract: When a digital adversary or an insider compromised a framework, cloud Forensic examiners can simply lay out the scene of the crime and reconstruct how the event took place using scientific evidence to determine when, why, and how it happened. Be that as it may, computerized proof procurement in a cloud environment is confounded and demonstrated troublesome, Despite modern scientific securing tool compartments. Multi-occupancy, Geo-area, and Administration Level Understanding have added another layer of complexity to obtaining computerized proof from a cloud environment. To moderate these intricacies of proof procurement in the cloud environment, we want a system that can …forensically keep up with the reliability and respectability of proof. In this review, we plan and execute a Blockchain-based Forensic in Cloud (BBFC) structure, utilizing a Cloud Forensic methodology (CFA). The outcomes from our single contextual analysis will exhibit that BBFC will alleviate the difficulties and intricacies looked at by computerized forensic specialists in getting acceptable advanced proof from the cloud biological system. Moreover, a quick exhibition observing the proposed Blockchain based measurable in cloud structure was assessed. BBFC will guarantee dependability, respectability, validness, and non-renouncement of the proof in the cloud. The proposed BBFC framework was also subjected to performance evaluation, considering factors such as latency, bandwidth, energy and resource utilization, and failure points. This evaluation provides insights into the efficiency and effectiveness of the framework in real-world cloud forensic scenarios. Show more

Keywords: Blockchain, cloud computing, forensic data

DOI: 10.3233/JIFS-231072

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9861-9874, 2023

Authors: Chen, Xinquan | Ma, Jianbo | Qiu, Yirou | Liu, Sanming | Xu, Xiaofeng | Bao, Xianglin

Article Type: Research Article

Abstract: The purpose of clustering is to identify distributions and patterns within unlabelled datasets. Since the proposal of the original synchronization clustering (SynC) algorithm in 2010, synchronization clustering has become a significant research direction. This paper proposes a shrinking synchronization clustering (SSynC) algorithm utilizing a linear weighted Vicsek model. SSynC algorithm is developed from SynC algorithm and a more effective synchronization clustering (ESynC) algorithm. Through analysis and comparison, we find that SSynC algorithm demonstrates superior synchronization effect compared to SynC algorithm, which is based on an extensive Kuramoto model. Additionally, it exhibits similar effect to ESynC algorithm, based on a linear …version of Vicsek model. In the simulations, a comparison is conducted between several synchronization clustering algorithms and classical clustering algorithms. Through experiments using some artificial datasets, eight real datasets and three picture datasets, we observe that compared to SynC algorithm, SSynC algorithm not only achieves a better local synchronization effect but also requires fewer iterations and incurs lower time costs. Furthermore, when compared to ESynC algorithm, SSynC algorithm obtains reduced time costs while achieving nearly the same local synchronization effect and the same number of iterations. Extensive comparison experiments with some class clustering algorithms demonstrate the effectiveness of SSynC algorithm. Show more

Keywords: SynC algorithm, Kuramoto model, shrinking synchronization, a linear weighted Vicsek model, near neighbor points

DOI: 10.3233/JIFS-231817

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9875-9897, 2023

Authors: Rida, Zakaria | Boukachour, Hadhoum | Ennaji, Mourad | Machkour, Mustapha

Article Type: Research Article

Abstract: The articulation between machine tutoring and human tutoring remains a productive research within in the context of Intelligent Tutoring Systems (ITS), particularly in the context of e-learning where the dropout rate is high. We explore an innovative approach, the automation of tutoring as it is done in the classroom to respond to the difficulties of the learner. We propose a generic Intelligent Multi-Tutoring System (IMTS) architecture composed of two modules COMES and MAT. The Communication Entry Service (COMES) module manages communications between the IMTS and a Learning Management System (LMS). The module Multi-Agent Tutoring (MAT) is the multi-agent system developed …with JADE, which allows the dynamic adaptation of tutoring (Machine, Peer, Teacher) according to the profile of the learner. We offer a configurable system to customize tutoring to the individual needs of each learner. It can be grafted onto any learning platform, making it multidisciplinary and easy to integrate into existing learning environments. The teacher will be able to devote more time to learners which need greater his intervention.The peer will develop human and relational qualities linked to their know-how, transversal skills sought by recruiters. To validate this architecture, we provide an application and results that integrate the elements of the described model. The results of the experiment prove the feasibility and reliability of our approach. Show more

Keywords: Intelligent tutoring system, multi-agent system, adaptive system, markov, complex system

DOI: 10.3233/JIFS-232319

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9899-9913, 2023

Authors: Liu, Yiyang | Li, Changxian | Cui, Yunxian | Song, Xudong

Article Type: Research Article

Abstract: Intelligent bearing fault diagnosis plays an important role in improving equipment safety and reducing equipment maintenance costs. Noise in the signal can seriously reduce the accuracy of fault diagnosis. To improve the accuracy of fault diagnosis, a novel noise reduction method based on weighted multi-scale morphological filter (WMMF) is proposed. Firstly, Teager energy operator (TEO) is used to amplify the morphological information of the signal. Then, a scale filtering operator using envelope entropy (SFOEE) is proposed to select appropriate scales. At these scales, the noise in the signal can be adequately suppressed. A new weighting method is proposed to integrate …the selected scales to construct the WMMF. Finally, multi-headed self-attention capsule restricted boltzmann network (MSCRBN) is proposed to diagnose bearing faults.The performance of the TEO-SFOEE-WMMF-MSCRBN fault diagnosis method is verified on the CWRU dataset. Compared with existing fault diagnosis methods, this approach achieves 100% identification accuracy. The experimental results indicate that the proposed diagnosis method can effectively resist noise and precisely diagnose bearing faults. Show more

Keywords: Bearing fault diagnosis, mathematical morphological filter, restricted boltzmann machine, capsule network

DOI: 10.3233/JIFS-232737

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9915-9928, 2023

Authors: Cheng, Gang | You, Qinliang | Shi, Lei | Wang, Zhenxue | Luo, Jia | Li, Tianbin

Article Type: Research Article

Abstract: With the rapid development of information science and social networks, the Internet has accumulated various data containing valuable information and topics. The topic model has become one of the primary semantic modeling and classification methods. It has been widely studied in academia and industry. However, most topic models only focus on long texts and often suffer from semantic sparsity problems. The sparse, short text content and irregular data have brought major challenges to the application of topic models in semantic modeling and topic discovery. To overcome these challenges, researchers have explored topic models and achieved excellent results. However, most of …the current topic models are applicable to a specific model task. The majority of current reviews ignore the whole-cycle perspective and framework. It brings great challenges for novices to learn topic models. To deal with the above challenges, we investigate more than a hundred papers on topic models and summarize the research progress on the entire topic model process, including theory, method, datasets, and evaluation indicator. In addition, we also analyzed the statistical data results of the topic model through experiments and introduced its applications in different fields. The paper provides a whole-cycle learning path for novices. It encourages researchers to give more attention to the topic model algorithm and the theory itself without paying extra attention to understanding the relevant datasets, evaluation methods and latest progress. Show more

Keywords: Topic model, text mining, semantic understanding, whole-cycle, topic detection

DOI: 10.3233/JIFS-233551

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9929-9953, 2023

Authors: Lalitha, K. | Murugavalli, S. | Roseline, A. Ameelia

Article Type: Research Article

Abstract: For retrieving the relevant images from the internet, CBIRs (content based image retrievals) techniques are most globally utilized. However, the traditional image retrieval techniques are unable to represent the image features semantically. The CNNs (convolutional neural networks) and DL has made the retrieval task simpler. But, it is not adequate to consider only the finalized aspect vectors from the completely linked layers to fill the semantic gap. In order to alleviate this problem, a novel Hash Based Feature Descriptors (HBFD) method is proposed. In this method, the most significant feature vectors from each block are considered. To reduce the number …of descriptors, pyramid pooling is used. To improve the performance in huge databases, the hash code like function is introduced in each block to represent the descriptors. The proposed method has been evaluated in Oxford 5k, Paris 6k, and UKBench datasets with the accuracy level of 80.6%, 83.9% and 92.14% respectively and demonstrated better recall value than the existing methods. Show more

Keywords: Content-based image retrieval, CNNs, hash based feature descriptor (HBFD), pyramid pooling and hash code

DOI: 10.3233/JIFS-233891

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9955-9964, 2023

Authors: Liao, Tao | Sun, Haojie | Zhang, Shunxiang

Article Type: Research Article

Abstract: The entity-relationship extraction model has a significant influence in relation extraction. The existing model cannot effectively identify the entity-relationship triples in overlapping relationships. It also has the problem of long-distance dependencies between entities. In this paper, an inter span learning for document-level relation extraction model is proposed. Firstly, the model converts input of the BERT pre-training model into word vectors. Secondly, it divides the word vectors to form span sequences by random initial span and uses convolutional neural networks to extract entity information in the span sequences. Dividing the word vector into span sequences can divide the entity pairs that …may have overlapping relationships into the same span sequence, partially solving the overlapping relationship problem. Thirdly, the model uses inter span learning to obtain entity information in different span sequences. It fuses entity type features and uses Softmax regression to achieve entity recognition. Aiming at solving the problem of long-distance dependence between entities, inter span learning can fuse the information in different span sequences. Finally, it fuses text information and relationship type features, and uses Linear Layer to classify relationships. Experiments demonstrate that the model improves the F1-score of the DocRED dataset by 2.74% when compared to the baseline model. Show more

Keywords: Joint extraction, entity relation extraction, span, document-level extraction, neural network

DOI: 10.3233/JIFS-234202

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9965-9977, 2023

Authors: Bai, Shi | Li, Pujie

Article Type: Research Article

Abstract: This paper presents an in-depth study and analysis of oil painting classification and simulation using an improved embedded learning fusion vision perception algorithm. This paper analyzes and models the image quality evaluation problem by simulating the human visual system and extracting quality perception features as the main entry point to improve the prediction accuracy of the overall algorithm. This paper proposes a multi-classification method of CCNN, which uses the similarity measure based on information first to achieve multi-classification of artwork styles and artists, and this part is the main part of this paper. This paper uses the wiki art repository …to construct a dataset of oil paintings, including over 2000 works by 20 artists in 13 styles. CNN achieves an accuracy of 85.75% on the artist classification task, which is far more effective than traditional deep learning networks such as Resnet. Finally, we use the network model of this paper and other network models to train the classification of 3, 4, and 6 categories of art images. The accuracy of art image classification by this paper’s algorithm is higher than that of the current mainstream convolutional neural network models, and the extracted features are more comprehensive and more accurate than traditional art image feature extraction methods, which do not rely on researchers to extract image features. Experiments show that the proposed method can achieve excellent prediction accuracy for both synthetic distorted images and distorted images. Show more

Keywords: Visual perception, embedded learning, oil painting classification, algorithm simulation

DOI: 10.3233/JIFS-234545

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9979-9989, 2023

Authors: Srivastava, Stuti | Bansal, Richa | Thapar, Antika

Article Type: Research Article

Abstract: Bandwidth consecutive multicoloring problem is also known as a b-coloring problem. Let G  = (V , E ) be a graph where V is the set of vertices and E is the set of edges. Let each vertex v of V has a positive integer weight b  (v ) and each edge (v , w ) of E has a non-negative integer weight b  (v , w ). A bandwidth consecutive multicoloring of a graph is a problem of assigning b  (v ) consecutive positive integers to each vertex v of V in such …a manner that the difference between all the integers of vertex v and all the integers of vertex w is greater than b  (v , w ). The maximum integer assigned in this coloring is called the span of the coloring. The b-coloring is the problem of minimizing this span. No metaheuristic is proposed for general graphs so far for this problem till date as it is strongly NP-hard. In this paper, we proposed three heuristics for the problem including a greedy randomized adaptive search procedure (GRASP). The efficiency of these algorithms is tested on benchmark graphs and their performance is compared among themselves. Experimental results showed that among all three proposed heuristics, GRASP performed well for the given problem. Show more

Keywords: Graph theory, bandwidth coloring, greedy coloring, GRASP

DOI: 10.3233/JIFS-224242

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9991-10002, 2023

Authors: Weng, Zhi | Liu, Ke | Zheng, Zhiqiang

Article Type: Research Article

Abstract: The detection and identification of individual cattle plays an integral role in precision feeding and insurance claims, among others. Most current research is based on high-performance computing devices, which limits the application of deep learning techniques to mobile terminals. To this end, in this paper, we propose a channel-pruned YOLOv5 network-based method for cattle face detection on mobile terminals, referred to as NS-YOLO. First, the original model is sparsely trained and a sparse regularization penalty term is applied to the BN layers, then the corresponding mask values are labeled according to different weight thresholds, and the channels are pruned with …global thresholds. Second, the detection precision is recovered by fine-tuning the model. Finally, the NCNN forward inference framework is used to quantize the model and an Android-based cattle face detection application is developed. Experimental results show that the model size, number of parameters and FLOPs are reduced by 86.10%, 88.19% and 63.25%, respectively, and the inference time is reduced by 35.53% compared to the original model, while mAP0.5 is reduced by only 1.6%. In particular, the 16-bit quantized model reduces the model size by 93.97% and the inference time by 34.97% compared to the original model on the mobile side. The results show that the proposed method can be easily deployed in resource-constrained mobile devices and has great advantages in practical engineering applications. Show more

Keywords: Cattle face detection, channel pruning, YOLOv5, model quantization, mobile deployment

DOI: 10.3233/JIFS-232213

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10003-10020, 2023

Authors: Tang, Bin | Xie, Kai | Tao, Wenbin | Liu, Zhenyu | Zhu, Chuanqi | Zhao, Neng | Wang, Yiyang

Article Type: Research Article

Abstract: In order to improve bearing capacity of rockbolts in deep-buried coal mine roadways, orthogonal tests were conducted to study influencing factors of rockbolt anchoring effect. Wavelet neural network model was introduced to predict the pull-out force of rockbolt. The activation and output functions of the wavelet neural network were improved, and the scaling and translation parameters were also modified by using the gradient descent method. These improvements enhanced the approximation rate of the wavelet neural network model, and solve the problem that the wavelet transform method is monotonous and difficult to adapt to the complex and variable engineering conditions. Research …results illustrated that The value of the ultimate pull-out force is positively correlated with the strength of the specimen and pre-tension value of the specimen. According to the test results, the coal mine roadway support scheme was optimized, and the high prestress full-length anchoring rockbolt support technology was proposed. The effectiveness of research was verified through the engineering applications and in-situ monitoring results. Show more

Keywords: Rockbolt, improved Wavelet Neural Network, high prestress, pull-out test, field performance

DOI: 10.3233/JIFS-232435

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10021-10032, 2023

Authors: Li, Jing | Li, Chengyu | Meng, Lusha

Article Type: Research Article

Abstract: Global warming caused by excessive emissions of carbon dioxide (CO2 ) has become a hot topic globally in today’s society, and optimizing carbon emission performance (CEP) is an effective way to alleviate CO2 emissions. Many studies have explored CEP at the global, national, provincial and sector levels. However, due to the difficulty in obtaining energy consumption data, there is a lack of studies at the urban agglomeration and city levels. Taking the urban agglomeration dimension as the starting point, this paper constructs an improved epsilon-based measure (EBM) model to measure the CEP of the Yellow River Basin. A spatial …data analysis model was introduced to explore the regional spatial characteristics of CEP. The newly developed spatial statistical model was used to study the driving factors of CEP. The results showed that: (1) The overall CEP of the Yellow River Basin was relatively high, showing an upward trend of volatility. There were significant differences between the seven urban agglomerations and 69 cities. (2) The CEP of the Yellow River Basin showed a trend of spatial agglomeration. The urban agglomerations of the eastern region showed a low-value agglomeration phenomenon, and the urban agglomerations of the central and western regions showed a trend of high-value agglomeration. (3) Economic development level (PGGDP), technological progress (TP), industrialization level (IND) and human capital (HC) can play a positive role in promoting the improvement in CEP, and population structure (PD) and energy structure (ES) can play a negative role in promoting the improvement in CEP. Industrial agglomeration (IA) and CEP show a “U"-shaped relationship that first inhibits and then promotes. In addition, foreign direct investment (FDI), IND, and HC have significant spatial spillover effects on neighboring cities. Show more

Keywords: Yellow River Basin, urban agglomeration, carbon emission performance, spatial Durbin model, spatial agglomeration

DOI: 10.3233/JIFS-233246

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10033-10052, 2023

Authors: Shu, Mingming | Liu, Xiaoyu | Zhou, Hongming

Article Type: Research Article

Abstract: In order to better realize the effective display of painting art, this paper puts forward an interactive modeling method of structural sense of painting art communication from the perspective of media integration. From the perspective of comprehensive media, the painting art is spread and displayed, and the interactive evaluation index of painting art communication structure sense is constructed, and the interactive behavior evaluation model of painting art communication structure sense is constructed to realize the interactive modeling of communication structure sense. The experimental results show that from the perspective of integrating media, the somatosensory interaction mode of the communication structure …of painting art is highly practical in the practical application process, which meets the research requirements and can realize the effective display of painting art in a modified way. Show more

Keywords: Integrated media perspective, painting art, somatosensory interaction

DOI: 10.3233/JIFS-234284

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10053-10062, 2023

Authors: Zhang, Hu | Bai, Ping | Li, Ru

Article Type: Research Article

Abstract: Short text classification task is a special kind of text classification task in that the text to be classified is generally short, typically generating a sparse text representation that lacks rich semantic information. Given this shortcoming, scholars worldwide have explored improved short text classification methods based on deep learning. However, existing methods cannot effectively use concept knowledge and long-distance word dependencies. Therefore, based on graph neural networks from the perspective of text composition, we propose concept and dependencies enhanced graph convolutional networks for short text classification. First, the co-occurrence relationship between words is obtained by sliding window, the inclusion relationship …between documents and words is obtained by TF-IDF, long-distance word dependencies is obtained by Stanford CoreNLP, and the association relationship between concepts in the concept graph with entities in the text is obtained through Microsoft Concept Graph. Then, a text graph is constructed for an entire text corpus based on the four relationships. Finally, the text graph is input into graph convolutional neural networks, and the category of each document node is predicted after two layers of convolution. Experimental results demonstrate that our proposed method overall best on multiple classical English text classification datasets. Show more

Keywords: Short text classification, Knowledge graph, Graph convolutional neural networks, Long-distance dependency, Building graph for text

DOI: 10.3233/JIFS-222407

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10063-10075, 2023

Authors: Guo, Peng | Wang, Xiaonan | Zhang, Duo

Article Type: Research Article

Abstract: Punishment promotes cooperation among selfish agents. Unlike previous studies, we propose a new supervision (heterogeneous preference supervision, HPS) mechanism based on the original random supervision (ORS) mechanism considering regulators’ limited supervision ability and agents’ heterogeneous preferences. The concepts of exemption list capacity, observation period, and removal time are introduced as the variables under the HPS mechanism. A public goods game model is built to verify the supervision effects under the ORS and HPS mechanisms. The simulation results show that the HPS mechanism can promote cooperation more than the ORS mechanism. Increasing the exemption list capacity can make regulators pay more …attention to defectors and improve the cooperation level. Setting a relatively moderate observation period benefits a better supervision effect, while a too-small or too-large observation period leads to the collapse of cooperation. Shortening the removal time can increase the updating speed of the exemption list and enhance the role of the exemption list, resulting in improving the fraction of cooperators. Show more

Keywords: Public goods game, supervision mechanism, supervision ability, heterogeneous preference, exemption list

DOI: 10.3233/JIFS-230775

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10077-10088, 2023

Authors: Bharathi, J. | Nandhini, S.

Article Type: Research Article

Abstract: This paper explores the behaviour of a Bulk Arrival Retrial Queue Model (BARQ) with two phases of service under the Bernoulli Vacation schedule and Breakdown (BVSB). Each batch of customers arriving the system finds if the server is available, instantly utilizes the service. If the server is busy, under breakdown, or taking a vacation, then the customers enter into the orbit. After completing both service stages, the server will either take a vacation with probability p or wait until the next customer arrives with probability 1 - p or q . Our approach considers the nature of the customer as …balking and also takes into account the breakdown of server, which may occur instantaneously during any stage of service. Significant performance measures have been derived and presented. A numerical study of the proposed model is carried out using MATLAB and results were reported. Show more

Keywords: Retrial Queues, two types of service, Bernoulli Vacation, steady-state, Fortuitous Breakdown, impatient customers

DOI: 10.3233/JIFS-231195

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10089-10098, 2023

Authors: Thilagavathy, A. | Mohanaselvi, S.

Article Type: Research Article

Abstract: Consolidating cubical fuzzy numbers (CFNs) is essential in an uncertain decision-making process. This study focuses on creating innovative cubical fuzzy aggregation operators based on the newly proposed Einstein operational laws, utilizing the Bonferroni mean function to capture the interrelationships among the aggregated CFNs. The first contribution of this paper is introducing a novel cubical fuzzy Einstein Bonferroni mean averaging operator. Building upon this operator, we extend our research to develop cubical fuzzy Einstein Bonferroni mean weighted, ordered weighted, and hybrid averaging operators, taking into account the weights of the aggregated CFNs. To ensure their effectiveness, we thoroughly investigate the desirable …properties of these proposed operators. Furthermore, we leverage the introduced operators to establish a new approach known as the cubical fuzzy linear assignment method, which proves valuable in resolving multiple criteria group decision-making problems. As a practical demonstration of the method’s utility, we apply it to address a real-life challenge: identifying the optimal location for constructing a wind power plant under a cubical fuzzy environment. To validate the effectiveness of our approach, we compare its results with those obtained using existing methods from the literature. Additionally, we conduct a statistical analysis to visualize the correlative conjunction between the ranking outcomes obtained by different operators Show more

Keywords: Cubical fuzzy set, Einstein operational laws, Bonferroni mean, averaging aggregation operators, linear assignment method, wind power plant location selection

DOI: 10.3233/JIFS-232252

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10099-10125, 2023

Authors: Guo, Yijian | Sun, Kaiqiong | Luo, Gang | Wang, Meng

Article Type: Research Article

Abstract: Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown …samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%. Show more

Keywords: Leaf extraction, deep learning, unsupervised image segmentation, mutual information, VAE

DOI: 10.3233/JIFS-232696

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10127-10139, 2023

Authors: Umamageswari, A. | Deepa, S. | Bhagyalakshmi, A. | Sangari, A. | Raja, K.

Article Type: Research Article

Abstract: To assess non-verbal reactions to commodities, services, or products, sentiment analysis is the technique of identifying exhibited human emotions utilizing artificial intelligence-based technology. The facial muscles flex and contract differently in response to each facial expression that a person makes, which facilitates the deep learning AI algorithms’ ability to identify an emotion. Facial emotion analysis has numerous applications across various industries and domains, leveraging the understanding of human emotions conveyed through facial expressions, so it is very much required in healthcare, security and survelliance, Forensics, Autism and cultural studies etc,.. In this study, facially expressed sentiments in real-time photographs as …well as in an existing dataset are classified using object detection techniques based on deep learning. Fast Region-based Convolution Neural Network (R-CNN) is an object detection system that uses suggested areas to categorize facial expressions of emotion in real-time. Using a high-quality video collection made up of 24 actors who were photographed facially expressing eight distinct emotions (Happy, Sad, Disgust, Anger, Surprise, Fear, Contempt and Neutral). The Fast R-CNN and Mouth region-based feature extraction and Maximally Stable Extremal Regions (MSER) method used for classification and feature extraction respectively. In order to assess the deep network’s performance, the proposed work builds a confusion matrix. The network generalizes to new images rather well, as seen by the average recognition rate of 97.6% for eight emotions. The suggested deep network approach may deliver superior recognition performance when compared to CNN and SVM methods, and it can be applied to a variety of applications including online classrooms, video game testing, healthcare sectors, and automated industry. Show more

Keywords: Deep learning, R-CNN, emotion recognition, facial expression, computer vision

DOI: 10.3233/JIFS-233842

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10141-10155, 2023

Authors: Liu, Jun

Article Type: Research Article

Abstract: Composite cylindrical shells play a crucial role in aerospace and marine structures. This study investigates the optimal structure for cylindrical multilayer composite shells under the effect of axial pressure using the finite element method and NSGA-II genetic algorithm to determine the maximum buckling load capacity. The critical buckling load of multilayer composite shells depends on various parameters, such as fiber angle, the number of layers, the material of the layers, and their thickness. The objective functions are used to increase the structure load capacity and reduce its weight. ABAQUS software was used to perform finite element analysis on the composite …cylindrical shell for determining the buckling load. Using the response surface model, the relationship between variables and objective functions has been determined. Results of the proposed response surface model for the training stages are evaluated using various statistical indices and the root mean square error for buckling load and shell weight variables is 0.065 and 0.140, respectively. In the next step, the NSGA-II genetic optimization algorithm was used to modify the layout and thickness of the composite layers to optimize the buckling strength and weight of the structure. A genetic algorithm based on NSGA-II was used to optimize the geometric characteristics. Show more

Keywords: Multi-objective optimization, NSGA-II, buckling load, genetic algorithm, cylindrical shell

DOI: 10.3233/JIFS-230826

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10157-10165, 2023

Authors: Sun, Tiantian

Article Type: Research Article

Abstract: A scientific financial transfer payment system is an important guarantee for promoting the modernization of the national governance system and governance capacity. The new development concept puts forward new requirements for fiscal governance at a new historical stage. The reform and improvement of the special transfer payment system match the responsibility and responsibility of fiscal governance, and better serve the national strategic pattern of rural revitalization and common prosperity. The performance evaluation of financial special poverty alleviation (SPA) development funds is conducive to improving the efficiency of fund utilization, achieving the radiation effect and multiple effect of financial SPA development …funds, improving the ability of financial transfer payments, and enhancing the modernization of national financial governance capabilities. The performance evaluation of financial SPA development funds under the background of rural revitalization is a multiple attribute group decision making (MAGDM). Based on the existing MABAC model, the MABAC model is extended to 2-tuple linguistic Pythagorean fuzzy sets (2TLPFSs). Firstly, the definitions of 2TLPFSs, 2TLPFWA operator and 2TLPFWG operator is introduced. Then, the existing MABAC method is also introduced. The 2-tuple linguistic Pythagorean fuzzy number MABAC method (2TLPFN-MABAC) is constructed to cope with the MAGDM under 2TLPFSs. Finally, a case study for performance evaluation of financial SPA development funds under the background of rural revitalization is constructed and some comparative analyses is employed to verify the 2TLPFN-MABAC method. Show more

Keywords: Multiple attribute group decision making (MAGDM), MABAC method, 2-tuple linguistic Pythagorean fuzzy numbers (2TLPFNs), Financial SPA development funds

DOI: 10.3233/JIFS-232168

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10167-10181, 2023

Authors: Sun, Yin-Kun | Hua, Jun | Li, Yan-Na | Chen, Guang-Wei

Article Type: Research Article

Abstract: With the rapid development of science and technology, automatic control systems have been applied in more and more fields. At the same time, the requirements for the stability, accuracy, response speed, and self-regulation ability of the system are also increasing. In the wood processing industry, the heating system of factories is an important link to ensure normal production. Therefore, in order to further improve the production efficiency of the wood processing industry and enhance the stability and controllability of the heating system in wood processing production, this article takes into account the delay and coupling effects in the rapid heating …process, and combines fuzzy control with temperature control to study and establish a woodworking thermal mechanical coupling model based on fuzzy control algorithm. The results show that compared with traditional PID control, fuzzy control has advantages such as short response time, small overshoot, high steady-state accuracy, fast steady-state recovery, and good dynamic and static performance. Under the condition of rapid heating, the existence of delay effect weakens the effect of Thermal shock, while the coupling effect not only affects the propagation of thermoelastic waves in the elastic body, but also weakens the weakening effect of delay effect on Thermal shock to a certain extent. Show more

Keywords: Woodworking, fuzzy control, thermal-mechanical coupling, thermodynamic coupling, delay effect

DOI: 10.3233/JIFS-232242

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10183-10192, 2023

Authors: Sritha, P. | Valarmathi, R.S. | Poongodi, C.

Article Type: Research Article

Abstract: One of the best methods for assessing a baby’s health is foetal electrocardiography (FECG). Previously restricted to more widespread global disorders such as common ischemia, it is new way to investigating foetal heart rate irregularities. Current prenatal monitoring practices ignore critical FECG waveform elements that are the foundation of both pediatric, adult cardiac assessment, and instead of focusing solely on the foetal heart rate. In this paper we proposed Double Multiply-and-Accumulate (MAC) approach used for package operators into a single DSP block of commercial FPGAs, theoretically doubling the calculation speed for FECG monitoring. For a variety of technical reasons, they …were using the Space-Time Block Code (STBC) monitoring mode of operation. To strengthen the security of FECG monitoring, the Advanced Encryption Standard (AES) method may be used with the double MAC operators using STBC based FECG monitoring that has been developed. The solution was then assessed using state-of-the-art the Space-Time Block Code (STBC) based FECG techniques, and its validity was confirmed using Verilog simulation and FPGA synthesis. The calculation throughput of an STBC-based FECG monitoring system was found to be doubled using the Double MAC approach. Our implementation result demonstrates that keys are necessary for 128-bit AES encoding and decoding operations via VHDL-coded transformations. It is now more vital than ever to do a feasibility analysis of any hardware design due to the increase in the number of ways presented for minimizing noise. The efficiency increased (92%), and the delay was decreased to 19.35 ns by employing this double MAC architecture. The simulation results demonstrate that transformations for coding on an FPGA are implemented using the Xilinx VIVADO tool. Show more

Keywords: FECG monitoring, Double MAC, STBC based FECG, Verilog, AES, Xilinx

DOI: 10.3233/JIFS-234164

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10193-10211, 2023

Authors: Wang, Hui

Article Type: Research Article

Abstract: In Visual Communication Design (VCD), noise data is easy to appear, which reduces image quality and affects the effect of VCD. The non local mean image denoising algorithm is a good filtering denoising algorithm, but there are still issues of information interference and missing. To improve the performance of noise recognition and image denoising technology, this study proposes a non local mean image denoising algorithm based on machine learning technology. The whale optimization algorithm, as a machine learning technique, has good performance in seeking optimal solutions. Therefore, it is applied to optimize the filtering parameters of non local mean image …denoising algorithms to improve the perforGAmance of non local mean image denoising algorithms. To address the shortcomings of the whale optimization algorithm, BP neural network is introduced for optimization. Finally, the experiment uses the improved particle swarm optimization algorithm to optimize the BPNN and applies it to the recognition and classification of noise data. Combining the above contents, the IBINLM image denoising algorithm is constructed experimentally. It is verified that the IPSO-BPNN model’s loss value is 0.12; The recognition accuracy of the model for noise pixels is 98.64%; F1 value reaches 96.32%; The fitting degree reaches 0.983. The PSNR of IBINLM algorithm is 35.86 dB; MSE is 0.29; AUC value reaches 0.903. The results show that the IPSO-BPNN model and IBINLM image denoising algorithm have better performance compared to other models, which can improve the quality of visual communication works, playing an essential role in image transmission and storage in visual communication design. Show more

Keywords: Machine learning, non-local mean, image denoising, whale optimization algorithm, visual communication design

DOI: 10.3233/JIFS-234632

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10213-10225, 2023

Authors: Guo, Ying | Peng, Jinzhu | Ding, Shuai | Liang, Jing | Wang, Yaonan

Article Type: Research Article

Abstract: In this paper, a variable impedance control method is proposed for uncertain robotic systems based on a nonlinear force contact-based flexible environmental model. First, a nonlinear force contact model between the rigid manipulator and flexible environment is applied to the compliant control of the manipulator, which can avoid excessive force overshoot that usually exists in the traditional spring-damping environmental model. Then, to achieve better force/position tracking performances, a fuzzy-based adaptive variable impedance controller is designed based on the force contact-based flexible environmental model, where the impedance parameters are adjusted online through the force and position feedback of the robotic system, …and the fuzzy logic system is used to compensate the uncertainties. Moreover, the stability of the adaptive variable impedance control scheme is proved by the Routh stability criterion, and the boundness of all the signals in the closed-loop control system is guaranteed by the Lyapunov stability theorem. Finally, the effectiveness of the proposed method is verified by the simulation of a two-link manipulator, and the results demonstrate that the performances of position tracking are improved, while the force overshoot and oscillation time are reduced. Show more

Keywords: Variable impedance control, flexible environment, fuzzy logic system, force contact model, robotic system

DOI: 10.3233/JIFS-224250

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10227-10241, 2023

Authors: Kayyidavazhiyil, Abhilash

Article Type: Research Article

Abstract: Prediction of malicious attacks and monitoring of network behaviour is significant for providing security and mitigating the loss of credential information. In order to monitor network traffic and identify different types of attacks in the network, numerous existing algorithms have been provided for classifying unauthorized access from the authorized access. However, the traditional techniques have faced complications in satisfying the accuracy while making predictions of malicious activities. Detection accuracy have been addressed as a drawback which hinders in making appropriate identification of threats. In order to overcome such challenges, the proposed work is designed with effective IDS mechanism for detecting …and classifying the attacks taken from the UNSW-NB15 and NSL-KDD dataset. IDS (Intrusion Detection System) implementation is accomplished with three stages such as pre-processing is the initial phase in which scaling re-sizing of all images to similar width and height. Process of checking missing values reduces the computational complexities and enhances accuracy. Second stage is the novel feature-selection process accomplished by E-GSS (Enhanced Genetic Sine Swarm Intelligence) for selecting significant and optimal features. Finally, classification is the final phase in which intrusion is classified using novel DMH-ANN (Deep Meta-Heuristics Artificial Neural Network) which is internally being compared to three classifiers such as RF (Random Forest), NB (Naïve Bayes) and XG-Boost (Extreme Gradient). Experimental evaluation is carried out with the performance metrics such as accuracy, precision and recall and compared with existing algorithms for exhibiting the effectiveness of the proposed model. The research outcome reveals its efficiency in detecting and classifying attacks with greater accuracy. Show more

Keywords: Intrusion detection, UNSW-NB15 dataset, NSL-KDD, Genetic Sine Swarm, Metaheuristic ANN, Naïve Bayes, XG-Boost, random forest

DOI: 10.3233/JIFS-224283

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10243-10265, 2023

Authors: Vaishnavi, D. | Balaji, G.N.

Article Type: Research Article

Abstract: Due to the drastic increase in the generation of high-quality fake images in social networking, it is essential to design effective recognition approaches. Image/video manipulation defines any set of actions which can be carried out on digital content by the use of software editing approaches or artificial intelligence. A major kind of image and video editing comprises replicating the regions of the image, named as copy-move technique. Conventional image processing methods physically search for the pattern relevant to the replicated contents, restricting the utilization in massive classification of data. Contrastingly, the recently developed deep learning (DL) models have exhibited promising …performance over the traditional models. In this aspect, this paper presents a novel intelligent deep learning based copy move image forgery detection (IDL-CMIFD) technique. The proposed IDL-CMIFD technique intends to design a DL model to classify the candidate images into two classes: original and forged/tampered and then localized the copy moved regions. In addition, the proposed IDL-CMIFD technique involves the Adam optimizer with Efficient Net based feature extractor to derive a useful set of feature vectors. Moreover, chaotic monarch butterfly optimization (CMBO) with deep wavelet neural network (DWNN) model is applied for classification purposes. The CMBO algorithm is utilized to optimally tune the parameters involved in the DWNN model in such a way that the classification performance gets improved. The performance validation of the proposed model takes place on benchmark MICC-F220, MICC-F2000, MICC-F600 datasets. A wide range of comparative analyses is performed and the results ensured the better performance of the IDL-CMIFD technique in terms of different evaluation parameters. Show more

Keywords: Copy Move technique, image forgery, deep learning, hyperparameter tuning, metaheuristics

DOI: 10.3233/JIFS-230291

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10267-10280, 2023

Authors: Sri Geetha, M. | Grace Selvarani, A.

Article Type: Research Article

Abstract: Breast cancer is responsible for the deaths of hundreds of women every year. The manual identification of breast cancer has more difficulties, and have the possibility of error. Many imaging approaches are being researched for their potential to identify breast cancer (BC). Incorrect identification might sometimes result in unneeded therapy and diagnosis. Because of this, accurate identification of breast cancer may save a great number of patients from needing unneeded surgery and biopsies. Deep learning’s (DL) performance in the processing of medical images has substantially increased as a result of recent breakthroughs in the sector. Because of their improved capacity …to anticipate outcomes, deep learning algorithms are able to reliably detect BC from ultrasound pictures. Transfer learning is a kind of machine learning that reuses knowledge representations from public models that were built with the use of large-scale datasets. Transfer learning has been shown to often result in overfitting. The primary purpose of this research is to develop and provide suggestions for a deep learning model that is effective and reliable in the detection and classification of breast cancer. A tissue biopsy is obtained from the suspicious region in order to ascertain the nature of a breast tumor and whether or not it is cancerous. Tumors may take any of these forms. When the images have been reconstructed with the help of a variational autoencoder (VAE) and a denoising variational autoencoder (DVAE), a convolutional neural network (CNN) model is used. This will be the case because it opens up a new area of the field to be investigated. The histological subtypes of breast cancer are used in conjunction with the degree of differentiation to execute the task of breast cancer categorization. Show more

Keywords: Medical image classification, disease detection, deep learning, breast cancer, convolutional neural network (CNN), variationalautoencoder, histopathology image

DOI: 10.3233/JIFS-231345

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10281-10294, 2023

Authors: Gao, Caiwen | Zhang, Zhiqiang | Liu, Baoliang

Article Type: Research Article

Abstract: This paper extends the traditional multifactor population model from a probabilistic background to an uncertain background, allowing us to better account for the fact that the birth and death rates are sometimes affected by different, independent uncertain noises. The theory of multifactor uncertain differential equation is applied to analyze the novel model. First, a multifactor uncertain population model is developed and the solution of the model is obtained. Secondly, the stability in measure and stability in distribution of the multifactor uncertain population model are studied respectively, and the relationship between the two kinds of stability is further discussed. Then, a …method of moment estimation based on residuals is proposed for the unknown parameters in the multifactor uncertain population model. Finally, an example is given to illustrate the validity and rationality of the parameter estimation method. Show more

Keywords: Parameter estimation, residual, multifactor differential equation, stability

DOI: 10.3233/JIFS-232020

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10295-10303, 2023

Authors: Mu, Yongan | Liu, Wei | Lu, Tao | Li, Juan | Gao, Sheng | Wang, Zihao

Article Type: Research Article

Abstract: The self-adaptive multi-agent system requires adaptive adjustments based on the dynamic environment during its runtime. Heterogeneous agent can accomplish different task goals, enhance the efficiency of system operation, but its complex collaboration problem poses new challenges to the study of verification of adaptive policies for heterogeneous multi-agents. This paper proposes a runtime verification method for self-adaptive multi-agent systems using probabilistic timed automata. The method constructs a probabilistic timed automaton model by formally describing the functional characteristics of heterogeneous agents and integrating random factors in the environment to simulate the operation process of the self-adaptive multi-agent system. Regarding the collaboration logic …among heterogeneous agents, security constraints are established to ensure the security of state transition processes during system operation. Combining model checking with runtime quantitative verification methods to conduct experiment and applying it in the case of an intelligent unmanned parking system. Experimental results manifest the correctness of the cooperation logic between agents can effectively ensure the stability of the system at runtime. Significant improvement in system uptime and efficiency compared to the initial system without runtime quantitative validation. Show more

Keywords: Self-adaptive system, heterogeneous multi-agent, probabilistic timed automata, agent cooperation logic, runtime quantitative verification

DOI: 10.3233/JIFS-232397

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10305-10322, 2023

Authors: Xu, Zan | Lu, TongWei

Article Type: Research Article

Abstract: Some anomaly detection methods are based on CNN to fuse spatial and channel-wise information together within local receptive fields. However, the correlation between feature channels has not been fully utilized. Channel attention has been shown to model the interdependence between convolution feature channels and improve network representation. It is possible to introduce channel attention into anomaly detection. We attempt to directly embed the SE(Squeeze and Excitation) module into the convolutional layer but reduced anomaly detection performance. Therefore, we propose a lightweight channel attention module C-SE(Current Squeeze and Excitation) suitable for anomaly detection. C-SE module not only improves the representation ability …of depth convolutional neural network but also has a significant effect on texture anomaly detection. C-SE module body is constructed by average pooling and maximum pooling branches, which ensure that local salient features of the image are not lost. Then reduce the negative impact of feature calibration through a long connection. In addition, the improvement of classifier plays an important role. Experimental results have shown that the proposed method outperforms the Patch SVDD methods by 3% in image-level AUROC and 0.7% in pixel-level AUROC on the MVTec benchmark. The higher AUROC score and the faster rate of convergence prove the effectiveness of the method. Show more

Keywords: Anomaly detection, channel attention, feature calibration, texture, MVTec

DOI: 10.3233/JIFS-232677

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10323-10334, 2023

Authors: Manivannan, K. | Sathiamoorthy, S.

Article Type: Research Article

Abstract: In the last decades, Tuberculosis (TB) can be considered a serious illness affecting people over the globe and it leads to mortality when left untreated. Chest X-Ray (CXR) is the topmost selection for the recognition of pulmonary diseases in hospitals since it can be cost-efficient and easily available in many nations. But, manual CXR image screening is a huge load for radiologists, which results in a maximum inter-observer discrepancy rate. At present, Computer-Aided Detection (CAD) is a powerful imaging equipment for detecting and screening dangerous ailments. In recent times, Deep Learning (DL) based CAD schemes have demonstrated positive outcomes in …the recognition of TB diseases. This study introduces an Egret Swarm Optimization Algorithm with Deep Feature Fusion based Tuberculosis Classification (ESOA-DFFTC) technique on CXR Images. The presented ESOA-DFFTC technique utilizes feature fusion and tuning processes for the classification of TB. To accomplish this, the ESOA-DFFTC model first exploits the Gaussian Filtering (GF) approach for image denoising purposes. Next, the ESOA-DFFTC model performs a feature fusion process using three DL models namely ResNeXt-50, MobileNetv2, and Xception. To enhance the achievement of the DL models, the ESOA-based hyperparameter optimizer is implemented in the study. For TB classification, the ESOA-DFFTC methodology uses an Arithmetic Optimization Algorithm (AOA) with Weight-Dropped Long Short-Term Memory (WDLSTM) methodology. The investigational output of the ESOA-DFFTC system was examined on a benchmark medical imaging dataset. A wide comparative investigation stated the greater achievement of the ESOA-DFFTC system over other current algorithms. Show more

Keywords: Computer-aided diagnosis, machine learning, Tuberculosis, chest X-Ray images, feature fusion, Metaheuristics

DOI: 10.3233/JIFS-233975

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10335-10347, 2023

Authors: Fang, Yuhua | Xie, Zhijun | Chen, Kewei | Huang, Guangyan | Zarei, Roozbeh | Xie, Yuntao

Article Type: Research Article

Abstract: Traditional Simultaneous Localization and Mapping application in dynamic situations is constrained by static assumptions. However, the majority of well-known dynamic SLAM systems use deep learning to identify dynamic objects, which creates the issue of trade-offs between accuracy and real-time. To tackle this issue, this work suggests a unique dynamic semantics method(DYS-SLAM) for semantic simultaneous localization and mapping that strikes a trade-off between high accuracy and high real-time performance. We propose M-LK, an enhanced Lucas-Kanade(LK) optical flow method. This technique keeps the continuous motion and greyscale consistency assumptions from the original method while switching out the spatial consistency assumption for a …motion consistency assumption, reducing sensitivity to image gradients to identify dynamic feature points and regions efficiently. In order to increase segmentation accuracy while maintaining real-time performance, we develop a segmentation refinement scheme that projects 3D point cloud segmentation results into 2D object detection zones. A dense semantic octree graph is built in the interim to expedite the high-level process. Compared to the four equivalent dynamic SLAM approaches, experiments on the publicly available TUM RGB-D dataset demonstrate that the DYS-SLAM method offers competitive localization accuracy and satisfactory real-time performance in both high and low-dynamic scenarios. Show more

Keywords: Visual SLAM, object detection, dynamic environment, deep learning for visual perception

DOI: 10.3233/JIFS-234235

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10349-10367, 2023

Authors: Mao, Yaxin

Article Type: Research Article

Abstract: The process of attempting to estimate the future prices of particular stocks by utilizing historical data and various analytical tools, including deep learning algorithms, is called stock price prediction. Insurance providers’ overall approach and decisions to manage their risks, enhance their profitability, and give value to their policyholders are referred to as the insurance strategy. It requires various things to be considered, including underwriting procedures, pricing strategies, product creation, risk analysis, claims administration, and investment choices. This study proposed optimizing an insurance strategy and predicting securities prices using a deep learning algorithm. Initially, the real stock data sources for Microsoft …Corporation (MSFT) were gathered from Ping An Insurance Company of China (PAICC) and the Shanghai-based National Association of Securities Dealers Automated Quotation (NASDAQ). Normalization is the procedure used to preprocess data for the raw data. We suggest an Enhanced dragonfly-optimized deep neural network (EDODNN) with stock price forecasting and insurance. The outcomes demonstrate that the proposed model outperforms the current methodology and achieves accuracy, precision, recall, F1 score, R 2 , and RMSE. To display the effectiveness of the suggested system, its performance is compared to more established methods to obtain the highest level of efficiency for the research. Show more

Keywords: Deep learning, stock price prediction, insurance strategy, microsoft corporation (MSFT), enhanced dragonfly optimized deep neural network (EDODNN)

DOI: 10.3233/JIFS-234292

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10369-10379, 2023

Authors: Yuan, Jinhai | Li, Sisi | Fan, Xin

Article Type: Research Article

Abstract: Educators across different fields disseminate their knowledge and utilize digital technologies to improve student skills for their careers and sustainability. Students’ skills that are improved are verified based on assessment and knowledge application over different circumstances. The article investigates the impact of the effective educator’s knowledge assessment and their role in student skill development. The motivation for the research arises from the realization that teachers’ knowledge and their capacity for transferring skills and information to students successfully play a significant role in the quality of education. The goal of the study is to develop a GA2M that has been verified …and can be used by educators to improve their performance, enhance student’s results, and eventually progress educational practices to use Fuzzy methods for reasoning and to include new rules for improving knowledge to bridge the knowledge gap between educators and students’ skill growth. It requires a great effect by the educator to enhance their ability over successive performance improvement. This article analyzes the ability for better improvement using the proposed Guided Ability Assessment Model (GA2M). The proposed model discards the negative impact of the ability on students’ skill deterioration. Besides, the ratio of skill improvement across various new abilities and exposures is analyzed using Fuzzy inference. This analysis frames the interference using knowledge rules required for different circumstances. These rules are framed using existing skill implications and problem-solving ability. This proposed model proposes new rules for development of various abilities of educators. Based on their current ability, further training process for the educator’s skill development is prescribed. Therefore, the inference for fuzzification is performed for the positive impact on students’ skill development. If the inference succeeds, the assessment is leveraged between skill guidance and ability. Show more

Keywords: Digital assessment, educator ability, fuzzy model, student skill

DOI: 10.3233/JIFS-231074

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10381-10395, 2023

Authors: Luo, Zhi-Yong | Chen, Ya-Nan | Liu, Xin-Tong

Article Type: Research Article

Abstract: In cloud computing, optimizing task scheduling is crucial for improving overall system performance and resource utilization. To minimize cloud service costs and prevent resource wastage, advanced techniques must be employed to efficiently allocate cloud resources for executing tasks. This research presents a novel multi-objective task scheduling method, BSSA, which combines the Backtracking Search Optimization Algorithm (BSA) and the Sparrow Search Algorithm (SSA). BSA enhances SSA’s convergence accuracy and global optimization ability in later iterations, improving task scheduling results. The proposed BSSA is evaluated and compared against traditional SSA and other algorithms using a set of 8 benchmark test functions. Moreover, …BSSA is tested for task scheduling in cloud environments and compared with various metaheuristic scheduling algorithms. Experimental results demonstrate the superiority of the proposed BSSA, validating its effectiveness and efficiency in cloud task scheduling. Show more

Keywords: Cloud computing, task scheduling, multi-objective optimization, sparrow search algorithm

DOI: 10.3233/JIFS-232527

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10397-10409, 2023

Authors: Khan, Muhammad Ishfaq | Almazrooei, Abdullah Eqal | Yanhong, Li | Ibrar, Muhammad | Nazif, Fatima | Latif, Abdul

Article Type: Research Article

Abstract: Disaster Management Program plays a critical role in coordinating and implementing strategies to address emergencies and disasters, ranging from natural events like hurricanes, earthquakes, and wildfire to human-made incidents such as industrial accidents or terrorist attacks. Simultaneously, it is widely studied as a typical multi-attribute decision-making (MADM) problem. This paper investigates the concept of complex picture fuzzy sets (CPFS), an extension of picture fuzzy sets (PFS), achieved by the inclusion of a phase term. The existence of phase terms expand the scope of CPFS from real line to a complex plane of unit disc and highlight its originality by demonstrating …its capacity to handle both vagueness and periodicity simultaneously. In this paper, the complex picture fuzzy Hamy mean operator (CPFHM) and complex picture fuzzy dual Hamy mean operator (CPFDHM) is studied. The reason of selecting complex picture fuzzy Hamy mean operator (CPFHMO) is that it can find interrelationship among multi-input variables. Then the various properties of CPFHM and CPFDHM operator are described in depth. A multi-attributes group decision-making (MAGDM) technique for solving group decision-making problems is proposed based on these operators. The validity of the present technique is demonstrated by analyzing a disaster management problem. Furthermore we check the sensitivity of parameter k and apply the validity test on our proposed technique. Finally, a comprehensive comparison is provided between the proposed model and specific existing approaches, illustrating that the suggested decision model is superior and more advantageous than the existing employed methodologies. Show more

Keywords: Picture fuzzy set, complex picture fuzzy set, Hamy mean operator, multi-attribute group decision making, evaluation the disaster management program

DOI: 10.3233/JIFS-232529

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10411-10436, 2023

Authors: Feng, Qingyuan

Article Type: Research Article

Abstract: China’s education has entered the era of quality, and in order for higher vocational colleges to develop better, effective measures must be taken to improve the quality of education. Facing the continuous innovation of education in higher vocational colleges, it is necessary to strengthen institutional construction and constrain educational management with institutional constraints, which is the key to ensuring the education quality. The higher vocational education quality evaluation in the new era is regarded as multiple attribute decision-making (MADM). Recently, the EDAS and CRITIC model has been employed to solve MAGDM. The triangular fuzzy neutrosophic sets (TFNSs) are constructed as …an efficient tool for portraying the uncertain information during the higher vocational education quality evaluation in the new era. In this paper, the triangular fuzzy neutrosophic number EDAS (TFNN-EDAS) model based on the Hamming distance and Euclid distance is constructed to solve the MADM under TFNSs. The CRITIC method is utilized to obtain the weight information based on the Hamming distance and Euclid distance under INNSs. Finally, a numerical example of higher vocational education quality evaluation in the new era is constructed and some efficient comparisons are founded to verify the TFNN-EDAS method. Show more

Keywords: Multiple attribute decision making (MADM), triangular fuzzy neutrosophic sets (TFNSs), EDAS method, higher vocational education quality evaluation

DOI: 10.3233/JIFS-234044

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10437-10450, 2023

Authors: Tan, Lirui | Zheng, Qiuju | Chen, Junji

Article Type: Research Article

Abstract: Network security is one of the key concerns with wireless sensor networks. Because sensor nodes employ radio channel frequencies, which are riskier than traditional networks, the attacker may be able to force the node to compromise, disrupt data integrity, eavesdrop, or insert false data into the network, wasting network resources. Creating dependable sensor networks that offer the highest level of security while using the fewest resources is thus one of the problems. The designers of wireless sensor networks can take into account providing an efficient key management system that can enhance any efficiency features such as communication overhead, calculation rate, …memory demand, and energy consumption rate. The energy level of nodes is determined in this article using a novel approach based on fuzzy systems and simple to implement in both hardware and software. In this study, the memory needed to carry out the plan was decreased, and the search performance was raised by integrating elliptic curve cryptography with an AVL search tree and a LEACH model. Also, the frequency range of radio channels in this study is 2.4 GHz. Based on the theoretical analysis as well as the outcomes of the experiments, the suggested key management strategy for wireless sensor networks improves security while also reducing computational overhead by 23%, energy consumption by 14%, and memory consumption parameters by 14%. 18% of people have used the network. Additionally, it was demonstrated that the suggested approach is scalable and extendable. Because of this, the suggested technique has a wide range of applications in massive wireless sensor networks. Show more

Keywords: Effective key management, transaction security, homogeneous mobile wireless sensor networks

DOI: 10.3233/JIFS-233476

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10451-10466, 2023

Authors: Dong, Yanfeng | Wang, Meng

Article Type: Research Article

Abstract: At present, China’s football sports are relatively backward in training theory and practice. If you want to break out of Asia and enter the world, and gain a firm foothold in the international football arena, you must use a scientific and realistic attitude, absorb the successful experience of advanced football countries, reflect on our training concepts and practices, and deeply study the training laws of football, in order to find a way suitable for our development. Athletes’ competitive ability is the core issue of sports training. The failure of our football level is directly related to our systematic understanding of …athletes’ competitive ability. This problem has led to the separation of our training practice from the actual competition, making training unable to meet the needs of the competition. Only by solving this problem, can we improve the level of football in China. The football players’ competitive ability evaluation is affirmed as multiple attribute decision making (MADM). In such paper, motivated by the idea of cotangent similarity measure (CSM), the CSMs are extended to DVNSs and four CSMs are created under DVNSs. Then, two weighted CSMs are built for MADM under DVNSs. Finally, a numerical example for Football players’ competitive ability evaluation is affirmed and some comparative algorithms are produced to affirm the built method. Show more

Keywords: Multiple attribute decision making (MADM), double-valued neutrosophic sets (DVNSs), cotangent similarity measure (CSM), football players’ competitive ability evaluation

DOI: 10.3233/JIFS-231194

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10467-10476, 2023

Authors: Kolla, Bhavannarayanna | Venugopal, P.

Article Type: Research Article

Abstract: Breast cancer is a widespread and significant health concern among women globally. Accurately categorizing breast cancer is essential for effective treatment, ultimately improving survival rates. Moreover, deep learning (DL) has emerged as a widely adopted approach for precise medical image classification in recent years, showing promise in this domain. However, despite the availability of DL models proposed in the literature for automated classification of breast cancer histopathology images, achieving high accuracy remains challenging. A minor modification to pre-trained models and simple training strategies can further enhance model accuracy. Based on the approach, this paper proposed an anti-aliased filter in a …pre-trained ResNet-34 and a novel three-step training process to improve BC histopathology image classification accuracy. The training involves systematically unfreezing layers and imposing additional constraints on the rate of change of learnable parameters. In addition, four-fold on-the-fly data augmentation enhances model generalization. The Ada-Hessian optimizer adjusts learning rates based on first and second-order gradients to improve convergence speed. The training process utilizes a large batch size to minimize the training loss associated with batch normalization layers. Even with the limited GPU size, the gradient accumulation technique achieves a large batch size. Collectively, these strategies minimize training time while maintaining or improving the accuracy of BC histopathology image classification models. In the experimental implementation, the proposed architecture achieves superior results compared to recent existing models, with an accuracy of 98.64%, recall (98.98%), precision (99.35%), F1-Score (99.17%), and MCC (97.36%) for binary classification. Similarly, the model achieves an accuracy of 95.01%, recall (95.01%), precision (94.95%), F1-Score (94.94%), and MCC (93.42%) for the eight-class category of BC images. Show more

Keywords: Deep learning, anti-aliased ResNet, BreakHis, breast cancer, fine-tuning, transfer learning

DOI: 10.3233/JIFS-231563

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10477-10495, 2023

Authors: Sowmya, S. | Jose, Deepa

Article Type: Research Article

Abstract: In order to assess the fetus health and make timely decisions throughout pregnancy, Fetal Electrocardiography (FECG) monitoring is essential. Huge datasets for electrocardiograms are freely accessible from Physionet ATM Dataset1- Abdominal and Direct Fetal ECG Database (adfecgdb), Dataset2- Fetal ECG Synthetic Database (fecgsyndb), Dataset3- Non-Invasive Fetal ECG Database(nifecgdb). In this study, categorization is done based on normal and abnormal (Atrial fibrillation) FECG from three online dataset which contains FECG recordings as major details. Deep learning models like Transfer Learning (TL) and Convolutional Neural Networks (CNN) are being investigated. The composite abdominal signal and the FECG are separated using a wavelet …transform approach. The best model for categorizing the parameters of the FECG is determined through a comparative analysis and performance is improved using Continuous Wavelet Transform (CWT). The accuracy of the CNN-based technique is found to be 98.59%, whereas the accuracy of the transfer learning model is 99.01% for FECG classification. The computation of metric parameters for all the datasets is done. The classification of normal and abnormal (Atrial fibrillation) is best performed in TL model compared to CNN. Real-time data analysis is done for PQRST plotting and comparative study is done using Net Reclassification Improvement (NRI) and obtained NRI = 13%, z static 0f 3.7641, p -Value of 0.00016721. Acute Myocardial Infraction (AMI) identification is done based on ST segment of Maternal ECG (MECG) images to analyze the heart attack risk. The proposed work can be utilized to track FECG waveforms in real-time for wearable technology because of its end-to-end properties and expandable intrinsic for diagnosing multi-lead heart disorders. Show more

Keywords: Fetal electrocardiogram, convolutional neural networks, transfer learning, physio net ATM, deep learning models

DOI: 10.3233/JIFS-231681

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10497-10514, 2023

Authors: Deepika, S. | Anandakumar, S. | Bhuvanesh Kumar, M. | Baskar, C.

Article Type: Research Article

Abstract: In the present marketing environment, choosing the right suppliers is very difficult for any construction company. Current supplier selection models in the construction industry often suffer from limitations such as incomplete criteria coverage, inadequate handling of uncertainties, and oversimplification of decision-making, leading to sub-optimal supplier choices and project risks. This paper aims in selecting the best suppliers among the different M-Sand environment suppliers. In this study 13 qualitative criterions are selected by the expert team. For handling the attributes, uncertainties, vagueness associated with supplier selection problems the Fuzzy Delphi, Fuzzy Analytical hierarchal Process (AHP) and Fuzzy Technique for order preference …by similarity to ideal solution (TOPSIS) methods were chosen. In the first phase of this study, Fuzzy Delphi Method is employed to select the 5 significant criterions. These criterions can be used to help the construction company in the direction to choose the right suppliers at the end. During the second phase, one of the significant Multi-criteria Decision Making Method called AHP is employed with extended support of fuzzy logic to evaluate the weightage of each criterion. Further ranking of various alternative suppliers are done by Fuzzy TOPSIS model. The ranking results indicate that A2 is the best supplier followed by A1 and A2. The third phase of this study deals with analyzing both the qualitative and quantitative criteria, hence Data Envelopment Analysis (DEA) is adopted to correlate the criteria. This is done to select efficient suppliers. The develop model is demonstrated in the construction industry. Show more

Keywords: Supplier selection, multi-criteria decision making method, fuzzy delphi method, fuzzy AHP, Fuzzy TOPSIS and DEA model.

DOI: 10.3233/JIFS-231790

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10515-10528, 2023

Authors: Wang, Liyang | Yang, Xiao

Article Type: Research Article

Abstract: Evaluating English teaching quality is vital for improving knowledge-based developments through communication for different aged students. Teaching quality assessment relies on the teachers’ and students’ features for constructive progression. With the development of computational intelligence, optimization and machine learning techniques are widely adapted for teaching quality assessment. In this article, a Quality-centric Assessment Model aided by Fuzzy Optimization (QAM-FO) is designed. This optimization approach validates the student-teacher features for a balanced model assessment. The distinguishable features for improving students’ oral and verbal communication from different teaching levels (basic, intermediate, and proficient) are extracted. The extracted features are the crisp input …for the fuzzy optimization such that the recurring fuzzification detains the least fit feature. Such features are replaced by the level-based teaching and performance feature that differs from the previous fuzzy input. This replacement is pursued until a maximum recommendable feature (performance/ learning) is identified. The identified feature is applicable for different teaching levels for improving the quality assessment. Therefore, the proposed optimization approach provides different feasible recommendations for teaching improvements. Show more

Keywords: English teaching, fuzzy optimization, quality assessment, recommendation model

DOI: 10.3233/JIFS-232034

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10529-10543, 2023

Authors: Bai, Xuemei | Tan, Jiaqi | Hu, Hanping | Zhang, Chenjie | Gu, Dongbing

Article Type: Research Article

Abstract: The paper proposes a deep learning model based on Chebyshev Network Gated Recurrent Units, which is called Spectral Graph Convolution Recurrent Neural Network, for multichannel electroencephalogram emotion recognition. First, in this paper, an adjacency matrix capturing the local relationships among electroencephalogram channels is established based on the cosine similarity of the spatial locations of electroencephalogram electrodes. The training efficiency is improved by utilizing the computational speed of the cosine distance. This advantage enables our method to have the potential for real-time emotion recognition, allowing for fast and accurate emotion classification in real-time application scenarios. Secondly, the spatial and temporal dependence …of the Spectral Graph Convolution Recurrent Neural Network for capturing electroencephalogram sequences is established based on the characteristics of the Chebyshev network and Gated Recurrent Units to extract the spatial and temporal features of electroencephalogram sequences. The proposed model was tested on the publicly accessible dataset DEAP. Its average recognition accuracy is 88%, 89.5%, and 89.7% for valence, arousal, and dominance, respectively. The experiment results demonstrated that the Spectral Graph Convolution Recurrent Neural Network method performed better than current models for electroencephalogram emotion identification. This model has broad applicability and holds potential for use in real-time emotion recognition scenarios. Show more

Keywords: Electroencephalogram, emotion recognition, chebyshev network gated recurrent units, spectral graph convolution recurrent neural network, adjacency matrix

DOI: 10.3233/JIFS-232465

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10545-10561, 2023

Authors: Xian, Luo | Tian, Lan

Article Type: Research Article

Abstract: In the era of big data, the exponentially increasing data volume and emerging technical tools have put forward new requirements for enterprise information management. Therefore, it is of great significance to enhance the core competitiveness of enterprises to explore how big data can empower the innovation of enterprise information management. Intelligent transportation system combines a variety of technologies and applies them to a large-scale transportation management system, so as to make a reasonable dispatch of traffic conditions. Aiming at the problem of the relatively low accuracy of bus passenger flow forecasting with the existing models, a short-term passenger flow prediction …model combining Stacked Denoising Auto Encoder (SDAE) and improved bidirectional Long-short Term Memory network (Bi-LSTM) is proposed. First, the SDAE model is used to fill in the missing bus passenger flow data, the characteristics of the bus passenger flow data are effectively utilized, and the data with rich information is used to predict the missing values with high accuracy. Second, Bi-LSTM model combined with attention mechanism is used for short-term bus passenger flow prediction. Considering that the data sequence of bus passenger flow is relatively long and there is a two-way information flow, the BiLSTM neural network is used for prediction tasks, and the influence of key factors is highlighted through attention weights to mine the internal laws of passenger flow data. The experimental results show that the proposed method achieves the lowest prediction error among all the comparison methods in the task of short-term bus passenger flow prediction on the public transportation dataset, with MAE, MRE, and RMSE values of 6.014, 0.052, and 9.874, respectively. These findings confirmed the effectiveness of the new model in the passenger flow prediction field. Show more

Keywords: Intelligent transportation system, passenger flow prediction, stacked denoising autoencoder, bidirectional long short-term memory network, attention mechanism introduction

DOI: 10.3233/JIFS-232979

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10563-10577, 2023

Authors: Fan, Kun | Hu, Yanrong | Liu, Hongjiu | Liu, Qingyang

Article Type: Research Article

Abstract: Accurately predicting soybean futures fluctuations can benefit various market participants such as farmers, policymakers, and speculators. This paper presents a novel approach for predicting soybean futures price that involves adding sequence decomposition and feature expansion to an Long Short-Term Memory (LSTM) model with dual-stage attention. Sequence decomposition is based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method, a technique for extracting sequence patterns and eliminating noise. The technical indicators generated enrich the input features of the model. Dual-stage attention are finally employed to learn the spatio-temporal relationships between the input features and the target sequence. The …research is founded on data related to soybean contract trading from the Dalian Commodity Exchange. The suggested method surpasses the comparison models and establishes a fresh benchmark for future price forecasting research in China’s agricultural futures market. Show more

Keywords: Soybean futures, time series forecasting, attention mechanism, sequence decomposition, technical indicator

DOI: 10.3233/JIFS-233060

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10579-10602, 2023

Authors: Jingjing, Huang | Xu, Zhang

Article Type: Research Article

Abstract: In view of the individual differences in learners’ abilities, learning objectives, and learning time, an intelligent recommendation method for offline course resources of tax law based on the chaos particle swarm optimization algorithm is proposed to provide personalized digital courses for each learner. The concept map and knowledge structure theory are comprehended to create the network structure map of understanding points of tax law offline courses and determine the learning objectives of learners; the project response theory is used to analyze the ability of different learners; According to the learners’ learning objectives and ability level, the intelligent recommendation model of …offline course resources of tax law is established with the minimum concept difference, minimum ability difference, minimum time difference, and minimum learning concept imbalance as the objective functions; Through the cultural framework, the chaotic particle swarm optimization algorithm based on the cultural framework is obtained by combining the particle swarm optimization algorithm and the chaotic mapping algorithm; The algorithm is used to solve the intelligent recommendation model, and the intelligent recommendation results of offline course resources in tax law are obtained. The experiential outcomes indicate that the process has a smaller inverse generation distance, larger super-volume, and smaller distribution performance index when solving the model; that is, the convergence performance and distribution performance of the model is better; This method can effectively recommend offline course resources of tax law for learners intelligently, and the minimum normalized cumulative loss gain is about 0.75, which is significantly higher than other methods, that is, the effect of intelligent recommendation is better. Show more

Keywords: Chaotic mapping, particle swarm, optimization algorithm, offline courses of tax law, resource intelligence recommendation

DOI: 10.3233/JIFS-233095

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10603-10617, 2023

Authors: Alsuwat, Emad

Article Type: Research Article

Abstract: Machine learning (ML) techniques play a crucial role in producing precise predictions without the use of explicit programming by utilizing representative and unbiased data. These methods, which are a subset of artificial intelligence (AI), are used in a variety of settings, including recommendation engines, spam filtering, malware detection, classification, and predictive maintenance. While ML algorithms improve results, they also present security and privacy threats, especially in the face of adversarial ML attacks such as data poisoning assaults that can undermine data modeling applications. This study introduces SecK2, a cutting-edge ML method developed to stop dangerous input from entering ML models. …The scalability of SecK2 is proved through meticulous experimental research, revealing its astonishing capacity to identify data poisoning attacks at a previously unheard-of pace. As a result, SecK2 becomes a valuable tool for guaranteeing the reliability and security of ML models. Our suggested method produces outstanding results by a variety of criteria. Notably, it achieves a noteworthy 61% convergence rate and an exceptional 89% attack detection rate. Additionally, it offers a phenomenal 96% throughput while protecting data integrity at 53%. The technique also boasts impressive Validation accuracy of 96% and Training accuracy of 92%. The suggested technology offers a strong and reliable barrier against the rising danger of data poisoning attacks. ML practitioners can have more faith in their models, thanks to SecK2’s capabilities, protecting against potential adversarial assaults and preserving the dependability of ML-based applications. Show more

Keywords: Data poisoning attacks, machine learning, privacy prediction, malicious data

DOI: 10.3233/JIFS-233942

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10619-10633, 2023

Authors: Nie, Kuang | Langari, Reza

Article Type: Research Article

Abstract: Surface electromyography (sEMG) signals have great potential for predicting upper limb motion. Although prior investigations have explored diverse applications of sEMG signal analysis, but few studies have focused on real-time motion prediction within the context of upper limb configuration space. Additionally, previous research has not adequately considered individual variability in sEMG features. This study aims to accomplish two main objectives. Firstly, it seeks to examine the dissimilarities in signal distribution across different subjects when employing various features. Additionally, the study aims to establish a correlation between signal distribution patterns and the model’s predictive accuracy. Secondly, the study introduced a personalized …standardization (PSD) technique, which will serve to normalize the shape of the signal distribution across different subjects, thereby addressing the inter-individual differences in sEMG features. A bi-directional long short-term memory (Bi-LSTM) network is employed to estimate the real-time moving intention of the upper limb after applying the PSD technique. The analysis of signal distribution involved nine combinations of features, encompassing six features, namely mean absolute value (MAV), wave length (WL), variance (VAR), root mean square (RMS), mean frequency (MNF) and median frequency (MDF). To assess predictive capabilities, several models were evaluated. Remarkably, the distribution analysis clearly demonstrated that the shape of the signal distribution notably influences the model’s performance. Accroding to results, the incorporation of the PSD technique resulted in a notable improvement in the accuracy of the Bi-LSTM model, which leds to an enhancement of up to 2.8 percentage points in predictive accuracy. Additionally, the Bi-LSTM model emerged as the highest-performing model among all the compared models during the analysis. These findings underscore the importance of considering individual variability in sEMG features when developing predictive models for upper limb motion and highlight the potential benefits of employing the PSD technique to enhance model performance. Show more

Keywords: Surface electromyography, Real-time motion prediction, Deep Learning, Signal pre-processing

DOI: 10.3233/JIFS-234018

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10635-10648, 2023

Authors: Gui, Zhen

Article Type: Research Article

Abstract: The task of multi-label text classification involves assigning a set of related labels to a given document. However, there are three main problems with this task. Firstly, the joint modeling of label-text and label-label relationships is inadequate. Secondly, the semantic mining of the label itself is insufficient. Lastly, the utilization of the internal structure information of the label is ignored. To address these issues, a new multi-label text classification method has been proposed. This method is based on joint attention and shared semantic space. The joint multi-head attention mechanism models the relationship between labels and documents as well as the …relationship between labels simultaneously. This helps to avoid error transmission and utilizes the interaction information between them. The decouple shared semantic space embedding method improves the method of using labels semantic information and reduces deviation in the phase of modeling correlation. The hierarchical hinting method based on prior knowledge relies on the prior knowledge in the pre-trained model to exploit the labels hierarchy information. Experimental results have shown that this proposed method is superior to existing multi-label text classification methods in public datasets. Show more

Keywords: Multi-label text classification, attention mechanism, label representation, semantic embedding, pre-trained model

DOI: 10.3233/JIFS-234151

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10649-10659, 2023

Authors: Deng, Yu | Zhang, Wenxia

Article Type: Research Article

Abstract: In recent years, due to the rapid development of internet technology, the integration process of digital technology and financial services has accelerated. Digital Financial inclusion has emerged as the times require, becoming an important force to promote private enterprises to get out of financing difficulties. The development level evaluation of digital inclusive finance is a classical multiple attribute group decision making (MAGDM) problems. Recently, Recently, the Exponential TODIM(ExpTODIM) and (grey relational analysis) GRA method has been used to cope with MAGDM issues. The intuitionistic fuzzy sets (IFSs) are used as a tool for characterizing uncertain information during the development level …evaluation of digital inclusive finance. In this paper, the intuitionistic fuzzy Exponential TODIM-GRA (IF-ExpTODIM-GRA) method is built to solve the MAGDM under IFSs. In the end, a numerical case study for development level evaluation of digital inclusive finance is supplied to validate the proposed method. The main contributions of this paper are outlined: (1) the ExpTODIM and GRA method has been extended to IFSs; (2) Information Entropy is used to derive weight under IFSs. (3) the IF-ExpTODIM-GRA method is founded to solve the MAGDM under IFSs; (4) a numerical case study for development level evaluation of digital inclusive finance and some comparative analysis are supplied to validate the proposed method. Show more

Keywords: Multiple attribute group decision making (MAGDM), intuitionistic fuzzy sets (IFSs), ExpTODIM, GRA, digital inclusive finance

DOI: 10.3233/JIFS-234827

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10661-10673, 2023

Authors: Chen, Ze | Lu, Ning | Hou, Botao | Liu, Xin | Zuo, Xiaojun

Article Type: Research Article

Abstract: In order to improve the effect and accuracy of risk source identification, this paper studied the network security risk source identification model of power CPS system based on fuzzy artificial neural network. The network security risk source index system of power CPS system was constructed, and the dimension of index data was reduced by principal component analysis. Fuzzy theory is used to process the index data after dimension reduction, and the comprehensive membership vector of each index is obtained. The dynamic clustering algorithm is used to determine the number of hidden layer units of radial basis function neural network, and …the network security risk source identification model is established. Finally, the quantitative value of risk source identification is output. The experimental results show that the model can effectively reduce the dimension of the network security risk source index data of the power CPS system. The optimal distance threshold of the hidden layer is 4.2, and the optimal number of units is 6. In the final identification results, four severe risk sources and five moderate risk sources were obtained, and the quantitative values of risk source identification of each index were 63, 70, 71, 77, 65, 89 and 96, respectively, indicating that the model can effectively identify network security risk sources of power CPS systems. With the increase of the proportion of communication nodes removed, when there are various types of security vulnerability information, the mean square error value of the model is always lower than the set threshold, indicating that the model has high recognition accuracy. Show more

Keywords: Fuzzy theory, artificial neural network, power CPS system, network security, risk sources, identification model

DOI: 10.3233/JIFS-224090

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10675-10691, 2023

Authors: Kamran, Muhammad | Ashraf, Shahzaib | Salamat, Nadeem | Naeem, Muhammad | Hameed, Muhammad Shazib

Article Type: Research Article

Abstract: One of the hottest areas for applying the solutions currently available is the internet of things-based smart housing society architecture and its uncertainty analysis. When intelligent parking, waste management, public transportation, public safety, and other automatic methods for housing society’s growth were implemented, it became even more crucial. An intelligent, smart system is necessary to manage these problems and provide smooth services. Additionally, it will be helpful in reducing issues with time waste and societal safety. However, the issue comes up when describing accurate, approximate, or questionable parking, transit, safety, and waste management areas. This paper discusses several mathematical solutions …for the smart housing society that use fuzzy rough sets, probabilistic hesitant fuzzy sets, and their extensions with neutrosophic sets. For further growth, a few studies on the graphic display of the evolution of the smart housing society are also considered. The rough set theory can be useful when dealing with imprecise, incomplete, or indeterminate data sets. The core contribution of this work is the construction of a novel generalized notion of a single-valued neutrosophic probabilistic hesitant fuzzy rough set (SV-NPHFRS), which is a hybrid structure of the single-valued neutrosophic set, the probabilistic hesitant fuzzy set, and the rough set. In contrast to the present literature, the underlying idea of SV-NPHFRS is that it is a powerful mathematical tool for managing uncertainty and imperfect information. This method is particularly beneficial when there are a number of competing criteria to consider. The aggregation technique plays an important role in decision-making concerns, especially when more competing criteria are present. In the study’s comparison phase, the suggested decision support system is compared to relevant existing approaches. The results suggest that, in terms of choice flexibility, the suggested technique has the potential to outperform the drawbacks of the current decision-making tools. The proposed study is expected to be useful for a number of researchers conducting future work on housing societies, waste management, public safety diagnostics, and hybridization. Show more

Keywords: Single-valued neutrosophic probabilistic hesitant fuzzy rough sets, aggregation operators, decision making

DOI: 10.3233/JIFS-224364

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10693-10737, 2023

Authors: Suo, Chunfeng | Li, Yongming | Guo, Li

Article Type: Research Article

Abstract: The polygonal interval-valued fuzzy number is constructed based on the polygonal fuzzy number and the interval-valued fuzzy number. Its main feature is that the linear operation of finite ordered points reduces the complexity of traditional interval-valued fuzzy number operations. This research presents a generalized distance formula between two polygonal interval-valued fuzzy numbers and explores topological properties under the distance of polygonal interval-valued fuzzy numbers. In addition, we adopt the TOPSIS (technique for order preference by similarity to an ideal solution) and prospect theory approach for the multi-attribute decision-making problem. The information of attributes describes with polygonal interval-valued fuzzy numbers, and …we then implement optimized ranking on the alternatives according to the profit and loss ratio. Finally, we verify the effectiveness and practicability of the decision-making method and fuzzy numbers at polygonal interval-valued fuzzy numbers in e-commerce risk assessment. Show more

Keywords: Polygonal interval-valued fuzzy number, human resource recruitment, generalized distance, arithmetic operation

DOI: 10.3233/JIFS-230040

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10739-10755, 2023

Authors: Cao, Xianghong | Wu, Kunning | Geng, Xin | Wang, Yongdong

Article Type: Research Article

Abstract: With the acceleration of urbanization, the frequency of building fire incidents has been increasing year by year. Therefore, rapid, efficient, and safe evacuation from buildings has become an urgent and important task. A construction fire escape path planning method based on an improved NavMesh algorithm is proposed in this paper. Firstly, by using the method of local updates in the navigation grid, redundant computation is reduced, and the update time of the improved algorithm is about 6.8% of that of the original algorithm, immediate generation of navigation is achieved. Secondly, the heuristic function of the pathfinding algorithm is improved, and …a multi-exit path planning mechanism is proposed to achieve more efficient, which can quickly plan a safe evacuation path away from the spreading fire and smoke in the event of a fire. Finally, a new evaluation index called Navigation Grid Complexity (NGC) is proposed and demonstrated to measure the quality of navigation grids. The feasibility and effectiveness of the proposed method are validated through simulation experiments on actual building models, which can provide real-time, efficient, intelligent, and safe path planning for rapid evacuation of evacuees in the fire scene. Show more

Keywords: NavMesh, path planning, fire emergency evacuation, dynamic environments

DOI: 10.3233/JIFS-232681

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10757-10768, 2023

Authors: Ran, Lang | Hong, Chaoqun | Zhang, Xuebai | Tang, Chaohui | Xie, Yuhong

Article Type: Research Article

Abstract: Human pose estimation is a challenging visual task that relies on spatial location information. To improve the performance of human pose estimation, it is important to accurately determine the constraint relationship among keypoints. To address this, we propose MfvPose, a novel hybrid model that leverages rich multi-scale information. The proposed model incorporates the HRFOV module, which uses cascaded atrous convolution to maintain high-resolution representations of the backbone extractor and enrich the multi-scale information. In addition, we introduce learnable scalar weights to the Transformer encoder. In detail, it involves a multiplication by a diagonal matrix with learnable scalar weights on output …of each residual block, which improves the dynamics of model training and enhances the accuracy of human pose estimation. It is experimentally shown that our proposed MfvPose achieves promising results on various benchmarks. Show more

Keywords: Receptive field, multi-head self-attention, atrous convolution, human pose estimation

DOI: 10.3233/JIFS-233375

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10769-10778, 2023

Authors: Baskar, A. | Rajaram, A.

Article Type: Research Article

Abstract: Mobile Adhoc Network (MANET) is a dynamic network with mobility nodes. Emerging applications for MANETs in real-time present numerous research challenges. Specifically, the mobile nodes’ dynamic character hinders the routing efficacy in MANET. Previous algorithms for routing like DSDV DSR, AODV, and are inefficient due to an ineffective route discovery method. Route selection becomes more complex and energy-intensive for large-scale applications, such as air pollution monitoring. For air pollution monitoring applications, this research seeks to improve data delivery while reducing energy consumption. In this work, we proposed DeepOptimizer for achieving optimal data transmission. First, the network is segregated into multiple …clusters using the Rough set theory. In the all clusters, Cluster Head is accountable for split a data into normal and emergency. This process is performed by grouping data by K++ means algorithm. For emergency data, Graph-based Route Selection (GRS) algorithm. This is the fast algorithm that selects the optimal route. On the other hand, the normal data transmission route is selected by the Deep-SpikeQNetwok-based Whale Optimization (WO) algorithm. Finally, the network is tested through simulations made in ns-3 based on network lifetime, throughput, energy level, delay and packet delivery ratio. Show more

Keywords: Deep routing, emergency data transmission, spiking networks, MANET

DOI: 10.3233/JIFS-233425

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10779-10797, 2023