Journal of Intelligent & Fuzzy Systems - Volume 44, issue 6

Authors: Senthilkumar, V.M. | Thenmozhi, S. | Kumudavalli, M.V. | Yedukondalu, U.

Article Type: Research Article

Abstract: The Severe Acute Respiratory Syndrome (SARS) are caused by the strain of the corona virus causes cold and influenza. In recent years, the covid pandemic spread throughout the world killing millions of people. The fatality rate has increased and it also leads to pneumonia for breathing problems. Several methods like wavelet filter banks, time series methods, Neural networks was developed for the diagnosis of severe acute respiratory syndrome coronavirus, still the accuracy can be improved. Less works is carried out for hardware implementation for syndrome detectors. This proposed work represents the FPGA (Field Programmable Gate Array) implementation of the hybrid …method using Convolutional Recurrent neural network and Independent Components Analysis (ICA). The architecture extracts the ccomplex features from ECG (Electrocardiogram) samples. The hybrid Statistical and Recurrent Neural Network (RNN) Architecture implementation in a real time hardware detects the Severe Acute Respiratory Syndrome presented. The proposed method can be implemented in MATLAB, Embedded and DSP (Digital Signal Processor). But, the FPGAs consume less power computationally efficient. Since, ICA is an efficient method due to its blind source separation property accumulate the extraction of features accurate described. The mathematical model for the analysis of ECG signal using RNN is analyzed and based on that the proposed model is selected. On investigation the hybrid method using the statistical and neural network model is efficient in the analysis of biomedical signal especially ECG. The proposed ICA based RNN model is mathematically evaluated and tested with real time data. For implementation, Quartus software is used for effectiveness of the proposed model. Show more

Keywords: Field programmable gate array, recurrent neural network, independent component analysis, electrocardiogram, severe acute respiratory syndrome

DOI: 10.3233/JIFS-224289

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8803-8816, 2023

Authors: Wang, Hua | Wang, Zhi-Ming | Cui, Xiu-Tao | Li, Long

Article Type: Research Article

Abstract: Considering the heterogeneity, diffusive shape, and complex background of tumors, automatic segmentation of hepatic lesions in computed tomography (CT) images has been considered a challenging task. The performance of existing methods remains subject to segmentation uncertainties, especially in tumor boundary regions. The pixel information in these regions will be affected by both sides, thereby exposing the segmentation results to missing marks. To this end, a new network architecture named Two Direction Segmentation U-Net (TDS-U-Net) is hereby designed based on the classic Attention U-Net to tackle this problem. As the most important blocks of the Attention U-Net network, attention gates (AGs) …focus on the target structures of different shapes and sizes. In the last layer of TDS-U-Net, two dichotomous convolutional networks are applied to obtain the segmentation maps of the liver and the tumor respectively. Superimposing two segmented maps to obtain the final image addresses the above problems. The entire structure has been verified on two widely accepted public CT datasets, LiTS17 and KiTS19. Compared with the state of the art, this method exhibits superior performance and excellent shape extractions with high detection sensitivity, perfectly demonstrating its effectiveness in medical image segmentation. Show more

Keywords: Attention gates, CT, deep learning, liver tumor segmentation, kidney tumor segmentation, U-Net

DOI: 10.3233/JIFS-221111

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8817-8825, 2023

Authors: Pavithra, R. | Ramachandran, Prakash

Article Type: Research Article

Abstract: A spectrum-image based representation of machine vibration signals with deep convolution neural network is proposed for machine fault classification in which the convolution layer is used for automatic feature extraction as an alternate to the conventional feature-based methods. Two different forms of spectrum representations are proposed, one based on the short time Fourier transform of the original signals and the other based on the short time Fourier transform of the intrinsic mode functions acquired by empirical mode decomposition. Empirical mode decomposition has its own merits in discriminating non stationary signals and the novelty of the work is to use the …short time Fourier transform of intrinsic mode functions with deep convolution neural network model. The classification and validation accuracy of the model are investigated with respect to epochs. It is demonstrated that both spectrum-based techniques perform good with 100% model accuracies in a numerical experiment of binary classification on a bearing dataset that comprises of normal and faulty signals. In another experiment using milling data set, short time Fourier transform of intrinsic mode functions representation performs better with 100% training accuracy, F1 score of 0.8933 which is better than that of using short time Fourier transform of raw signals whose training accuracy is 64% and F1 score of 0.7486. The numerical study shows that the empirical mode decomposition based spectrum representation delivers the highest accuracy in the learning model obviating the necessity for independent feature extraction, feature selection, and dimension reduction. The numerical experiment is extended using empirical mode decomposition based spectrums for multiple class classification problems in bearing dataset. The confusion matrix obtained for 10 classes, shows that validation accuracy is 100% for all classes. The performance comparison throws light on the merits of empirical mode decomposition spectrum method over other state of the art methods. Show more

Keywords: Convolutional neural network (CNN), empirical mode decomposition (EMD), intrinsic mode function (IMF), short-time Fourier transform (STFT)

DOI: 10.3233/JIFS-223012

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8827-8840, 2023

Authors: Qiu, Guangying | Tao, Dan | Su, Housheng

Article Type: Research Article

Abstract: The fault diagnosis of vessel power equipment is established by the manual work with low efficiency. The knowledge graph(KG) usually is applied to extract the experience and operation logic of controllers into knowledge, which can enrich the means of fault judgment and recovery decision. As an important part of KG building, the performance of named entity recognition (NER) is critical to the following tasks. Due to the challenges of information insufficiency and polysemous words in the entities of vessel power equipment fault, this study adopts the fusion model of Bidirectional Encoder Representations from Transformers (BERT), revised Convolutional neural network (CNN), …bidirectional long short-term memory (BiLSTM), and conditional random field (CRF). Firstly, the adjusted BERT and revised CNN are respectively adopted to acquire the multiple embeddings including semantic information and contextual glyph features. Secondly, the local context features are effectively extracted by adopting the channel-wised fusion structures. Finally, BiLSTM and CRF are respectively adopted to obtain the semantic information of the long sequences and the prediction sequence labels. The experimental results show that the performance of NER by the proposed model outperforms other mainstream models. Furthermore, this work provides the foundation of the tasks of intelligent diagnosis and NER in other fields. Show more

Keywords: Vessel, power equipment, named entity recognition, BERT

DOI: 10.3233/JIFS-223200

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8841-8850, 2023

Authors: Sharma, Surya Prakash | Singh, Laxman | Tiwari, Rajdev

Article Type: Research Article

Abstract: In the current market scenario, online customer reviews had a significant impact on boosting the sale of online products. Recently, there has been exponential growth in e-commerce industry owning to the online customer reviews. Over the years, researchers has observed the importance of online consumer reviews for purchasing online products. Hence, in this study, authors made an attempt to develop an efficient convolutional neural network (CNN) based classification model that aims to predict the usefulness of product reviews with higher accuracy on two different types of data sets (i.e., search product and experienced product). In our proposed study, to determine …the usefulness of a review in terms of structural, linguistic, sentimental, lexical, and voting feature sets, we build a deep learning model to predict the review helpfulness as a binary classification problem. The performance of the proposed method is evaluated in terms of accuracy, precision, F1 score etc. and had been compared against the various leading machine learning (ML) state of art models viz., K-nearest neighbor (KNN), Linear regression (LR), Gaussian Naive Bays (GNB), Linear Discriminant Analysis (LDA) etc. The results demonstrate that CNN achieved better classification performance in comparison to other state of art models, with highest accuracy of 99.26% and 98.97%, precision of 99% and 99.01%, F1 score of 99% and 99.89%, AUC of 0.9999 and 0.9998, Average Precision (AP) of 0.9999 and 0.9997 and recall of 100% and 100% for two different amazon product datasets. Show more

Keywords: CNN, reviews helpfulness, online reviews, machine learning, binary classification, reviews feature set

DOI: 10.3233/JIFS-223546

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8851-8868, 2023

Authors: Selvarajan, L. | Venkataramanan, K. | Rajavel, R. | Senthilkumar, T.S.

Article Type: Research Article

Abstract: Electro discharge machining (EDM) is a cycle for molding tough materials and framing profound contour formed openings by warm disintegration in all sort of electrically conductive materials. The goal of the venture to be concentrating because of working parameters of EDM for machining of silicon nitride-titanium nitride in the machining qualities with copper electrode, for example input Spark on time (Son ), current (Ip ), Spark off time (Soff ), spark gap and dielectric pressure on the metal removal rate (MRR) and Electrode Wear Rate (EWR) were analyzed. Subsequently, using Taguchi analysis of various plots like Mean effect plots, Interaction …plots, and contour plots, performance characteristics are looked at in relation to multiple process factors. Fuzzy logic and Regression analysis is utilized to combine various reactions into a solitary trademark record known as the Multi Response Performance Index (MRPI).The trial and anticipated qualities were in a decent programming instrument for discovering the MRPI esteem. For numerous performance aspects, such as material removal rate, electrode wear rate and so on, the optimal process parameter combination was established using fuzzy logic analysis. The key process factors, which included spark off time and current, were found using an ANOVA based on a fuzzy algorithm. Topography on machined surface and cross-sectional view of conductive Si3 N4 -TiN composite and surface characteristics of machined electrode is examined by SEM analysis and identified the best hole surface and worst hole surface. Sensitivity analysis is being utilized to determine how much the input values, such as Ip, Son and Soff , will need to alter in order to get the desired, optimal result. In the complexity analysis, each constraint of the machine, composite and process is addressed. Future researches might look into various electrodes to assess geometrical tolerances including angularity, parallelism, total run out, flatness, straightness, concentricity, and line profile employing other optimization methodologies to achieve the best outcome. The findings of the confirmatory experiment have been established, indicating that it may be feasible to successfully strengthen the spark eroding technique. Show more

Keywords: EDM, Si3N4–TiN, fuzzy logic optimization, MRPI, surface texture

DOI: 10.3233/JIFS-223650

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8869-8888, 2023

Authors: Rajeswary, C. | Thirumaran, M.

Article Type: Research Article

Abstract: Phishing is a major problem on darknets. Phishing is the practice of attacking an unaware person by pretending to be someone else to steal their digital data. In anonymous platforms such as the dark web or deep web of Tor, detecting the attacker or phishing attacks is a much more complicated practice. Generic phishing attacks can be easy to spot. Today’s challenge is detecting the various attacks in the anonymous network is very hard. The intelligent factor of attacks can bypass traditional detection solutions. To solve the problem of complications in the Tor Network, this work focuses on the development …of automated detection of vulnerable attacks in phishing-based Tor hidden services. The proposed model initially divides the attack parameters into three categories into Class A, Class B, and Class C based on technical perspectives and some defined threshold values. Next, the class A attacks (i.e. top level domain and protocol similarity) attacks are detected by a random forest (RF) classifier. Then, the class B attacks can be identified by the convolutional neural network (CNN). Finally, the LSTM model is applied for the accurate classification of multiple attacks in the Tor network. The experimental validation of the proposed model is tested using the CIRCL and AIL datasets. The experimental values highlighted the promising performance of the proposed model over other methods with a maximum overall detection accuracy of 95.60% and 95.77% on CIRCL and AIL datasets respectively. Therefore, the proposed model effectively detects multiple attacks in the Tor network under dynamic and real-time environments. Show more

Keywords: Phishing detection, attacks, tor network, random forest, CNN, LSTM

DOI: 10.3233/JIFS-224142

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8889-8903, 2023

Authors: Pei, Mengjiao | Liu, Shuli | Wen, Haolan | Wang, Weizhong

Article Type: Research Article

Abstract: Failure mode and effect analysis (FMEA) is one of the most effective means for potential systematic risk assessment in a real work environment. Nevertheless, the traditional FMEA approach has been extensively criticized for many deficiencies in coping with risk evaluation and prioritization problems under inter-uncertain environments. To overcome the limitations, in this paper, a synthesized risk priority calculation framework is proposed for FMEA by combining the gained and lost dominance score (GLDS) method, the combination ordered weighted averaging (C-OWA) operator, and Fermatean fuzzy set (FFS). Firstly, we use FFS to express the experts’ uncertain risk evaluation information which can depict …the fuzziness and ambiguity of the information. Secondly, the C-OWA operator combined with FFS is introduced to build the group risk matrix which can provide a more reasonable risk analysis result. Then, the developed GLDS method with FFS is presented to calculate the risk priority of each failure mode which takes both individual and group risk attitudes into consideration. Finally, a medical device risk analysis case is introduced to demonstrate the proposed FMEA framework. We also perform comparison analyses to confirm the effectiveness and rationality of the hybrid risk prioritization framework for FMEA under a complex and uncertain situation. Show more

Keywords: Failure mode and effect analysis, GLDS, Fermatean fuzzy set, C-OWA operator

DOI: 10.3233/JIFS-222692

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8905-8923, 2023

Authors: Wang, W.-C. | Yeh, Y.-W. | Chen, R.

Article Type: Research Article

Abstract: In the cooperative multi-agent pathfinding and motion planning, given a unique start position and a unique goal position for each agent, all agents are able to pursue their own goals without colliding with each other. To aim at realizing the collision-free motion of the agents within the tractable time, this work proposes a polynomial-time solver, called the HBD-AOI, hybridizing centralized and decentralized schemes. Firstly, an algorithm of centralized pathfinding is utilized to plan the optimal paths of all agents. Afterwards, each of the agents updates the local motion pattern to tracks its own planned waypoints with the obstacle avoidance in …a decentralized manner. Furthermore, to resolve unavoidable egoistic conflicts occurring in the decentralized scheme, a centralized intervener with the route replanning is invoked to coach the involved agents to abort the existing deadlocks. Bounded by an amount of time, the performances of the proposed and benchmarked algorithms are simulated on the same instance, from the evaluated testbeds that consists of various maps and scenarios. In the simulations, it is proved that this work outperforms other benchmarked algorithms for all presented instances in the term of the success rate. The experimental results are also demonstrated to verify the feasibility of the proposed methodology. Show more

Keywords: Multi-agent, pathfinding, motion navigation, hybrid approach, deadlock

DOI: 10.3233/JIFS-223157

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8925-8941, 2023

Authors: He, Xiaoxu

Article Type: Research Article

Abstract: Complex time series appear in numerous applications and are related to some essential physiological and natural systems. Their comparison faces big challenges: 1) with different complexity; 2) with significant phase shift in one series or shift∖on the time axis. Existing methods work well for periodic time-series data, but fail to produce satisfactory results in complex time-series. In this paper, we introduce a novel distance function based on the evolution rule for complex time series comparison. Here, the evolution rule, as the innate generative mechanism of time series, is creatively used to characterize complicated dynamics from complex time series. The comparison …includes different level comparisons: the coarse level is to compare the difference in complexity, and the fine level is to compare the difference in actual evolution behavior. The proposed method is inspired by the observation that similar sequences come from the same source, e.g. a person’s heart, in the case of ECG, thus two similar series will have the same innate generative mechanism. The performance has been verified by the conducting experiments, and the experiment results show that the proposed method is superior to the previously existing methods in clustering and classification on some real data sets. Show more

Keywords: Complex time series, evolution rule, complex system, data mining, non-parametric

DOI: 10.3233/JIFS-223338

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8943-8955, 2023

Authors: Yu, Ming | Lin, Xiaoqing | Liu, Yi | Guo, Yingchun

Article Type: Research Article

Abstract: Existing saliency detection methods have achieved great progress in extracting multi-level features, however it is a challenging problem to catch accurate long-range dependencies that can enhance the accuracy of semantic information. To address this, a Transformer-based multi-scale attention and boundary enhancement with long-range dependency (MSBE) network is proposed in this paper. A multi-scale attention enhancement module (MSAEM) is designed to reduce the redundant or noisy features and generate a high-quality feature representation by integrating multiple attentional features with diverse perspectives. The high-quality features are then fed into the triple Transformer encoder embedding module (TEM) to enhance high-level semantic features by …learning long-range dependencies across layers. In the decoder part, a cross-layer feature fusion module (CLFFM) and boundary enhancement module (BEM) are designed to improve the effect of feature fusion and get accurate prediction results. Extensive experiments on six challenging public datasets demonstrate that the proposed method achieves competitive performance. Show more

Keywords: Salient object detection, long-range dependencies, transformer encoder, cross-layer feature fusion, boundary enhancement module

DOI: 10.3233/JIFS-223726

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8957-8969, 2023

Authors: Belal, Mohamad Mulham | Sundaram, Divya Meena

Article Type: Research Article

Abstract: The security defenses that are not comparable to sophisticated adversary tools, let the cloud as an open environment for attacks and intrusions. In this paper, an intelligent protection framework for intrusion detection in a cloud computing environment based on a covariance matrix self-adaptation evolution strategy (CMSA-ES) and multi-criteria decision-making (MCDM) is proposed. The proposed framework constructs an optimal intrusion detector by using CMSA-ES algorithm which adjusts the best parameter set for the attack detector. Moreover, the proposed framework uses a MEREC-VIKOR, a hybrid standardized evaluation technique. MEREC-VIKOR generates the own performance metrics (S, R, and Q) of the proposed framework …which is a combination of multi-conflicting criteria. The proposed framework is evaluated for attack detection by using CICIDS 2017 dataset. The experiments show that the proposed framework can detect cloud attacks accurately with low S (utility), R (regret), and Q (integration between S and R). The proposed framework is analyzed with respect to several evolutionary algorithms such as GA, IGASAA, and CMA-ES. The performance analysis demonstrates that the proposed framework that depends on CMSA-ES converges faster than the other evolutionary algorithms such as GA, IGASAA, and CMA-ES. The outcomes also demonstrate that the proposed model is comparable to the state-of-the-art techniques. Show more

Keywords: Multi-criteria decision-making, MEREC, VIKOR, CMSA-ES, intrusion detection system, security

DOI: 10.3233/JIFS-224135

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 8971-9001, 2023

Authors: Zhang, Haibo

Article Type: Research Article

Abstract: For a long time, the level of endurance quality of our male basketball athletes is not high, and there is a gap with the strongest countries in Europe and America. The former head coach of Chinese men’s basketball team diagnosed the biggest problem of Chinese men’s basketball team and Chinese youth men’s basketball team is the poor quality of endurance. It is especially important to strengthen the endurance training of our basketball players and improve their endurance level. However, from the current situation, the teams in the training due to the lack of standards for endurance quality training has led …to a great blindness in endurance quality training. The endurance quality level evaluation of young male basketball players is a classic multiple attribute group decision making (MAGDM) issue with vague, inconsistent, and indeterminate information. The 2-tuple linguistic neutrosophic sets (2TLNSs) is an appropriate form to express the indeterminate decision-making information in the endurance quality level evaluation of young male basketball players. Therefore, in this paper, the 2-tuple linguistic neutrosophic numbers CLVA (2TLNN-CLVA) is built based on traditional close value (CLVA) method and applies it to evaluate the endurance quality level of young male basketball players. Finally, a numerical example for evaluating the endurance quality level of young male basketball players has been given and some decision comparisons are also conducted to further illustrate the advantages of the 2TLNN-CLVA method. Show more

Keywords: Multiple attribute group decision making (MAGDM) problems, 2-tuple linguistic neutrosophic sets (2TLNSs), CLVA method, endurance quality level, basketball players

DOI: 10.3233/JIFS-224327

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9003-9014, 2023

Authors: Yao, Zhigang | Ran, Hui

Article Type: Research Article

Abstract: At present, the basic pension insurance system for urban and rural residents in China has played a positive role in guaranteeing the basic life of the elderly in urban and rural areas. At present, the basic pension insurance system for urban and rural residents is not perfect, and there is still a great lag in the formulation of cross-system and cross-regional policies. There are differences in treatment between groups, between regions and between urban and rural areas. The coverage is not comprehensive enough and there are still some people who are not included in the basic protection system, etc. People …urgently need a social pension insurance system that can provide reliable and sustainable protection in their old age. The operational efficiency evaluation of urban and rural residents’ basic pension insurance systems is viewed as the multi-attribute decision-making (MADM). In this paper, the triangular fuzzy neutrosophic numbers grey relational analysis (TFNN-GRA) method is built based on the traditional grey relational analysis (GRA) and triangular fuzzy neutrosophic sets (TFNSs). Finally, a numerical example for operational efficiency evaluation of urban and rural residents’ basic pension insurance systems has been given and some comparisons are used to illustrate advantages of 2TLNN-GRA method. Show more

Keywords: Multiple attribute decision making (MAGDM) problems, triangular fuzzy neutrosophic sets (TFNSs), GRA method, operational efficiency evaluation

DOI: 10.3233/JIFS-221631

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9015-9026, 2023

Authors: Premananthan, G. | Nagaraj, B. | Jaya, J.

Article Type: Research Article

Abstract: In recent times, ML algorithms that plays a significant role right from drug discovery to clinical decision making. The recent advances in DL technologies contribute towards improved performance for carrying out computer aided medical image analysis and disease diagnosis. The key benefit of AI in processing of medical big data offers spectacular insights into the hierarchal relationships that exist among data which can be algorithmically explored thus replacing the tedious manual processes to extract and localize specific areas of interests in medical images thus considerably changing the way medicine has been practiced so far. In bio medical related clinical applications, …there is a constant demand pertaining the research and development with respect to deploying AI as a mainstream tool to perform several medical imaging activities like analysis, diagnosis, segmentation as well as classification. The increased usage of electronic health records and medical images being its integral component the need for appropriate and efficient AI assisted medical image analysis system that takes care of accurate and automated decision making could be of great help to radiologists and medical practitioners. Molecular image analysis is a dynamic field that makes use of ML and DL algorithms that utilizes labeled and structured information which also proves to be helpful to the patients as they serve as an initial interface before further diagnosis and treatments. Thus our research aims to offer a novel and efficient AI based medical analysis system that can assist clinical practitioners to focus on enhancing the disease diagnosis through DL based medical image analysis and decision making. In addition, we also address specific challenges related to disease diagnosis and propose novel GAN model for improved diagnosis and implementation. Our proposed technique can also be generalized to generate synthetic data for further issues related to molecular image analysis in the field of medicine and help towards building a better disease diagnosis model. Show more

Keywords: Artificial Intelligence (AI), Deep learning (DL), electronic health records (EHR), Generative Adversarial networks (GAN), medical image analysis, Machine learning (ML).

DOI: 10.3233/JIFS-223354

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9027-9037, 2023

Authors: He, Qiang | Wang, Guanqun | Huo, Lianzhi | Wang, Hengyou | Zhang, Changlun

Article Type: Research Article

Abstract: Multivariate time series anomaly detection has made significant progress and has been studied in many fields. One of the difficulties in time-series data analysis is the complex nonlinear dependencies between multiple time steps and multiple variables. Therefore, detecting anomalies in these data is challenging. Although many studies used classical attention mechanisms to model the temporal patterns of data, few have combined multiple attention mechanisms and analyzed the data’s temporal characteristics and feature correlations. Therefore, we propose an autocorrelation and attention mechanism-based anomaly detection (ACAM-AD) framework that combines an autocorrelation model based on the Autoformer model, which is superior to the …self-attention mechanism, a multi-head graph attention network, and a dot-product attention mechanism to model the complex dependencies of data considering temporal and feature dimensions. The autoregressive model is parallelized with the neural network, and a sparse autocorrelation mechanism and sparse graph attention network are used to reduce model complexity. Experiments on public datasets show that the model is effective and performs better than the baseline model. Show more

Keywords: Multivariate time series, anomaly detection, autocorrelation, multi-head graph attention network

DOI: 10.3233/JIFS-224416

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9039-9051, 2023

Authors: Yang, Guangfen | Zhang, Hui

Article Type: Research Article

Abstract: Owing to the lack of information, it is more realistic that the sum of probabilities is less than or equal to one in the probabilistic hesitant fuzzy elements (P-HFEs). Probabilistic-normalization method and cardinal-normalization method are common processing methods for the P-HFEs with incomplete information. However, the existed probabilistic-normalization method of sharing the remaining probabilities will lose information and change the information integrity of the P-HFEs. The first existed cardinal-normalization method of adding maximum or minimum membership degree with probability zero are influenced by the subjectivity of the decision makers. And the second existed cardinal-normalization method named as reconciliation method only …applicable to the P-HFEs with complete information. Aiming at solving those shortcomings, we propose a possibility degree method based on a novel cardinal-normalization method for the sake of comparing the P-HFEs in pairs. In the process of comparison, the information integrity remains unchanged. Then, we propose a multi-criteria decision making (MCDM) problem, where the attribute weight is determined by entropy measures of the integration results. Finally, an application case in green logistics area is given for the sake of illustrating the efficiency of the proposed method, where the evaluation values are given in the P-HFEs form with incomplete information. Numerical and theoretical results show that a MCDM problem based on the proposed cardinal-normalization method and possibility degree method have a wide range of application. Show more

Keywords: Probabilistic hesitant fuzzy element, possibility degree method, entropy measures, reconciliation method, the identical membership method

DOI: 10.3233/JIFS-222733

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9053-9072, 2023

Authors: Ding, Ji-Feng | Weng, Ju-Hui | Chou, Chien-Chang

Article Type: Research Article

Abstract: Evaluating the factors affecting customer value in department stores will shed light on the motivations of customers when choosing department stores, which will help department stores to improve their business performance and competitiveness. This paper applies the fuzzy Analytic Hierarchy Process (AHP) method to empirically analyze the determinants of customer value at department stores in Taiwan. This study first found the major factors influencing customer value at department stores in Taiwan through a review of the literature and expert interviews, and these factors consisted of four evaluation dimensions and 20 evaluation criteria. An empirical investigation was then conducted through an …AHP expert questionnaire survey. The main findings of this paper were as follows: (1) “Physical environment” was the most important evaluation dimension for customer value at department stores in Taiwan. (2) The four leading factors influencing customer value in department stores were “roomy and comfortable space,” “responsive customer service,” “planning of lines of movement at counters,” and “parking area and facilities.” This study also performed further discussion of the four evaluation criteria as a reference for department stores that wish to raise their competitiveness. Show more

Keywords: Customer value, determinant, department store, fuzzy, analytic hierarchy process (AHP)

DOI: 10.3233/JIFS-222175

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9073-9089, 2023

Authors: Lian, Lian

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-222395

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9091-9107, 2023

Authors: Karthigha, M. | Latha, L.

Article Type: Research Article

Abstract: Industrial Control Systems (ICS) are susceptible to threats or attacks, and even minor changes or manipulation could cause major damage to industrial operations. Industrial control system cybersecurity is vital owing to the severe negative effects it could have on the economy, the environment, people, and politics. Therefore, it’s also crucial to design intrusion detection systems for industrial control systems. In this paper, an efficient intrusion detection system with clustered ensemble feature selection and a Multi-Level Modified Gated Recurrent Unit (M-GRU) classification model is proposed. This intrusion detection system with a general framework for clustered ensemble feature ranking approach is proposed …to effectively find the best feature subset in network packet traffic data. The features designated are fed into a multi class classification algorithm Multi-Level Modified Gated Recurrent Unit (M-GRU) to efficiently detect the cyberattacks. Evaluation criteria including precision, accuracy, recall and F1 score are assessed and compared to other cutting-edge algorithms to assess the performance of the proposed model. The proposed model attained an average accuracy of 98.21 %. Results show that the suggested model increased the attack detection accuracy by an average of 5.935% and 0.116% when compared to the Gated Recurrent Unit, Long Short Term Memory, random forest and naïve bayes models. Show more

Keywords: Industrial control system, intrusion detection, ensemble feature selection, classification, gated recurrent unit

DOI: 10.3233/JIFS-222643

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9109-9127, 2023

Authors: Nurhidayat, Irfan | Pimpunchat, Busayamas | Klomsungcharoen, Wiriyabhorn

Article Type: Research Article

Abstract: This study aims to present the modified SVM polynomial method in order to evaluate insurance data. The research methodology discusses classical and modified SVM polynomial methods by R programming, and uses performance profiles to create the most preferable methods. It offers a new algorithm called an accurate evaluating algorithm as the way to construct the modified SVM polynomial method. The classical SVM polynomial method is also represented as the main idea in finding the modified polynomial SVM method. Model Performance Evaluation (MPE), Receiver Operating Characteristics (ROCs) Curve, Area Under Curve (AUC), partial AUC (pAUC), smoothing, confidence intervals, and thresholds are …further named an accurate evaluating algorithm, employed to build the modified SVM polynomial method. The research paper also presents the best performance profiles based on the computing time and the number of iterations of both classical and modified SVM polynomial methods. Performance profiles show numerical comparisons based on both methods involving insurance data also displayed in this paper. It can be concluded that applying an accurate evaluating algorithm on the modified SVM polynomial method will improve the data accuracy up to 86% via computing time and iterations compared to the classical SVM polynomial method, which is only 79%. This accurate evaluating algorithm can be applied to various large-sized data by utilizing R programming with changing any suitable kernels for that data. This vital discovery will offer solutions for faster and more accurate data analysis that can benefit researchers, the private sector, or governments struggling with data. Show more

Keywords: Modified SVM polynomial method, classical SVM polynomial method, accurate evaluating algorithm, insurance data, simulation

DOI: 10.3233/JIFS-222879

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9129-9141, 2023

Authors: Feng, Xiangqian | Zibibula, Minawaer | Wei, Cuiping

Article Type: Research Article

Abstract: With the rapid development of science and technology, high-tech enterprises need to constantly carry out technological innovation to adapt to the changes in the external environment, and maintain their competitive advantages. However, the current research on technological innovation of high-tech enterprises is carried out from a static perspective, which is difficult to understand the dynamic evolution process of continuous technological innovation of high-tech enterprises in a turbulent environment. Therefore, this paper studies high-tech enterprises’ dynamic technological innovation ability from a dynamic perspective, through literature reading and the investigation of the technological innovation status of high-tech enterprises, the evaluation index system …of 12 indicators under three dimensions is constructed. The multi-objective optimization by ratio analysis plus full multiplicative form (MULTIMOORA) –Level-based weight assessment (LBWA) comprehensive evaluation model based on Pythagorean fuzzy number (PFN) is proposed to evaluate the dynamic technological innovation ability of high-tech enterprises. Finally, the accuracy and reliability of the model are verified by case analysis. The result of this study shows that the ability to identify new technological knowledge and information outside the enterprise, the ability to obtain technological innovation resources, and the ability to strengthen the input of innovation resources are important factors for the dynamic technological innovation capability of enterprises, so enterprises should pay more attention from these aspects. This study provides a new comprehensive evaluation model and evaluation results can help the decision-makers find their strengths and weaknesses in time and improve them, to promote the sustainable development of high-tech enterprises. Show more

Keywords: Dynamic capability, Pythagorean fuzzy set, LBWA, MULTIMOORA, high-tech enterprises innovation

DOI: 10.3233/JIFS-222965

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9143-9165, 2023

Authors: Jin, Feifei | Li, Danning | Guo, Shuyan | Zhou, Ligang | Chen, Yi | Zhu, Jiaming

Article Type: Research Article

Abstract: Under the Pythagorean fuzzy environment, this paper presents a multi-attribute decision-making (MADM) model based on exponential entropy measure and exponential similarity measure to evaluate new energy battery supplier’s performance. In this method, the notion of Pythagorean fuzzy linguistic sets (PFLSs) is first introduced by combining the linguistic fuzzy sets (LFSs) and the Pythagorean fuzzy sets (PFSs). Then, the axiomatic definitions of Pythagorean fuzzy entropy and Pythagorean fuzzy similarity measure are developed to measure the degree of uncertainty and similarity between two Pythagorean fuzzy linguistic values (PFLVs). The PFLVs can be expressed by the linguistic membership degree (LMD) and linguistic non-membership …degree (LNMD). In addition, we construct two new information measure formulas based on exponential function. Through a series of proofs, we verify that they satisfy the axiomatic conditions of entropy and similarity measure of Pythagorean fuzzy language respectively. On this basis, we research the relationship between the two information measures. Finally, we present a novel Pythagorean fuzzy linguistic MADM model. An example for evaluating performance of new energy battery supplier is given to explain the effectiveness of the newly-developed approach. The stability and validity of the newly-developed approach is performed by sensitivity analysis and comparative analysis. Show more

Keywords: Pythagorean fuzzy linguistic sets, information entropy, similarity measure, new energy battery supplier evaluation

DOI: 10.3233/JIFS-223088

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9167-9182, 2023

Authors: Choudhary, Ashutosh Kumar | Rahamatkar, Surendra

Article Type: Research Article

Abstract: DoS, GH, Sybil, Masquerading, Spoofing, Man in the Middle, etc. constantly attack IoT networks. Internal or external attacks reduce end-to-end delay, throughput, energy use, and other metrics. To counter these attacks, researchers have proposed a number of security & privacy mechanisms with varying computational complexity and security levels. Immutability, traceability, transparency, and distributed nature make blockchain-based models secure. QoS depends on blockchain length, so these models aren’t scalable. Researchers say sidechaining improves QoS while remaining secure. Splitting or merging complex sidechains requires machine learning. Low-power IoT networks can’t use models. This text suggests a lightweight MGWO Model that helps establish …initial routes by choosing high-trust nodes, reducing sidechaining power consumption, and incorporating fault-aware trust establishment. MGWO Model determines blockchain piece count for high QoS. MGWO Model uses Q-Learning to detect network faults. Fault identification is controlled by a stochastically modelled and activated Intrinsic Genetic Algorithm (IGA). Q-Learning, MGWO, and IGA can mitigate Sybil, Masquerading, Grey Hole, DDoS, and MITM attacks. Even when attacked, the proposed model maintains high QoS, improving real-time deployment efficiency. The proposed model improves energy efficiency by 15.9%, throughput by 10.6%, communication speed by 8.3%, and packet delivery by 0.8% for different network scenarios. Show more

Keywords: Trust, wireless, IoT, blockchain, sidechain, MITM, MGWO, Q learning, IGA, DDoS, Sybil, QoS

DOI: 10.3233/JIFS-223316

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9183-9201, 2023

Authors: Xiao, Yanjun | Zhao, Yue | Li, Zeyu | Wan, Feng

Article Type: Research Article

Abstract: Fault diagnosis of rapier loom is an inevitable requirement to meet the demand of intelligent manufacturing. Facing the strong noise interference caused by complex working environment, accurate and reliable vibration signal detection of blade loom spindle is the key to realize the rapier loom fault diagnosis. This paper proposes a method to extract the spindle vibration signal of the rapier loom by Adaptive Piecewise Hybrid Stochastic Resonance (APHSR) after the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN). Firstly, ICEEMDAN is used to pre-process the weak vibration signal containing noise, decompose the signal into multiple IMF components and …display the high and low frequency signal characteristics of the original signal. Then, the energy density method and the correlation coefficient method are used to remove high and low noise, respectively, to filter the optimal IMF components, and then the signal containing valid information is reconstructed. Finally, the reconstructed signal is input to APHSR for noise-assisted enhancement after scale transformation to restore the faint vibration signal feature frequencies and achieve effective feature extraction. Through the simulation experiment and the engineering fault experiment analysis, comparing ICEEMDAN-APHSR with CEEMDAN-SR, ICEEMDAN-SR, CEEMDAN-APHSR methods. The difference between the spectrum amplitude, the spectrum amplitude and the maximum noise and the maximum signal to noise ratio (SNR) of the fault feature frequency of the rapier loom spindle bearing increased by 3.3668 dB,1.7205 dB,2.3952 dB, respectively. The results show that ICEEMDAN-APHSR method can accurately extract the fault feature frequency of the spindle bearing of rapier loom, and effectively solves the problem of extracting the weak vibration signal feature of rapier loom in the background of strong noise. This method is beneficial to the future research of rapier loom fault diagnosis, and is of great significance to promote the maintenance of loom equipment and production safety and quality. Show more

Keywords: Weak signal detection, ICEEMDAN, APHSR, feature extraction, rapier loom, fault diagnosis

DOI: 10.3233/JIFS-223664

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9203-9230, 2023

Authors: Ma, Haishu | Ma, Zongzheng

Article Type: Research Article

Abstract: Unexpected failure of production equipment may lead to fatal accidents and economic losses of the enterprise. It is important to find out the cause and reason as soon as possible and take appropriate maintenance measures. Condition monitoring is often applied to predict equipment failures based on certain parameters. Moreover, when the parts of the rotating machinery fail, the vibration signals collected by the sensors are often mixed with a large amount of noise, which will cause difficulties for the accuracy and generalization of traditional fault diagnosis models. How to extract more effective feature information from complex vibration signals is of …indescribable importance for optimizing fault diagnosis models. In order to improve the accuracy of fault diagnosis in manufacturing system, a deep neural network model was proposed, which was validated on a blower. First, the vibration signal was collected using the sensors mounted on the blower. Then, wavelet packet decomposition and fast fourier transform were applied for feature extraction. Deep learning model was built using keras to diagnose the blower. The stacked Autoencoder is adopted in the DNN for dimension reduction. The extracted features are fed into the Multilayer Perceptron for fault diagnosis. Experimental results show that the proposed deep neural network model is able to predict the degradation of the mechanical equipment with high accuracy. Show more

Keywords: Deep neural network, wavelet packet decomposition, Fourier transform, feature extraction, fault diagnosis

DOI: 10.3233/JIFS-224077

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9231-9239, 2023

Authors: Shao, Yubo | Zhang, Bangcheng | Yin, Xiaojing | Gao, Zhi | Li, Jing

Article Type: Research Article

Abstract: The anomaly detection research of drive end bearings (DEBs) is of great significance to the safe and reliable operation of hoist. This paper proposes an anomaly detection method of DEBs based on the linear weighted sum combines with the belief rule base. First, in order to improve the accuracy of anomaly detection, the time-domain features and frequency-domain features are integrated by linear weighted sum (LWS) respectively. Then, belief rule base (BRB) method is provided for anomaly detection using fused features. Meanwhile, the covariance matrix adaption evolution strategy (CMA-ES) is utilized to optimize the parameters of belief rule base model. Finally, …the validity of the proposed method is verified by the vibration data, which are acquired from the condition monitoring system of hoist in body-in-white (BIW) welding production line. The proposed method achieves a high detection accuracy. It is proved that the proposed method is suitable for anomaly detection of DEBs in the actual BIW welding production line. Show more

Keywords: Anomaly detection, linear weighted sum, belief rule base, drive end bearing

DOI: 10.3233/JIFS-224102

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9241-9255, 2023

Authors: Liu, Peng | Geng, Xiaonan

Article Type: Research Article

Abstract: Coal is a vital basic energy source for any economy in the world, and our country is no exception. Our coal resources are abundant, with high production and demand, not comparable to oil and natural gas. The coal supply chain plays an equally important role in economic production, but unfortunately, the current coal supply chain is not focused on greening while creating profits. Unfortunately, the current coal supply chain does not focus on green production and energy conservation and emission reduction while creating profits, which has caused irreversible harm and loss to resources and environment. This has caused irreversible damage …and loss to resources and the environment. The green supplier selection for coal enterprises is affirmed as multiple attribute decision making (MADM). In such paper, motivated by the idea of cosine 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 Green supplier selection for coal enterprises 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), cosine similarity measure (CSM), green supplier selection

DOI: 10.3233/JIFS-224123

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9257-9265, 2023

Authors: Chang, Kuei-Hu

Article Type: Research Article

Abstract: Risk prediction, assessment, and control are key parts of the successful operation and sustainable development of any enterprise. During the process of product failure risk assessment, evaluated risk factors belong to the group of multiple-criteria decision-making (MCDM) problems, including severity, occurrence, and detection when failure occurs. However, the traditional risk ranking method does not consider the subjective and objective weights of the assessment factors, and during risk prediction, assessment, and control, some unknown information in many practical situations is included. These reasons may cause the risk assessment results to be biased. In order to effectively deal with the problem of …risk assessment, this paper proposes a D numbers risk ranking method by considering subjective and objective weights between assessment factors under incomplete linguistic information. An illustrative example of screening unit failure risk assessment is used to explain and prove the rationality and correctness of the proposed method. Some risk ranking methods are compared with the proposed D numbers risk ranking method, and the simulation results present that the proposed ranking method handles the issue of incomplete information and provides more reasonable risk ranking results. Show more

Keywords: D numbers, risk ranking method, subjective weights and objective weights, multiple-criteria decision-making

DOI: 10.3233/JIFS-224139

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9267-9280, 2023

Authors: Abdul Lathif, Syed Ismail | Cruz Antony, J. | Noel Jeygar Robert, V. | Aishwarya, D.

Article Type: Research Article

Abstract: A failure risk assessment must be carried out and potential drilling equipment failure risks must be promptly addressed in order to prevent drilling fluid pollution during offshore oil drilling. The qualitative, comprehensive, and quantitative failure risks for Drilling Permanent Magnetic Synchronous Motors (DPMSM) are examined in this article using a hybrid methodology. First, the Drilling PMSM using Failure Mode Analysis (FMA) method is combined with the Risk Matrix (RM) approach to analyse the risk levels of risk factors individually. Next, the Borda number is introduced to compare the risk levels exactly. To execute a Fuzzy Comprehensive Evaluation (FCE) of the …system failure risk, a fuzzy relation matrix of risk factors is generated, and the weight of each risk component is calculated using importance analysis. The failure rate is then determined using fuzzy inference, and the Fault Tree (FT) is then built based on the risk variables. Fault tree analysis is used to compute the system failure rate, and the significance of the bottom event is evaluated. The Bayesian network (BN) is used to depict the Fuzzy Fault Tree (FFT) analysis. By utilizing Bayesian forward causal inference and reverse diagnostic inference to calculate the leaf node failure rate and root node posterior probability, the system’s weak points and potential failure causes are determined. Show more

Keywords: Risk matrix, fuzzy comprehensive evaluation, fault tree, bayesian network, failure mode analysis

DOI: 10.3233/JIFS-224462

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9281-9295, 2023

Authors: Jebin Bose, S. | Kalaiselvi, R.

Article Type: Research Article

Abstract:  The use of smartphones is increasing rapidly and the malicious intrusions associated with it have become a challenging task that needs to be resolved. A secure and effective technique is needed to prevent breaches and detect malicious applications. Through deep learning methods and neural networks, the earliest detection and classification of malware can be performed. Detection of Android malware is the process to identify malicious attackers and through the classification method of malware, the type is categorized as adware, ransomware, SMS malware, and scareware. Since there were several techniques employed so far for malware detection and classification, there were some …limitations like a reduced rate of accuracy and so on. To overcome these limitations, a deep learning-based automated process is employed to identify the malware. In this paper, initially, the datasets are collected, and through the preprocessing method, the duplicate and noisy data are removed to improve accuracy. Then the separated malware and benign dataset from the preprocessing phase is dealt with in feature selection. The reliable features are extracted in this process by Meta-Heuristic Artificial Jellyfish Search Optimizer (MH-AJSO). Further by the process of classification, the type of malware is categorized. The classification method is performed by the proposed Dense Dilated ResNet101 (DDResNet101) classifier. According to the type of malware the breach is prevented and secured on the android device. Although several methods of malware detection are found in the android platform the accuracy is effectively derived in our proposed system. Various performance analysis is performed to compare the robustness of detection. The results show that better accuracy of 98% is achieved in the proposed model with effectiveness for identifying the malware and thereby breaches and intrusion can be prevented. Show more

Keywords: Android, smartphones, datasets, malware, detection, classification, deep learning neural network, benign, preprocessing, feature selection, meta-heuristic artificial jellyfish search optimizer, dense dilated ResNet101

DOI: 10.3233/JIFS-230186

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9297-9310, 2023

Authors: Jiang, Lin | Chen, Biyun

Article Type: Research Article

Abstract: To study the bilateral matching problem of new R&D institution-talent teams based on uncertain linguistic assessment information and multiple indicators-multiple talents, a cloud model regret theory-based information gathering method is proposed, and a bi-objective bilateral matching model based on single-indicator utility maximization and overall indicator utility maximization is constructed.. The method firstly constructs the demand indicators of new R&D institutions for talent teams, uses cloud data to characterize uncertain group linguistic assessment information, and converts cloud data into cloud perceived utility based on power function; secondly, calculates the indicator weights of each expert based on entropy power method, and secondly …uses entropy power method to calculate comprehensive indicator weights, optimally solves objective expert weights based on the minimum variance of assessment information among experts, and integrates with subjective expert Again, based on regret theory, the cloud perceived utility of each talent under each index is converted into regret cloud perceived utility, and set with the index weights and expert weights into comprehensive cloud perceived utility; finally, a local-whole dual-objective bilateral matching model is constructed to obtain the matched talent team, and example analysis and method comparison are used to show that the method has feasibility and effectiveness. Show more

Keywords: New R&D institution, talent team, cloud model, regret theory, bilateral matching

DOI: 10.3233/JIFS-221944

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9311-9325, 2023

Authors: Muthuvinayagam, M. | Vengadachalam, N. | Subha Seethalakshmi, V. | Rajani, B.

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-221820

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9327-9345, 2023

Authors: Periakaruppan, Sudhakaran | Shanmugapriya, N. | Sivan, Rajeswari

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-222537

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9347-9362, 2023

Authors: Senthamil Selvi, M. | Ranjeeth Kumar, C. | Jansi Rani, S.

Article Type: Research Article

Abstract: A smart city is a phenomenon that combines information technology with physical and social infrastructure to regulate a city’s cooperative intelligence. Wireless sensor networks (WSN) are the fundamental technology that smart cities use to administer and sustain their service offerings. To decrease the network’s energy consumption, clustering and multihop routing algorithms have been suggested, verified, and put into practice in the literature. This inspiration led to the development of the “energy-aware clustered route approach” in the current study, which is suggested for WSNs in smart cities. The presented method focuses on choosing the right cluster heads (CHs) and the best …pathways in a WSN. The presented model includes a fitness value-based clustering scheme for efficient CH selection to achieve this. The Deep Neural Network (DNN) algorithm is then used to carry out the routing operation. The suggested approach technique calculates a fitness function (FF) that consists of three variables, including node degree, base station distance, and residual energy. This fitness function aids in the WSN’s best route selection. Simulations were run to verify the presented model’s superiority in terms of network lifespan and energy efficiency, and the results demonstrated the model’s outstanding performance. Show more

Keywords: Wireless sensor networks, cluster based routing, deep neural networks, genetic algorithm, and fitness function based route

DOI: 10.3233/JIFS-222615

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9363-9377, 2023

Authors: Gomes, Daiana | Serra, Ginalber

Article Type: Research Article

Abstract: In this paper, an interval type-2 evolving fuzzy Kalman filter is designed for processing of unobservable spectral components of uncertain experimental data. The adopted methodology consider the following steps: an initial model of the interval type-2 fuzzy Kalman filter, which is off-line identified from an initial window of the experimental data; the updating of antecedent proposition of interval type-2 fuzzy Kalman filter by using an interval type-2 formulation of evolving Takagi-Sugeno (eTS) clustering algorithm and the updating of consequent proposition by using a type-2 fuzzy formulation of Observer/Kalman Filter Identification (OKID) algorithm, taking into account the multivariable recursive Singular Spectral …Analysis of the experimental data. The computational results for tracking the Mackey-Glass chaotic time series illustrate the efficiency of proposed methodology as compared to relevant approaches from literature, and the experimental results for tracking a 2DoF helicopter demonstrate its applicability. Show more

Keywords: Systems identification, Kalman filter, interval type-2 fuzzy model, singular spectral analysis, evolving fuzzy systems

DOI: 10.3233/JIFS-222919

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9379-9394, 2023

Authors: Liu, Jinpei | Bao, Anxing | Jin, Feifei | Zhou, Ligang | Shao, Longlong

Article Type: Research Article

Abstract: Multiplicative probabilistic linguistic preference relation (MPLPR) has been widely used by decision-makers (DMs) to tackle group decision-making (GDM) problems. However, due to the complexity of the decision-making circumstance and individual subjectivity of DMs, they often provide inconsistent MPLPRs which often lead to unreasonable decision results. To solve this problem, this paper investigates a novel approach to GDM with MPLPRs based on consistency improvement and upgraded multiplicative data envelopment analysis (DEA) cross-efficiency. First, the concept of sequential consistency of MPLPR is defined. Then, a consistency improvement algorithm is proposed, which can convert any unacceptable consistent MPLPR into an acceptable one. Furthermore, …we use geometric averages to transform MPLPR into multiplicative preference relation (MPR). Meanwhile, considering the conservative psychology of DMs, an upgraded multiplicative DEA cross-efficiency model based on the pessimistic criterion is constructed, which can derive the priority vector of MPLPR. Therefore, we can obtain the rational ranking results for all alternatives. Finally, a case analysis of emergency logistics under COVID-19 is provided to illustrate the validity and applicability of the proposed approach. Show more

Keywords: Group decision-making approach, multiplicative probabilistic linguistic preference relations, consistency adjustment, pessimistic criterion, DEA cross-efficiency

DOI: 10.3233/JIFS-223117

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9395-9410, 2023

Authors: Jin, LeSheng | Chen, Zhen-Song | Yager, Ronald R. | Langari, Reza

Article Type: Research Article

Abstract: This letter reports a new type of uncertain information that is different from some well known existing uncertain information, such as probability information, fuzzy information, interval information and basic uncertain information. This type of uncertain information allows some specified compromise in interacting decision environments and gives some acceptance area when facing with uncertainties. We firstly introduce the cognitive interval information and then naturally propose the cognitive uncertain information as an extension. The featured acceptance area provides more flexibility in uncertain information handling and it can be regarded as some specified uncertain range (versus the certainty degree in basic uncertain information). …The new proposals have advantages in some uncertain decision making scenarios where intersubjectivity and interaction of decision makers play important roles. Besides, some basic structural properties are briefly discussed. Moreover, some motivational examples are presented to show its usage in group decision making to help automatically obtain consistency or consensus in aggregating the different individual evaluations. Show more

Keywords: Cognitive interval information, cognitive uncertain information, decision making, group decision making, information fusion, uncertain information

DOI: 10.3233/JIFS-223119

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9411-9418, 2023

Authors: Sangeetha, M. | Thiagarajan, Meera Devi

Article Type: Research Article

Abstract: A recommendation System (RS) is an emerging technology to figure out the user’s interests and intentions. As the amount of data increases exponentially, it is hard to analyze the user intentions and trigger the recommendation accordingly. In this research work, a novel recommendation system called the Deep Knowledge Graph based Attribute Preserving Recommendation (DKG-APR) is presented to analyze massive data and provide personalized recommendations to users. The Deep Knowledge Graph for Recommendation System (DKG-RS) uses Deep Convolutional Neural Network (DCNN) and attention mechanism to explicitly model high-order connections in knowledge graphs. According to empirical findings, Knowledge Graph Attention Network (KGAT) …performs better than other state-of-the-art recommendation techniques like RippleNet and Neural FM. Additional research demonstrates the effectiveness of embedding propagation for high-order relation modeling and the advantages of the attention mechanism for interpretability.The results also show that user information is crucial in the recommendation system, as seen from the optimal node-drop-out ratio of 0.2, which led to the best recall value of 0.2 for all datasets. Show more

Keywords: Knowledge graph, DCNN, DKG, recommendation system

DOI: 10.3233/JIFS-223775

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9419-9430, 2023

Authors: Osman, H. Saber | El-Sheikh, S.A. | Radwan, Abdelaziz E. | El-Atik, Abdelfattah A.

Article Type: Research Article

Abstract: In this paper, the generalization of pre-topological spaces called bipretopological spaces (briefly, π-pre-topology) depending on two pre-topologies on an arbitrary universal set has been introduced. New kinds of separations axioms on π-pre-topological spaces are established and some of their properties are investigated. A comparison between four separation axioms on π-pre-topological spaces and pre-topological spaces with different sorts of counterexamples are presented. The topological property for some π-pre-separation axioms are satisfied and its relation with disubgraphs are discussed. A human heart will be studied through it is generated digraph. It is noted that all separation axioms for human heart are not …all satisfied. Show more

Keywords: Pre-topology, π-pre-topology, separation axioms, human heart, regularity, normality, hereditary, pre-topological property

DOI: 10.3233/JIFS-223891

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9431-9439, 2023

Authors: Madhavi, S. | Santhosh, N.C. | Rajkumar, S. | Praveen, R.

Article Type: Research Article

Abstract: In Wireless Sensor Networks (WSNs), resource depletion attacks that focusses on the compromization of routing protocol layer is identified to facilitate a major influence over the network. These resource depletion attacks drain the batter power of the sensor nodes drastically with persistent network disruption. Several protocols were established for handling the impact of Denial of Service (DoS) attack, but majority of them was not able to handle it perfectly. In specific, thwarting resource depletion attack, a specific class of DoS attack was a herculean task. At this juncture, Multicriteria Decision Making Model (MCDM) is identified as the ideal candidate for …evaluating the impact introduced by each energy depletion compromised sensor nodes towards the process of cooperation into the network. In this paper, A Pythagorean Fuzzy Sets-based VIKOR and TOPSIS-based multi-criteria decision-making model (PFSVT-MCDM) is proposed for counteracting with the impacts of resource depletion attacks to improve Quality of Service (QoS) in the network. This PFSVT-MCDM used the merits of Pythagorean Fuzzy Sets information for handling uncertainty and vagueness of information exchanged in the network during the process of data routing. It utilized VIKOR and TOPSIS for exploring the trust of each sensor nodes through the exploration of possible dimensions that aids in detecting resource depletion attacks. The experimental results of PFSVT-MCDM confirmed better throughput of 21.29%, enhanced packet delivery fraction of 22.38%, minimized energy consumptions 18.92%, and reduced end-to-end delay of 21.84%, compared to the comparative resource depletion attack thwarting strategies used for evaluation. Show more

Keywords: Wireless sensor networks, resource depletion attacks, pythagorean fuzzy sets, TOPSIS (Technique For Order Performance By Similarity To Ideal Solution), quality of service, VIKOR (VlseKriterijumska Optimizacija Kompromisno Resenje)

DOI: 10.3233/JIFS-224141

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9441-9459, 2023

Authors: Cao, Maojun | Hu, Yingda | Yue, Lizhu

Article Type: Research Article

Abstract: The uncertainty of weight makes the weight density between samples not fixed. Aiming at the problem that the existing CLIQUE clustering algorithm does not consider the weight of object features, which leads to low accuracy, an improved weighted method combined with the thought of posets is proposed. In addition, this method does not need accurate weight assignment, only the weight order can run efficiently. First, the weight order of object features is obtained, and then the partial order weight is applied to the original data to obtain weighted data with weights. Then the traditional CLIQUE algorithm is used to cluster …according to weighted data, and finally the partial order weighted CLIQUE model is obtained. Through the experiment of six groups of data, the results show that: under the given weight sequence constraints, the clustering quality of the weighted CLIQUE model is significantly higher than that of the unweighted model, and the clustering accuracy and other aspects are significantly improved. In this method model, weight information is effectively integrated into the algorithm when only the feature weight order is obtained, and the function of feature weight is fully played to enhance the robustness of clustering results. At the same time, the idea of poset can effectively integrate expert information, and the representation of the nearest neighbor elements in Hasse graph can show the effect intuitively. It is an effective improvement method of CLIQUE clustering algorithm. Show more

Keywords: Clustering, proposed, CLIQUE algorithm, feature weight, Hasse graph

DOI: 10.3233/JIFS-224214

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9461-9473, 2023

Authors: Peng, Peng | Wu, Danping | Han, Fei-Chi | Huang, Li-Jun | Wei, Zhenlin | Wang, Jie | Jiang, Yizhang | Xia, Kaijian

Article Type: Research Article

Abstract: Currently, breast cancer is one of the most common cancers among women. To aid clinicians in diagnosis, lesion regions in mammography pictures can be segmented using an artificial intelligence system. This has significant clinical implications. Clustering algorithms, as unsupervised models, are widely used in medical image segmentation. However, due to the different sizes and shapes of lesions in mammography images and the low contrast between lesion areas and the surrounding pixels, it is difficult to use traditional unsupervised clustering methods for image segmentation. In this study, we try to apply the semisupervised fuzzy clustering algorithm to lesion segmentation in mammography …molybdenum target images and propose semisupervised fuzzy clustering based on the cluster centres of labelled samples (called SFCM_V, where V stands for cluster centre). The algorithm refers to the cluster centre of the labelled sample dataset during the clustering process and uses the information of the labelled samples to guide the unlabelled samples during clustering to improve the clustering performance. We compare the SFCM_V algorithm with the current popular semisupervised clustering algorithm and an unsupervised clustering algorithm and perform experiments on real patient mammogram images using DICE and IoU as evaluation metrics; SFCM_V has the highest evaluation metric coefficient. Experiments demonstrate that SFCM_V has higher segmentation accuracy not only for larger lesion regions, such as tumours, but also for smaller lesion regions, such as calcified spots, compared with existing clustering algorithms. Show more

Keywords: Medical image segmentation, semisupervised, fuzzy clustering algorithm, mammogram

DOI: 10.3233/JIFS-224458

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9475-9493, 2023

Authors: Wang, Zeyuan | Cai, Qiang | Lu, Jianping | Wei, Guiwu

Article Type: Research Article

Abstract: With the development of globalization, companies from all over the world are now more closely connected, and they all play different roles in the industry in which they are located. There are more and more companies in a complete supply chain, which can greatly influence the stability of the supply chain, presents certain challenges. Therefore, choosing suppliers with sustainable development capabilities, especially in the event of interruption, can ensure the stability of the entire supply chain, thereby enhancing the company’s image and competitive advantage in a large-scale competition. The sustainable supplier selection is a classical multiple attribute group decision making …(MAGDM) issues. In this study, the dual probabilistic linguistic EDAS (DPL-EDAS) method is built based on the traditional EDAS method and dual probabilistic linguistic term sets (DPLTSs). Firstly, the DPLTSs is introduced. Then, combine the traditional EDAS method with DPLTSs information, the DPL-EDAS method is established and the computing steps for MAGDM are built. Finally, there are a numerical case involving sustainable supplier selection and some comparisons in this paper. The comparisons are used to illustrate advantages of DPL-EDAS method. Show more

Keywords: Multiple attribute group decision making (MAGDM), dual probabilistic linguistic term sets (DPLTSs), EDAS method, ITARA method, sustainable supplier selection

DOI: 10.3233/JIFS-230117

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9495-9512, 2023

Authors: Wang, Encheng | Liu, Xiufeng | Wan, Jiyin

Article Type: Research Article

Abstract: Among the indoor localization algorithms, the algorithm based on traditional Back Propagation Neural Network (BPNN) has the problems of slow convergence and easy to fall into local optimum. It is difficult to apply the algorithm in noisy environments. Therefore, in this paper, we propose a novel indoor localization algorithm where the whole localization process is divided into two parts: data preprocessing and localization output. Data preprocessing means using filtering algorithm to process the Received Signal Strength Indication (RSSI) sequence. It is considered that the initial value of the received sequence has a significant impact on the performance of Kalman Filter …(KF). An improved Kalman Filtering algorithm (DBSCAN-KF) is proposed based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. First, the RSSI values that are seriously disturbed by noise in the sequence are removed using the DBSCAN algorithm, and then the RSSI sequences are processed using KF so that the RSSI values can be closer to the theoretical values. The localization output part is to reduce the localization error caused by the BPNN. In this paper, the Differential Evolution (DE) algorithm and Particle Swarm Optimization (PSO) algorithm are combined, and the Differential Evolution Particle Swarm Optimization (DE-PSO) algorithm is proposed. The BPNN weights and thresholds are optimized in parallel, which improves the speed and ability of global optimization search and further avoids the shortcomings of traditional BPNNs that are prone to fall into local optimization in the training process. Experimental results show that the BPNN localization algorithm based on DBSCAN-KF improves the average localization accuracy by 0.26m compared with the BPNN localization algorithm without filtering. After filtering, the localization algorithm based on DE-PSO improved BPNN (DE-PSO-BP) improves the average localization accuracy by about 24% compared with the localization algorithm based on DE-PSO-BP. The localization algorithm based on DE-PSO-BP improves the average localization accuracy by about 61% compared with the traditional BPNN. Show more

Keywords: Indoor localization, RSSI, Kalman filtering, DBSCAN-KF, DE-PSO-BP

DOI: 10.3233/JIFS-230178

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9513-9525, 2023

Authors: Zhang, Xianyong | Wang, Qian | Fan, Yunrui

Article Type: Research Article

Abstract: Feature selection facilitates classification learning and can resort to uncertainty measurement of rough set theory. By fuzzy neighborhood rough sets, the fuzzy-neighborhood relative decision entropy (FNRDE) motivates a recent algorithm of feature selection, called AFNRDE. However, FNRDE has fusion defects for interaction priority and hierarchy deepening, and such fusion limitations can be resolved by operational commutativity; furthermore, subsequent AFNRDE has advancement space for effective recognition. For the measurement reinforcement, an improved measure (called IFNRDE) is proposed to pursue class-level priority fusion; for the algorithm promotion, the corresponding selection algorithm (called AIFNRDE) is designed to improve AFNRDE. Concretely, multiplication fusion of …algebraic and informational measures is preferentially implemented at the class level, and the hierarchical summation generates classification-level IFNRDE. IFNRDE improves FNRDE, and its construction algorithm and granulation monotonicity are acquired. Then, IFNRDE motivates a heuristic algorithm of feature selection, i.e., AIFNRDE. Finally, relevant measures and algorithms are validated by table examples and data experiments, and new AIFNRDE outperforms current AFNRDE and relevant algorithms FSMRDE, FNRS, FNGRS for classification performances. Show more

Keywords: Feature selection, fuzzy neighborhood rough set, uncertainty measure, relative decision entropy, hierarchical fusion

DOI: 10.3233/JIFS-223384

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9527-9544, 2023

Authors: Shen, Hanhan | Pan, Xiaodong | Peng, Xiaoyu | Dan, Yexing | Qiao, Junsheng

Article Type: Research Article

Abstract: This paper focuses on simplifying the structure of fuzzy systems and improving the precision. By regarding the fuzzy rule base as a mapping from the vague partition on the input universe to the vague partition on the output universe, we first design a new type of fuzzy system using the complete and continuous fuzzy rule base in terms of vague partitions. We then exploit Weierstrass’s approximation theorem to show that this new type of fuzzy system can approximate any real continuous function on a closed interval to arbitrary accuracy and provide the corresponding approximation accuracy with respect to infinite norms. …We also provide two numerical examples to illustrate the effectiveness of this new type of fuzzy system. Both theoretical and numerical results show that this new type of fuzzy system achieves the quite approximation effect with a few fuzzy rules. Show more

Keywords: Vague partition, Fuzzy system, Fuzzy rule base, Approximation

DOI: 10.3233/JIFS-223542

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9545-9563, 2023

Authors: Sathya, V. | Mahendra Babu, G.R. | Ashok, J. | Lakkshmanan, Ajanthaa

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-224586

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9565-9579, 2023

Authors: Yu, Bin | Zhu, Qing | Fu, Yu | Cai, Mingjie

Article Type: Research Article

Abstract: Forecasting is making predictions about what will happen or how things will change. This can help people avoid blindness and losses and play a significant role in their lives. In multi-attribute prediction problems, the correlation between attributes is often ignored, which affects prediction accuracy. Based on fuzzy rough sets and logistic regression, this paper proposes a new logistic regression method that fully considers attribute correlation, namely a twin logistic regression method based on attribute-oriented fuzzy rough sets. Firstly, attribute-oriented fuzzy rough sets are studied and analyzed. Then, the optimistic and pessimistic predictions are achieved by fuzzy rough sets and logistic …regression, and the final result is obtained by fusing the optimistic and pessimistic predictions. Finally, the effectiveness of the twin logistic regression method is verified. Show more

Keywords: Attribute-oriented fuzzy rough set, logistic regression, twin logistic regression based on attribute-oriented fuzzy rough set, multi-attribute prediction

DOI: 10.3233/JIFS-222986

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9581-9597, 2023

Authors: Li, Bing | Cao, Yuwei | Li, Yongkun

Article Type: Research Article

Abstract: In this paper, the existence, uniqueness and global exponential stability of pseudo almost periodic solutions for a class of octonion-valued neutral type high-order Hopfield neural network models with D operator are established by using the Banach fixed point theorem and differential inequality techniques. Compared with most existing models, in this class of networks, all connection weights and activation functions are assumed to be octonion-valued functions except for time delays. And unlike most of the existing methods of studying octonion-valued neural networks, our method is a non-decomposition method, that is, the method of directly studying octonion-valued systems. The results and …methods in this paper are new. In addition, an example and its numerical simulation are given to illustrate the feasibility of our results. Show more

Keywords: Octonion, neutral type neural network, D operator, pseudo almost periodic solution, global exponential stability

DOI: 10.3233/JIFS-223766

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9599-9613, 2023

Authors: Zhu, Yakun | Gong, Weiqiang | Lu, Xuesong | Wang, Haixian

Article Type: Research Article

Abstract: Using functional neuroimaging, electrophysiological techniques and neural data processing techniques, neuroscientists have found that mathematically gifted adolescents exhibit unusual neurocognitive features in the activation of task-related brain regions. Hemispheric information interaction, functional reorganization of networks, and utilization of task-related brain regions are beneficial to rapid and efficient task processing. Based on Granger causality channel selection, the transfer entropy (TE) value between effective channels was computed, and the information flow patterns in the directed functional brain networks derived from electroencephalography (EEG) data during deductive reasoning tasks were explored. We evaluated the workspace configuration patterns of the brain network and the global …integration characteristics of separated brain regions using node strength, motif, directed clustering coefficient and characteristic path length in the brain networks of mathematically gifted adolescents with effective connectivity. The empirical results demonstrated that a more integrated functional network at the global level and a more efficient clique at the local level support a pattern of workspace configuration in the mathematically gifted brain that is more conducive to task-related information processing. Show more

Keywords: Effective connectivity, EEG, mathematically gifted adolescents, information flow, graph theory

DOI: 10.3233/JIFS-223819

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9615-9626, 2023

Authors: Varish, Naushad | Hasan, Mohammad Kamrul | Khan, Asif | Zamani, Abu Taha | Ayyasamy, Vadivel | Islam, Shayla | Alam, Rizwan

Article Type: Research Article

Abstract: This paper proposed a novel texture feature extraction technique for radar remote sensing image retrieval application using adaptive tetrolet transform and Gray level co-occurrence matrix. Tetrolets have provided fine texture information in the radar image. Tetrominoes have been employed on each decomposed radar image and best pattern of tetrominoes has been chosen which represents the better radar image geometry at each decomposition level. All three high pass components of the decomposed radar image at each level and low pass component at the last level are considered as input values for Gray level co-occurrence matrix (GLCM), where GLCM provides the spatial …relationship among the pixel values of decomposed components in different directions at certain distances. The GLCMs of decomposed components are computed in (1). (0, π/2, π, 3π/2), (2). (π/4, 3π/4, 5π/4, 7π/4) (3). (0, π/4, π/2, 3π/4, π, 3π/2, 5π/4, 7π/4) directions individually and subsequently a texture feature descriptor is constructed by computing statistical parameters from the corresponding GLCMs. The retrieval performance is validated on two standard radar remote sensing image databases: 20-class satellite remote sensing dataset and 21-class land-cover dataset. The average metrices i.e., precision, recall and F-score are 61.43%, 12.29% and 20.47% for 20-class satellite remote sensing dataset while 21-class land-cover dataset have achieved 67.75%, 9.03% and 15.94% average metrices. The retrieved results show the better accuracy as compared to the other related state of arts radar remote sensing image retrieval methods. Show more

Keywords: Radar remote sensing image retrieval, adaptive tetrolet transform, gray level Co-occurrence matrix, prediction learning, statistical parameters

DOI: 10.3233/JIFS-224083

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9627-9650, 2023

Authors: Du, Baigang | Zha, Dahu | Guo, Jun | Yu, Xiaobing

Article Type: Research Article

Abstract: The water transmission and distribution process of the water supply pump station of the water purification plant plays a key role in the entire urban water supply system. When the requirements of water supply quantity and water pressure are satisfied, the reduction of operating energy consumption of the pump set and improvement of its service life are urgent problems. Therefore, to reduce the cost of water supply pump station, a mathematical model is established to minimize the energy consumption of pump group, the number of pump switches and the load balancing in this paper. In order to solve the pump …scheduling problem, a two-stage strategy based on genetic algorithm is proposed. In stage one, the frequency conversion ratio and the number of pumps needed to be turned on at the lowest energy consumption are calculated. In stage two, through the improved genetic algorithm and iterative way to reduce the number of pump switches and load balancing. Finally, a case study from a real waterworks in Suzhou, China is used to verify the validity of the proposed model. Numerical results reveal that the improved genetic algorithm outperforms the competing algorithms. In addition, a proper sensitivity analysis allows assessing the effects under different pump operating conditions. Show more

Keywords: Pump scheduling, load balancing, improved genetic algorithm

DOI: 10.3233/JIFS-224245

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9651-9669, 2023

Authors: Hashmi, Mohammad Farukh | Naik, Banoth Thulasya | Keskar, Avinash G.

Article Type: Research Article

Abstract: Computer vision algorithms based on deep learning have evolved to play a major role in sports analytics. Nevertheless, in sports like table tennis, detecting the ball is a challenge as the ball travels at a high velocity. However, the events in table tennis games can be detected and classified by obtaining the locations of the ball. Therefore, existing methodologies predict the trajectories of the ball but do not detect and classify the in-game events. This paper, therefore, proposes a ball detection and trajectory analysis (BDTA) approach to detect the location of the ball and predict the trajectory to classify events …in a table tennis game. The proposed methodology is composed of two parts: i) Scaled-YOLOv4 which can detect the precise position of the ball ii) Analysis of trajectory based on ball coordinates to detect and classify the events. The dataset was prepared and labeled as a ball after enhancing the frame resolution with a super-resolution technique to get the accurate position of the ball. The proposed approach demonstrates 97.8% precision and 98.1% f1-score in detecting the location of the ball and 97.47% precision and achieved 97.8% f-score in classifying in-game events. Show more

Keywords: Table tennis sport, ball detection, event classification, Scaled-YOLOv4, Trajectory analysis

DOI: 10.3233/JIFS-224300

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9671-9684, 2023

Authors: Huang, Juan | Zhang, Chaoren

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-230572

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9685-9696, 2023

Authors: Shanmuga Priya, K. | Vasanthi, S.

Article Type: Research Article

Abstract: An emotion is a conscious logical response that varies for different situations in women’s life. These mental responses are caused by physiological, cognitive, and behavioral changes. Gender-based violence undermines the participation of women in decision-making, resulting in a decline in their quality of life. More accurate and automatic classification of women’s emotions can enhance human-computer interfaces and security in real time. There are some wearable technologies and mobile applications that claim to ensure the safety of women. However, they rely on limited social action and are ineffective at ensuring women’s safety when and where it is needed. In this work, …a novel CDB-LSTM network has been proposed to accurately classify the emotions of women in seven different classes. The electroencephalogram (EEG) offers non-radioactive methods of identifying emotions. Initially, the EEG signals are preprocessed and they are converted into images via Time-Frequency Representation (TPR). A smoothed pseudo-Wigner-Ville distribution (SPWVD) is employed to convert the EEG time-domain signals into input images. Consequently, these converted images are given as input to the Convolutional Deep Belief Network (CDBN) for extracting the most relevant features. Finally, Bi-directional LSTM is used for classifying the emotions of women into seven classes namely: happy, relax, sad, fear, anxiety, anger, and stress. The proposed CDB-LSTM network preserves the high accuracy range of 97.27% in the validation phase. The proposed CDB-LSTM network improves the overall accuracy by 6.20% 32.98% 6.85% and 3.30% better than CNN-LSTM, Multi-domain feature fusion model, GCNN-LSTM and CNN with SVM and DT respectively. Show more

Keywords: Women safety, EEG signals, emotion classification, smoothed pseudo-wigner-ville distribution, convolutional deep belief network, bi-directional LSTM

DOI: 10.3233/JIFS-221825

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9697-9707, 2023

Authors: Chitra, R. | Prabakaran, K.

Article Type: Research Article

Abstract: Accumulation of q ˜ -rung picture fuzzy information plays an essential part in decision-making situations. q ˜ -rung picture fuzzy sets can handle the uncertain information more precisely and flexibly because of the presence of parameter q ˜ . Also the Frank t-norm and t-conorm operations perform suitably for the data accumulation with the operational parameter. In this paper, we introduce q ˜ -Rung picture fuzzy Frank weighted averaging operator and q ˜ -rung picture …fuzzy Frank weighted geometric operator by extending q ˜ -rung orthopair fuzzy Frank arithmetic and geometric aggregation operators respectively. We establish an algorithm to address the tedious decision-making problems using these operators. Eventually, we discuss a multiple attribute decision-making problem to demonstrate the utility and efficacy of the proposed method. A comparison of existing methods is made to reveal the supremacy and benefits of our proposed method. Show more

Keywords: Accumulation, q-rung picture fuzzy, Frank weighted averaging, Frank weighted geometric, decision-making

DOI: 10.3233/JIFS-221889

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9709-9721, 2023

Authors: Nguyen, Tuan Anh

Article Type: Research Article

Abstract: This article studies the instability of automobiles when steering at high speeds. In this article, the model of spatial dynamics is used to simulate vehicle oscillation. Besides, the model of nonlinear double-track dynamics is also combined to determine the effects of the wheel when steering. To limit the instability when steering, the hydraulic stabilizer bar is suggested. The performance of the system depends on the previously designed controller. The FLC algorithm with two inputs is used to control the operation of the system. The membership function and fuzzy rules are determined based on the designer’s experience. The simulation is performed …by MATLAB software with three specific steering cases. In each case, the speed of the vehicle will be increased gradually. The results of the article show that the value of the roll angle is greatest in the third case, corresponding to the speed of v3  = 100 (km/h). If the vehicle does not have a stabilizer bar, the vehicle can roll over at any time. In contrast, when the active stabilizer bar was combined with the proposed FLC algorithm, the vehicle’s stability was significantly improved. The vehicle’s roll angle and the difference in vertical force at the wheels were also significantly reduced when using this algorithm for the stabilizer bar model. This result should be further verified through the experimental process. Show more

Keywords: Rollover, active stabilizer bar, nonlinear dynamics model, fuzzy control

DOI: 10.3233/JIFS-222780

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9723-9741, 2023

Authors: Huang, Shuangliu | Chen, Huazai

Article Type: Research Article

Abstract: As one of the teaching models that promote the orderly development of vocational education in China, the integration of industry and education has been recognized by all sectors of society in China’s many years of practice. In recent years, with the strong advocacy of the education sector in China, its development speed has been rapidly improved. Rural vocational education in China has also actively implemented and innovated the teaching mode of integration of industry and education, which has trained more excellent talents for agricultural development in various regions. The quality evaluation of industry-education integration for rural vocational education in the …perspective of rural revitalization is viewed as the multiple attribute group decision making (MAGDM). In this paper, the probabilistic linguistic Mixed Aggregation by Comprehensive Normalization Technique (PL-MACONT) method is built for MAGDM. At last, to verify the validity of the extended method, a numerical example to further account for quality evaluation of industry-education integration for rural vocational education in the perspective of rural revitalization is put into use. Show more

Keywords: Multiple attribute group decision making (MAGDM), Probabilistic linguistic term sets (PLTSs), Mixed Aggregation by Comprehensive Normalization Technique (MACONT), entropy weight method (EWM), quality evaluation of industry-education integration

DOI: 10.3233/JIFS-223856

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9743-9755, 2023

Authors: Wei, Chun | Shi, Haiyan | Liu, Baoliang | Zhang, Zhiqiang | Wen, Yanqing

Article Type: Research Article

Abstract: A system undergoes a failure process in which the internal degradation and external loads are independent and compete with each other. In the reliability model of competitive failure, the threshold of failure is often a dynamic process that changes with time. Based on this, this paper constructs a model in which the failure threshold is an uncertain Liu process and applies it to the competitive failure reliability process, where soft and hard failure thresholds are modeled by different Liu processes. In the absence of a large amount of failure data, uncertainty theory is used as a tool to analyze the …belief reliability and mean time to failure of the system. Taking gas-insulated substation (GIS) as an example, the effect of parameters on belief reliability is analyzed, and the reliability under Liu process threshold and constants threshold is compared, which shows the validity of the prosed model. Show more

Keywords: Belief reliability, uncertain failure threshold, uncertain liu process, uncertainty theory

DOI: 10.3233/JIFS-224057

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9757-9767, 2023

Authors: Kalaivani, K. | Kshirsagarr, Pravin R. | Sirisha Devi, J. | Bandela, Surekha Reddy | Colak, Ilhami | Nageswara Rao, J. | Rajaram, A.

Article Type: Research Article

Abstract: The electrocardiogram (ECG), electroencephalogram (EEG), and electromyogram (EMG) are all very useful diagnostic techniques. The widespread availability of mobile devices plus the declining cost of ECG, EEG, and EMG sensors provide a unique opportunity for making this kind of study widely available. The fundamental need for enhancing a country’s healthcare industry is the ability to foresee the plethora of ailments with which people are now being diagnosed. It’s no exaggeration to say that heart disease is one of the leading causes of mortality and disability in the world today. Diagnosing heart disease is a difficult process that calls for much …training and expertise. Electrocardiogram (ECG) signal is an electrical signal produced by the human heart and used to detect the human heartbeat. Emotions are not simple phenomena, yet they do have a major impact on the standard of living. All of these mental processes including drive, perception, cognition, creativity, focus, attention, learning, and decision making are greatly influenced by emotional states. Electroencephalogram (EEG) signals react instantly and are more responsive to changes in emotional states than peripheral neurophysiological signals. As a result, EEG readings may disclose crucial aspects of a person’s emotional states. The signals generated by electromyography (EMG) are gaining prominence in both clinical and biological settings. Differentiating between neuromuscular illnesses requires a reliable method of detection, processing, and classification of EMG data. This study investigates potential deep learning applications by constructing a framework to improve the prediction of cardiac-related diseases using electrocardiogram (ECG) data, furnishing an algorithmic model for sentiment classification utilizing EEG data, and forecasting neuromuscular disease classification utilizing EMG signals. Show more

Keywords: Electrocardiography (ECG), electroencephalography (EEG), electromyographic (EMG), deeplearning techniques, prediction, heart attack, emotion recognition, neuromuscular disease, R-CNN

DOI: 10.3233/JIFS-230399

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9769-9782, 2023

Authors: Kianifar, Mohammad Ali | Motallebi, Hassan | Bardsiri, Vahid Khatibi

Article Type: Research Article

Abstract: Dynamic Classifier Selection (DCS) techniques aim to select the most competent classifiers from an ensemble per test sample. For each test sample, only a subset of the most competent classifiers is used to estimate its target value. The performance of the DCS highly depends on how we define the local region of competence, which is a local region in the feature space around the test sample. In this paper, we propose a new definition of region of competence based on a new proximity measure. We exploit the observed similarities between traffic profiles at different links, days and hours to obtain …similarities between different values. Furthermore, long-term traffic pattern prediction is a complex problem and most of the traffic prediction literature are based on time-series and regression approaches and their prediction time is limited to next few hours or days. We tackle the long-term traffic pattern prediction as a classification of discretized traffic indicators to improve the accuracy of urban traffic pattern forecasting of next weeks by using DCS. We also employ two different link clustering methods, for grouping traffic links. For each cluster, we train a dynamic classifier system for predicting the traffic variables (flow, speed and journey time). Our results on strategic road network data shows that the proposed method outperforms the existing ensemble and baseline models in long-term traffic prediction. Show more

Keywords: Long-term traffic prediction, monthly SRN data set, traffic link clustering, dynamic classifier selection, region of competence

DOI: 10.3233/JIFS-220759

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9783-9797, 2023

Authors: Ramesh, Pinapilli | Yadaiah, Narri

Article Type: Research Article

Abstract: This paper presents the design and development of Brain Emotional Learning based adaptive Type-2 Fuzzy Systems for control of dynamical systems. The BEL controller belongs to the class of bio inspired controllers, as its architecture is based on limbic system of human brain and is capable of providing solutions for complex real time problems. In this work, dynamics of Brain Emotional Learning are used for the adaptation of membership functions in the design of Type-2 Fuzzy Logic Controllers. The stability of the overall system is analysed through Lyapunov Yakubovich’s criteria. The proposed approach is validated on the benchmark system such …as inverted pendulum, CSTR and Ship heading control through simulation and in real-time environment using OPAL RT OP5600. Show more

Keywords: Type-2 fuzzy logic controller, brain emotional learning, adaptive memberships functions

DOI: 10.3233/JIFS-222143

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9799-9820, 2023

Authors: Wang, Yuan | Yu, Xiaobing | Wang, Xuming

Article Type: Research Article

Abstract: Multi-verse optimizer (MVO) is a novel nature-inspired algorithm that has been applied to solve many practical optimization problems. Nevertheless, the original MVO has problems of low convergence speed and accuracy of final solutions. Besides, the failure to strike a balance between exploration and exploitation and the easiness of falling into local optimum in the early stages makes MVO hard to converge. In this paper, we propose a novel hybrid algorithm called Hybrid Queuing Search algorithm with MVO (HQS-MVO) by introducing Queuing Search Algorithm (QSA) and Metropolis rule to overcome these shortcomings. The introduction of QSA is to improve the accuracy …of final solutions. At the same time, the Metropolis rule is employed to prevent the algorithm from falling into the local optimum, thus improving the convergence speed of the original MVO. Then, we compare the performance of HQS-MVO on 30 benchmark functions of CEC2014 and 10 benchmark functions of CEC2019 with the other four related algorithms and three latest algorithms. The results show that HQS-MVO has the most accurate solutions in most cases compared with other seven algorithms in most cases, and gains the lowest standard deviations. Moreover, we make convergence curve of the eight algorithms. Compared with other algorithms, HQS-MVO shows outstanding performances and converge faster in general. Finally, we apply the proposed algorithm in a real engineering optimization problem and compare its performance with other algorithms, the results show that HQS-MVO is still the best one in problem of designing of gear train. Show more

Keywords: Multi-verse optimizer, queuing searching algorithm, metropolis rule

DOI: 10.3233/JIFS-223369

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9821-9845, 2023

Authors: Zhu, Xingchen | Wu, Xiaohong | Wu, Bin | Zhou, Haoxiang

Article Type: Research Article

Abstract: The fuzzy c-mean (FCM) clustering algorithm is a typical algorithm using Euclidean distance for data clustering and it is also one of the most popular fuzzy clustering algorithms. However, FCM does not perform well in noisy environments due to its possible constraints. To improve the clustering accuracy of item varieties, an improved fuzzy c-mean (IFCM) clustering algorithm is proposed in this paper. IFCM uses the Euclidean distance function as a new distance measure which can give small weights to noisy data and large weights to compact data. FCM, possibilistic C-means (PCM) clustering, possibilistic fuzzy C-means (PFCM) clustering and IFCM are …run to compare their clustering effects on several data samples. The clustering accuracies of IFCM in five datasets IRIS, IRIS3D, IRIS2D, Wine, Meat and Apple achieve 92.7%, 92.0%, 90.7%, 81.5%, 94.2% and 88.0% respectively, which are the highest among the four algorithms. The final simulation results show that IFCM has better robustness, higher clustering accuracy and better clustering centers, and it can successfully cluster item varieties. Show more

Keywords: Fuzzy clustering, FCM, PCM, Euclidean distance, distance function

DOI: 10.3233/JIFS-223576

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9847-9862, 2023

Authors: Bolourchi, Pouya | Ghasemzadeh, Aman

Article Type: Research Article

Abstract: In bioinformatics studies, many modeling tasks are characterized by high dimensionality, leading to the widespread use of feature selection techniques to reduce dimensionality. There are a multitude of feature selection techniques that have been proposed in the literature, each relying on a single measurement method to select candidate features. This has an impact on the classification performance. To address this issue, we propose a majority voting method that uses five different feature ranking techniques: entropy score, Pearson’s correlation coefficient, Spearman correlation coefficient, Kendall correlation coefficient, and t -test. By using a majority voting approach, only the features that appear in …all five ranking methods are selected. This selection process has three key advantages over traditional techniques. Firstly, it is independent of any particular feature ranking method. Secondly, the feature space dimension is significantly reduced compared to other ranking methods. Finally, the performance is improved as the most discriminatory and informative features are selected via the majority voting process. The performance of the proposed method was evaluated using an SVM, and the results were assessed using accuracy, sensitivity, specificity, and AUC on various biomedical datasets. The results demonstrate the superior effectiveness of the proposed method compared to state-of-the-art methods in the literature. Show more

Keywords: Classification, correlation coefficient, feature selection, feature ranking, gene data, majority

DOI: 10.3233/JIFS-224029

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9863-9877, 2023

Authors: Mecheri, Karima | Klai, Sihem | Souici-Meslati, Labiba

Article Type: Research Article

Abstract: Web service recommender systems have a fundamental role in the selection, composition and substitution of services. Indeed, they are used in several application areas such as Web APIs and Cloud Computing. Likewise, Deep Learning techniques have brought undeniable advantages and solutions to the challenges faced by recommendations in all areas. Unfortunately, the field of Web services has not yet benefited well from these deep methods, moreover, the works using these methods for Web services domain are very recent compared to the works of other fields. Thus, the objective of this paper is to study and analyze state-of-the-art work on Web …services recommender systems based on Deep Learning techniques. This analysis will help readers wishing to work in this field, and allows us to direct our future work concerning the Web services recommendation by exploiting the advantages of Deep Learning techniques. Show more

Keywords: Deep learning, recommendation systems, web services, mashup, quality of service, performance evaluation metrics

DOI: 10.3233/JIFS-224565

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9879-9899, 2023

Authors: Qu, Ying | Chen, Hong

Article Type: Research Article

Abstract: During an emergency, the negative Internet public opinion in colleges and universities, especially the negative endogenous public opinion, will have a serious impact on the reputation of colleges and universities. It is of great significance to find out the negative influencing factors of endogenous public opinion and explore the mechanism of public opinion dissemination for resolving the crisis of public opinion in universities. The existing research does not distinguish the endogenous Internet public opinion in colleges and universities from the general Internet public opinion in colleges and universities, and the SIR model adopted fails to fully reflect the difference between …students and other dissemination subjects of endogenous public opinion in campus. In addition, various research methods and models currently used focus on the static expression of dissemination results, and the explanation of results is insufficient. The reason is that they do not well express the dynamic interaction mechanism between influencing factors and the dynamic conversion rate between roles. In this study, based on the improved infectious disease model and system dynamics theory, AnyLogic software is used to simulate the improved SNIDR model of infectious disease, to analyze the sensitivity of school supervision, school intervention, school response time and information transparency and to study the dynamic conversion rate between different roles. The SNIDR model effectively simulates the process of endogenous public opinion dissemination in colleges and universities after emergencies. The results show that, what has the greatest impact on the dissemination of public opinion is the school’s supervision and intervention efforts, which can suppress the dissemination from the source. Information transparency is an auxiliary variable and cannot function independently. During the dissemination period, the timelier the school responds, the faster the spreaders will drop to zero, and the better it will be to control the secondary dissemination of public opinion. Show more

Keywords: SNIDR model, governance strategies, internet public opinion, dissemination mechanism, emergency

DOI: 10.3233/JIFS-230002

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9901-9917, 2023

Authors: Liu, Biyu | Chen, Ting | Yang, Haidong | Segerstedt, Anders

Article Type: Research Article

Abstract: Suppliers significantly affect the effectiveness of sustainable supply chain management. Hence, it is extremely important to evaluate and select suppliers scientifically and objectively. Based on the theory of triple bottom line (economic, social, and environmental dimension) and a balanced scorecard, a measureable supplier evaluation framework in a sustainable supply chain is first formulated. Second, to reduce the defects of the single weight method, the subjective and objective weights of evaluation indicators are determined by combining the fuzzy best-worst method (BWM) and the entropy method, and then the combination weights are obtained through linear weighting. Third, the grey relational technique for …order performance by similarity to ideal solution (TOPSIS) method is further adopted to evaluate and rank the suppliers. Finally, a case study illustrates and demonstrates the availability of the proposed supplier evaluation index system and evaluation method. Subsequently, some suggestions are proposed according to the results. Show more

Keywords: Sustainable supply chain management, supplier evaluation, the fuzzy BWM, grey relational, TOPSIS

DOI: 10.3233/JIFS-212996

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9919-9932, 2023

Authors: Gao, Wang | Ni, Mingyuan | Deng, Hongtao | Zhu, Xun | Zeng, Peng | Hu, Xi

Article Type: Research Article

Abstract:  As people increasingly use social media to read news, fake news has become a major problem for the public and government. One of the main challenges in fake news detection is how to identify them in the early stage of propagation. Another challenge is that detection model training requires large amounts of labeled data, which are often unavailable or expensive to acquire. To address these challenges, we propose a novel Fake News Detection model based on Prompt Tuning (FNDPT). FNDPT first designs a prompt-based template for early fake news detection. This mechanism incorporates contextual information into textual content and extracts …relevant knowledge from pre-trained language models. Furthermore, our model utilizes prompt-based tuning to enhance the performance in a few-shot setting. Experimental results on two real-world datasets verify the effectiveness of FNDPT. Show more

Keywords: Fake news detection, few-shot, prompt-based tuning, pre-trained language model

DOI: 10.3233/JIFS-221647

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9933-9942, 2023

Authors: Geo Jenefer, G. | Deepa, A.J.

Article Type: Research Article

Abstract: Globally, diabetes directly causes 1.5 million fatalities each year. It is necessary to predict such diseases at an earlier stage and cure them. Since modern healthcare data comprises huge amounts of information, it is tough to process such data in conventional databases. Previously, various machine learning (ML) algorithms were used to predict diabetics, and their performance was evaluated. But still, those existing algorithms result in poor accuracy and performance.This work proposes a FOCB (Firefly Optimization-based CatBoost) classifier for predicting diabetes. The PIMA Indian diabetic dataset has been taken as the input dataset. The proposed FOCB algorithm has been compared with …various machine learning algorithms. From the results, we can see that the FOCB classifier gives the best accuracy of 96% with improved performance. The proposed system has been compared with other FO-based machine learning algorithms like NB, KNN, RF, AB, GB, XGB, CNN, DBN, and CB, and it has been proven that CB based on FO produces better accuracy with less hamming loss. Show more

Keywords: CatBoost(CB), feature scaling, machine learning

DOI: 10.3233/JIFS-223105

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9943-9954, 2023

Authors: Dhiyanesh, B. | Rameshkumar, M. | Karthick, K. | Radha, R.

Article Type: Research Article

Abstract: Healthcare data is the most sensitive information for processing through machine learning and cloud computing in the various healthcare organizations. Electronic Health Record (EHR) manipulation are now on the rise, and we need to focus on using the data generated by the healthcare applications. Many sensitive data are associated with various health care domains, particularly neurology and cardiology. Previous approaches, such as manual data records, had significant disadvantages, and hence disease prediction based on the above records was found ineffective resulting with improper diagnosis on the patients. These data records require special attention, and current frameworks focused on these areas …must implement sophisticated technologies to predict specific patterns. To address the above concerns, the proposed work incorporates the integration of Neuro Fuzzy Logistic Regression (NFLR) machine learning algorithm and cloud computing storage management to solve these problems. The usage of cloud storage reduces data duplication while handling the storage of EHRs where the proposed ML algorithm accurately predict the disease. In the proposed research, the features are extracted using a specific algorithm –Self-organizing Clustering (SOC) which forms a clustered data with highest weight. To select the maximum number of features, and to predict the disease risk factors, the S2 NO algorithm and NFLR algorithms are used in this work. Further, the database storage estimation with fuzzy rules, logistic analysis, and other benefits such as experimental learning of different ML tools, data privacy constraints related to healthcare are considered in this paper. Show more

Keywords: Neuro-Fuzzy Logistic Regression (NFLR), Social Spider Neural Optimization (S2NO), Self-organizing Clustering (SOC), Electronic Health Record (EHR), Healthcare Medical database

DOI: 10.3233/JIFS-223280

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9955-9964, 2023

Authors: Zhang, Yunqi | Sheng, Yuhong

Article Type: Research Article

Abstract:  Risk measurement and insurance pricing have always been issues of concern in actuarial science. Under the framework of uncertainty theory, this paper puts forward a new premium principle: uncertain standard deviation premium principle, proposes some of its properties about risk and compares the premiums of different risks. Based on the utility function of risk aversion, the additional premium coefficient is derived and two specific numerical examples are used to calculate the maximum premium. Furthermore, the unknown parameters of the policy with deductible are estimated by uncertain moment estimation and uncertain maximum likelihood estimation.

Keywords: Uncertainty theory, standard deviation premium principle, additional premium coefficient, utility function, parameter estimation

DOI: 10.3233/JIFS-223297

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9965-9975, 2023

Authors: Yu, Yan | Qiu, Dong | Yan, Ruiteng

Article Type: Research Article

Abstract: To mine more semantic information between words, it is important to utilize the different semantic correlations between words. Focusing on the different degrees of modifying relations between words, this article provides a quantum-like text representation based on syntax tree for fuzzy semantic analysis. Firstly, a quantum-like text representation based on density matrix of individual words is generalized to represent the relationship of modification between words. Secondly, a fuzzy semantic membership function is constructed to discuss the different degrees of modifying relationships between words based on syntax tree. Thirdly, the tensor dot product is defined as the sentence semantic similarity by …combining the operation rules of the tensor to effectively exploit the semantic information of all elements in the quantum-like sentence representation. Finally, extensive experiments on STS’12, STS’14, STS’15, STS’16 and SICK show that the provided model outperforms the baselines, especially for the data set containing multiple long-sentence pairs, which confirms there are fuzzy semantic associations between words. Show more

Keywords: Quantum-like text representation, fuzzy semantic analysis, fuzzy semantic membership function, neural networks, syntax tree

DOI: 10.3233/JIFS-223499

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9977-9991, 2023

Authors: Dai, Songsong | Zheng, Jianwei

Article Type: Research Article

Abstract: In a recent work (Wang et al. 2020), a partial order ⪯, a join operation ⊔ and a meet operation ⊓ of probabilistic linguistic term sets (PLTSs) were introduced and it was proved that L 1  ⊓ L 2  ⪯ L 1  ⪯ L 1  ⊔ L 2 and L 1  ⊓ L 2  ⪯ L 2  ⪯ L 1  ⊔ L 2 . In this paper, we demonstrate that its join and meet operations are not satisfy the above requirement. To satisfy this requirement, we modify its join and meet operations. Moreover, we define a negation operation of PLTSs based on the partial order ⪯. The …combinations of the proposed negation, the modified join and meet operations yield a bounded, distributive lattice over PLTSs. Meanwhile, we also define a new join operation and a new meet operation which, together with the negation operation, yield a bounded De Morgan over PLTSs. Show more

Keywords: Probabilistic linguistic term sets, operations, orders, lattices

DOI: 10.3233/JIFS-223747

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 9993-10003, 2023

Authors: Fu, Chao | Qin, Keyun | Yang, Lei | Hu, Qian

Article Type: Research Article

Abstract: Covering rough sets have been successfully applied to decision analysis because of the strong representing capability for uncertain information. As a research hotspot in decision analysis, hesitant fuzzy multi-attribute decision-making (HFMADM) has received increasing attention. However, the existing covering rough sets cannot handle hesitant fuzzy information, which limits its application. To tackle this problem, we set forth hesitant fuzzy β-covering rough set models and discuss their application to HFMADM. Specifically, we first construct four types of hesitant fuzzy β-covering ( T , I ) rough set models via hesitant fuzzy logic operators and hesitant fuzzy …β-neighborhoods, which can handle hesitant fuzzy information without requiring any prior knowledge other than the data sets. Then, some intriguing properties of these models and their relationships are also discussed. In addition, we design a new method to deal with HFMADM problems by combining the merits of the proposed models and the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method. In this method, we not only consider the risk preferences of decision-makers, but also present a new hesitant fuzzy similarity measure expressed by hesitant fuzzy elements to measure the degree of closeness between two alternatives. Finally, an enterprise project investment problem is applied to illustrate the feasibility of our proposed method. Meanwhile, the stability and effectiveness of our proposed method are also verified by sensitivity and comparative analyses. Show more

Keywords: Hesitant fuzzy sets, covering rough sets, hesitant fuzzy logic operators, hesitant fuzzy β-covering, multi-attribute decision-making

DOI: 10.3233/JIFS-223842

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10005-10025, 2023

Authors: Wali, Aamir | Ahmad, Muzammil | Naseer, Asma | Tamoor, Maria | Gilani, S.A.M.

Article Type: Research Article

Abstract: Deep networks require a considerable amount of training data otherwise these networks generalize poorly. Data Augmentation techniques help the network generalize better by providing more variety in the training data. Standard data augmentation techniques such as flipping, and scaling, produce new data that is a modified version of the original data. Generative Adversarial networks (GANs) have been designed to generate new data that can be exploited. In this paper, we propose a new GAN model, named StynMedGAN for synthetically generating medical images to improve the performance of classification models.  StynMedGAN builds upon the state-of-the-art styleGANv2 that has produced remarkable results …generating all kinds of natural images. We introduce a regularization term that is a normalized loss factor in the existing discriminator loss of styleGANv2. It is used to force the generator to produce normalized images and penalize it if it fails. Medical imaging modalities, such as X-Rays, CT-Scans, and MRIs are different in nature, we show that the proposed GAN extends the capacity of styleGANv2 to handle medical images in a better way. This new GAN model (StynMedGAN) is applied to three types of medical imaging: X-Rays, CT scans, and MRI to produce more data for the classification tasks. To validate the effectiveness of the proposed model for the classification, 3 classifiers (CNN, DenseNet121, and VGG-16) are used. Results show that the classifiers trained with StynMedGAN-augmented data outperform other methods that only used the original data. The proposed model achieved 100%, 99.6%, and 100% for chest X-Ray, Chest CT-Scans, and Brain MRI respectively. The results are promising and favor a potentially important resource that can be used by practitioners and radiologists to diagnose different diseases. Show more

Keywords: GANs, deep learning, synthetic data, data augmentation, CNN, styleGANv2, brain tumor, MRI, CT-scan, CXRs

DOI: 10.3233/JIFS-223996

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10027-10044, 2023

Authors: Zhu, Sheng | Tan, Min Keng | Lim, Kit Guan | Chin, Renee Ka Yin | Chua, Bih Lii | Teo, Kenneth Tze Kin

Article Type: Research Article

Abstract: Misfire fault is a common engine failure which is caused by incomplete combustion in the engine cylinders. Conventionally, the misfire fault is diagnosed manually by mechanics, but the diagnosis process is time-consuming. Therefore, this study aims to explore the feasibility of using Subtractive Clustering based Adaptive Neuro-Fuzzy Inference System (SC-ANFIS) algorithm to assist in diagnosing misfire faults. The Subtractive Clustering (SC) approach initializes the parameters of Adaptive Neuro-Fuzzy Inference System (ANFIS), whereas Back Propagation (BP) and Least Square Estimation (LSE) approaches are implemented to optimize the ANFIS parameters. The proposed algorithm will pre-diagnose the cause of misfire faults based on …the engine exhaust gas. In this work, exhaust gases for different causes of misfire faults are collected from Volkswagen 1.8TSI 4-cylinder petrol engine. These collected data are used to train the proposed algorithm. The performances of the proposed algorithm are compared to two commonly used algorithms, namely Fuzzy C-Mean Clustering based ANFIS (FCM-ANFIS) and BP algorithms. The simulation results show the proposed algorithm has improved 2.4% to 5.5% averagely in terms of accuracy, efficiency and stability. Show more

Keywords: Engine misfire, fault diagnosis, SC-ANFIS, FCM-ANFIS

DOI: 10.3233/JIFS-224059

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10045-10066, 2023

Authors: Wu, Meiqin | Song, Jiawen | Fan, Jianping

Article Type: Research Article

Abstract: As COVID-19 swept through, production in various industries was affected. Epidemic control leads to logistical disruptions from time to time and suppliers have to make production and shipping decisions after analyzing the customer’s situation. Therefore, the majority of manufacturers need to establish effective methods for the selection of distribution customers. The method presented in this paper can classify customers into three regions and rank their status to help suppliers effectively make decisions. The three-way decision (3WD) is a well-known fast sorting method in multi-attribute decision-making (MADM). In this paper, we proposed the 3WD model based on Indifference Threshold based Attribute …Ratio Analysis (ITARA), ELimination Et Choix Traduisant la REalite III (ELLECTRE III) in the spherical fuzzy environment. Then, we used the SF-ITARA-ELECTRE III-3WD method to select the suitable customers for dispensing. In addition, comparison with the conventional SF-PROMETHEE-3WD, SF-EVAMIX-3WD, SF-TOPSIS-3WD and SF-VIKOR-3WD are created to verify the effectiveness of the proposed method. An effective risk-averse solution to the MADM problem for spherical fuzzy environment is provided. Show more

Keywords: 3WD, ITARA, ELECTRE III, spherical fuzzy number (SFN), customers selection

DOI: 10.3233/JIFS-224062

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10067-10084, 2023

Authors: Liu, Xinyu | Liu, Lu | Jiang, Tianhua

Article Type: Research Article

Abstract: Energy-aware scheduling has been viewed as a feasible way to reduce energy consumption during the production process. Recently, energy-aware job shop scheduling problems (EAJSPs) have received wide attention in the manufacturing area. However, the majority of previous literature about EAJSPs supposed that all jobs are fabricated in the in-house workshop, while the outsourcing of jobs to some available subcontractors is neglected. To get close to practical production, the outsourcing and scheduling are simultaneously determined in an energy-aware job shop problem with outsourcing option (EAJSP-OO). To formulate the considered problem, a novel mathematical model is constructed to minimize the sum of …completion time cost, outsourcing cost and energy consumption cost. Considering the strong complexity, a self-learning interior search algorithm (SLISA) is developed based on reinforcement learning. In the SLISA, a new Q-learning algorithm is embedded to dynamically select search strategies to prevent blind search in the iteration process. Extensive experiments are carried out to evaluate the performance of the proposed algorithm. Simulation results indicate that the SLISA is superior to the compared existing algorithms in more than 50% of the instances of the considered EAFJSP-OO problem. Show more

Keywords: Job shop, outsourcing option, energy-aware scheduling, interior search algorithm

DOI: 10.3233/JIFS-224624

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10085-10100, 2023

Authors: Zhang, Zhandong | Wang, Xiaoyan

Article Type: Research Article

Abstract: Traditional Chinese medicine is a complex discipline that needs to combine theory with practice under the background of the magnificent Chinese history and civilization. It is a subject that needs “lifelong” learning. Teachers should gradually change the dull and rigid teaching mode in the past and explore a scientific and effective teaching mode that conforms to the background of the current era. Applying the advantages of the Internet to organically integrate teaching modes such as flipped classroom, which can stimulate students’ learning interest, cultivate students’ thinking mode of traditional Chinese medicine and clinical problem-solving ability, and realize the common development …of students’ ability and quality of traditional Chinese medicine. While improving the teaching effect of internal medicine of traditional Chinese medicine, this diversified teaching method will provide new ideas and methods for deepening the reform of traditional Chinese medicine teaching and lead the teaching of traditional Chinese medicine to a new level. The teaching quality evaluation of Chinese medicine specialty in higher vocational colleges is classical multiple-attribute group decision-making (MAGDM) issues. Recently, the TODIM and VIKOR method has been used to solve MAGDM issues. The probabilistic uncertain linguistic term sets (PULTSs) are used as a tool for characterizing uncertain information during the teaching quality evaluation of Chinese medicine specialty in higher vocational colleges. In this manuscript, we design the TODIM-VIKOR model to solve the MAGDM under PULTSs. In the end, a numerical case study for teaching quality evaluation of Chinese medicine specialty in higher vocational colleges is given to validate the proposed method. Show more

Keywords: Multiple-attribute group decision-making (MAGDM), probabilistic uncertain linguistic term sets (PULTSs), TODIM, VIKOR, teaching quality evaluation

DOI: 10.3233/JIFS-230760

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10101-10112, 2023

Authors: Arul King, J. | Helen Sulochana, C.

Article Type: Research Article

Abstract: Lung cancer is a severe disease that may lead to death if left undiagnosed and untreated. Lung cancer recognition and segmentation is a difficult task in medical image processing. The study of Computed Tomography (CT) is an important phase for detecting abnormal tissues in the lung. The size of a nodule as well as the fine details of nodule can be varied for various images. Radiologists face a difficult task in diagnosing nodules from multiple images. Deep learning approaches outperform traditional learning algorithms when the data amount is large. One of the most common deep learning architectures is convolutional neural …networks. Convolutional Neural Networks use pre-trained models like LeNet, AlexNet, GoogleNet, VGG16, VGG19, Resnet50, and others for learning features. This study proposes an optimized HDCCARUNet (Hybrid Dilated Convolutional Channel Attention Res-UNet) architecture, which combines an improved U-Net with a modified channel attention (MCA) block, and a HDAC (hybrid dilated attention convolutional) layer to accurately and effectively do medical image segmentation for various tasks. The attention mechanism aids in focusing on the desired outcome. The ability to dynamically allot input weights to neurons allows it to focus only on the most important information. In order to gather key details about different object features and infer a finer channel-wise attention, the proposed system uses a modified channel attention (MCA) block. The experiment is conducted on LIDC-IDRI dataset. The noises present in the dataset images are denoised by enhanced DWT filter and the performance is analysed at various noise levels. The proposed method achieves an accuracy rate of 99.58 % . Performance measures like accuracy, sensitivity, specificity, and ROC curves are evaluated and the system significantly outperforms other state-of-the-art systems. Show more

Keywords: Lung, segmentation, CNN, hybrid, UNet

DOI: 10.3233/JIFS-222215

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10113-10129, 2023

Authors: Zhou, Wei | Wang, Degang | Li, Hongxing | Bao, Menghong

Article Type: Research Article

Abstract: The aim of this study is to improve randomized methods for designing a Takagi-Sugeno-Kang (TSK) fuzzy system. A novel adaptive incremental TSK fuzzy system based on stochastic configuration, named stochastic configuration fuzzy system (SCFS), is proposed in this paper. The proposed SCFS determines the appropriate number of fuzzy rules in TSK fuzzy system by incremental learning approach. From the initial system, new fuzzy rules are added incrementally to improve the system performance until the specified performance is achieved. In the process of generation of fuzzy rules, the stochastic configuration supervision mechanism is applied to ensure that the addition of fuzzy …rules can continuously improve the performance. The premise parameters of new adding fuzzy rules are randomly assigned adaptively under the supervisory mechanism, and the consequent parameters are evaluated by Moore-Penrose generalized inverse. It has been proved theoretically that the supervisory mechanism can help to ensure the universal approximation of SCFS. The proposed SCFS can reach any predetermined tolerance level when there are enough fuzzy rules, and the training process is finite. A series of synthetic data and benchmark datasets are used to verify SCFS’s performance. According to the experimental results, SCFS achieves satisfactory prediction accuracy compared to other models. Show more

Keywords: Stochastic configuration, fuzzy system, universal approximation, incremental learning

DOI: 10.3233/JIFS-222930

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10131-10143, 2023

Authors: Wu, Haowen | Rao, Fengshuo

Article Type: Research Article

Abstract: Teaching quality is the foundation and lifeline of colleges and universities. To establish a distinctive university, we must adhere to the scientific concept of development, deepen teaching reform and improve teaching quality. The classroom teaching quality (CTQ) evaluation of college physical education (PE) is an essential part of the teaching process. Building a scientific, comprehensive, reasonable and effective evaluation system is crucial to improve the quality of college PE classroom teaching. This process is not easy and needs long-term efforts and persistence. The CTQ evaluation of college volleyball training is viewed as the multi-attribute decision-making (MADM). In this paper, we …connect the geometric Heronian mean (GHM) operator and power geometric (PG) operator with 2-tuple linguistic neutrosophic sets (2TLNSs) to build the generalized 2-tuple linguistic neutrosophic numbers weighted power GHM (G2TLNWPGHM) operator. Then, the G2TLNWPGHM operator is used to tackle MADM with 2TLNSs. Finally, an example for CTQ evaluation of college volleyball training is used to show the proposed methods. Show more

Keywords: Multiple attribute decision making (MADM), neutrosophic numbers, 2-tuple linguistic neutrosophic sets (2TLNSs), G2TLNWPGHM operator, CTQ evaluation

DOI: 10.3233/JIFS-223830

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10145-10158, 2023

Authors: Razzaq, Ayesha | Riaz, Muhammad

Article Type: Research Article

Abstract: Picture fuzzy sets (PFSs), the generalization of intuitionistic fuzzy sets (IFSs), are more capable of dealing with vague data in real-life problems. Models based on PFSs may be suitable particularly in those circumstances where human perceptions become challenging as well as various kinds of reasoning, like yes, no, abstention, or denial. The aggregation operators (AOs) are essential components in information aggregation as they have the ability to aggregate a group of fuzzy numbers into a single fuzzy number of the same kind. A lot of aggregation operations for PFSs have been developed. Nevertheless, the existing aggregation operators for picture fuzzy …information are inaccurate as they fail to aggregate a group of picture fuzzy numbers into a single picture fuzzy number (PFN). To cover the drawbacks of existing AOs, we developed some modified picture fuzzy aggregation operators (PFAOs) named as picture fuzzy modified weighted averaging (PFMWA), picture fuzzy modified ordered weighted averaging (PFMOWA) and picture fuzzy modified hybrid averaging (PFMHA) aggregation operator along with their distinctive features. These operators are essential in developing new multi-criteria decision-making (MCDM) techniques. This paper defines a number of stakeholder roles (or tactics), with an objective of overcoming the challenges to executing Education 4.0 (EDUC4) that have recently been highlighted in the literature. A MCDM problem provides the basis for the evaluation of the responsibilities of the stakeholders with respect to these constraints. Several management concerns are provided as stepping stones for the development of EDUC4 implementation. The purpose of this study is to identify the qualities that influence the degree of optimism for the adoption and implementation of the EDUC4 in Pakistan’s education system while taking government policies into account. Show more

Keywords: Picture fuzzy information, accuracy function, score function, PFMWA operator, PFMOWA operator, PFMHA operator, MCDM

DOI: 10.3233/JIFS-224600

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10159-10181, 2023

Authors: Nguyen-Trong, Khanh | Trinh, Thinh

Article Type: Research Article

Abstract: Visually rich documents, such as forms, invoices, receipts, and ID cards, are ubiquitous in daily business and life. Various methods have been used to convey such diverse information, including text, layout, font size, or text position. Combining these elements in information extraction can improve the result performance. However, previous works have not effectively utilized the cooperation between these rich information sources. Text detection and recognition have been performed without semantic supervision (e.g., entity name annotation), and text information extraction has been performed using only serialized plain text, ignoring rich visual information. This paper presents a method for extracting information from …such documents, which integrates textual, non-spatial, and spatial visual features. The method consists of two main steps and uses three deep neural networks. The first step, Text Reading, employs two CNN models (Lightweight DB and C-PREN) for OCR tasks, based on the state-of-the-art models DB and PREN, with two improvements. These improvements include reducing noise by removing the SE block of DB and integrating both context and position features in PREN. The second step, Text Information Extraction, uses a graph convolutional network, RGCN, for name entity recognition. Experiments on self-collected and two public datasets have demonstrated that our method improves the performance of the original models and outperforms other state-of-the-art methods. Show more

Keywords: Graph Convolutional Network, OCR, Text detection, text recognition, NER

DOI: 10.3233/JIFS-230204

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10183-10195, 2023

Authors: Teimoury, Ebrahim | Rashid, Reza

Article Type: Research Article

Abstract: In recent years, e-commerce has become increasingly popular, and consumers expect quick and affordable delivery, placing additional pressure on city logistics activities. An innovative approach is proposed to coordinate ground vehicles and drones for delivery services, which has gained tremendous attention from academia and logistic service providers. This paper introduces a variant of this problem: the two-echelon truck and drone routing problem, characterized by stochastic demand existence and soft time windows. A Markov chain is used to model the problem, and a linear mathematical model is presented. This work employs a hybrid large-neighborhood search approach. Numerous computational experiments are conducted …to evaluate the performance of the proposed solution method, and the results demonstrate its efficacy. Show more

Keywords: Last-mile delivery, truck and drone routing, stochastic optimization, Markov chain, large-neighborhood search

DOI: 10.3233/JIFS-224307

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10197-10211, 2023

Authors: Cao, Guo | Shen, Lixiang

Article Type: Research Article

Abstract: As an extension of picture fuzzy sets (PFSs), interval-valued picture fuzzy sets (IVPFSs) can better model and handle incomplete, indeterminate and inconsistent information in some practical applications. One of the important topics in IVPFSs is the similarity measure of IVPFSs, for which few studies have been proposed within the literature. Moreover, some existing similarity measures cannot adequately meet the conditions of similarity measure with some counterintuitive cases. In this work, we devise a novel similarity measure between IVPFSs based on the effect of the margin of the degree of refusal membership. First, the interval-valued picture fuzzy numbers will be transformed …into two right-angled triangular-based pyramids in a spatial rectangular coordinate system. Then, a new parameter distance measure for IVPFSs is defined to assess the similarity between IVPFNs according to the centers of gravity of their corresponding right-angled triangular-based pyramids. Meanwhile, a comparison between different similarity measures is performed to illustrate that the proposed similarity measure can overcome the deficiencies of other extant measures. Finally, we apply it to handle pattern recognition problems. The comparison results indicate that the proposed algorithm can adequately meet the conditions of similarity measure, produce more reasonable and creditable results and perform well in complex contexts. Show more

Keywords: Interval-valued picture fuzzy sets (IVPFSs), distance measure, similarity measure, pattern recognition

DOI: 10.3233/JIFS-224314

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10213-10239, 2023

Authors: Khan, Madad | Anis, Saima | Ahmad, Sarfraz | Zeeshan, Muhammad

Article Type: Research Article

Abstract: A fuzzy soft matrix is a type of mathematical matrix that combines the principles of fuzzy set theory and soft set theory. It is used to handle uncertainty and vagueness in decision-making problems. Fuzzy soft matrix theory cannot handle negative information. To overcome this difficulty, we define the notion of bipolar fuzzy soft (BFS) matrices and study their fundamental properties. We define products of BFS matrices and investigate some useful properties and results. We also give an application of bipolar fuzzy soft matrices to decision-making problems. We propose a decision-making algorithm based on computer programs under the environment of the …bipolar fuzzy soft sets. Show more

Keywords: Soft sets, fuzzy soft matrices, bipolar fuzzy soft matrices, BFS decision-makings

DOI: 10.3233/JIFS-221569

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10241-10253, 2023

Authors: Fernandes, Anita Maria da Rocha | Cassaniga, Mateus Junior | Passos, Bianka Tallita | Comunello, Eros | Stefenon, Stefano Frizzo | Leithardt, Valderi Reis Quietinho

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-223218

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10255-10274, 2023

Authors: Mudgil, Pooja | Gupta, Pooja | Mathur, Iti | Joshi, Nisheeth

Article Type: Research Article

Abstract: Social media platforms, namely Instagram, Facebook, Twitter, YouTube, etc. have gained a lot of attention as users used to share their views, and post videos, audio, and pictures for social networking. In near future, understanding the meaning and analyzing this enormously rising volume and size of online data will become a necessity in order to extract valuable information from them. In a similar context, the paper proposes an analysis model in two phases namely the training and the sentiment classification using the reward-based grasshopper optimization algorithm. The training architecture and context analysis of the tweet are presented for the sentiment …analysis along with the ground truth processing of emotions. The proposed algorithm is divided into two phases namely the exploitation and the exploration part and creates a reward mechanism that utilizes both phases. The proposed algorithm also uses cosine similarity, dice coefficient, and euclidean distance as the input set and further processes using the grasshopper algorithm. Finally, it presents a combination of swarm intelligence and machine learning for attribute selection in which the reward mechanism is further validated using machine learning techniques. The comparative performance in terms of precision, recall, and F-measure has been measured for the proposed model in comparison to existing swarm-based sentiment analysis works. Overall, simulation analysis showed that the proposed work based on grasshopper optimization outperformed the existing approaches for Sentiment 140 by 5.93% to 10.05% SemEval 2013 by 6.15% to 12.61% and COVID-19 tweets by 2.72% to 9.13%. Thus, demonstrating the efficiency of the context-aware sentiment analysis using the grasshopper optimization approach. Show more

Keywords: Grasshopper optimization, sentiment, social media, swarm intelligence, Twitter

DOI: 10.3233/JIFS-221879

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10275-10295, 2023

Authors: Zhi, Zhaodan | Tao, Juan

Article Type: Research Article

Abstract: In this study, the constrained interval arithmetic (CIA) is used as an effective mathematical tool for solving the stability analysis for interval two-dimensional semi-linear differential equations. Under certain assumptions, the origin is a focus of the interval semi-linear differential equations if it is a focus of the interval linear ones. Meanwhile, the origin can be a center, a center-focus or a focus of interval semi-linear differential equations if it is a center of the interval linear ones. On the other word, the types of equilibrium point are still determined by the linear part when a nonlinear disturbance is added to …the interval linear differential equations. Based on CIA, the stability results of interval differential equations are the same as those of the real differential equations. At last, three illustrative examples validate the stability results of the origin for interval two-dimensional semi-linear differential equations. Show more

Keywords: Constrained interval arithmetic (CIA), interval differential equations, semi-linear, stability

DOI: 10.3233/JIFS-222020

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10297-10310, 2023

Authors: Korkoman, Malak Jalwi | Abdullah, Monir

Article Type: Research Article

Abstract: Online services have advanced to the point where they have made our lives much easier, but many problems should be solved to make these services safer for consumers. Numerous transactions are conducted daily, and much personal information is published and shared on e-commerce and social media platforms. This makes security, privacy, and problematic reliability barriers to overcome. One of these problems is detecting credit card fraud because thieves aim to make all transactions legitimate by stealing credit card information. Imbalanced data is a potential problem in machine learning that impairs the performance of the classifiers used in real-world systems. For …example, anomaly detection and fraudulent transactions. The term “data imbalance” refers to the problem in which the sample distribution is skewed or skewed towards a particular class. Due to its inherent nature, the software failure prediction dataset falls into the same category as non-defective software modules. The main objective of this paper is to solve the problem of the imbalanced fraud credit card dataset for enhancing the detection accuracy of using machine learning algorithms. This paper provides a unique fraud detection model using the Particle Swarm Optimization (PSO) based on oversampling technique of the minority class to solve the imbalanced dataset problem compared with the Genetic Algorithm (GA) technique. Random Forest (RF) algorithm shows up with sensitivity, specificity, and accuracy. The experimental results achieved 99.3% and 99.4% for GA and PSO within seconds, respectively. Experiments show that the proposed methods outperform other methods, evidenced by the higher classification accuracy obtained. Show more

Keywords: Fraud detection, genetic algorithm, particle swarm optimization, oversampling, random forest

DOI: 10.3233/JIFS-222344

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10311-10323, 2023

Authors: Wang, Chunying | Zhang, Jiahui | Yang, Qi

Article Type: Research Article

Abstract: The traditional fuzzy C-means clustering technology only considers one performance Angle of image segmentation process when processing data, resulting in low accuracy of image segmentation. In this paper, the traditional FCM algorithm is analyzed, and the low clustering accuracy, noise interference and lack of flexibility and other problems are fully considered from the relationship between parameter components, non-local spatial information elements and noise sensitivity. Firstly, a distance calculation method based on robust statistics theory is proposed, which can deal with abnormal noise stably. Secondly, based on the extreme learning machine theory, the non-local spatial information coefficient is introduced to improve …the identification ability of the influence factors. This method not only guarantees the anti-noise performance of the algorithm, but also preserves the image data, improving the iteration efficiency and segmentation accuracy of the algorithm. The test results show that the accuracy of the improved C-means clustering algorithm for image segmentation is 95.5%, which is compared with the traditional C-means clustering technique and other optimization algorithms. Show more

Keywords: C-means, noise, clustering, image processing, fuzzy

DOI: 10.3233/JIFS-222912

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10325-10335, 2023

Authors: Wang, Weize | Feng, Yurui

Article Type: Research Article

Abstract:  There are various uncertainties in the multi-criteria group decision making (MCGDM) process, including the definition of the importance of decision information and the assignment of criterion assessment values, etc., which cause decision makers to be unconfident in their decisions. In this paper, an MCGDM approach based on the reliability of decision information is proposed in Fermatean fuzzy (FF) environment, allowing a decision to be made with confidence that the alternative chosen is the best performing alternative under the range of probable circumstances. First, we prove that the FF Yager weighted averaging operator is monotone with respect to the total order …and note the inconsistency between the monotonicity of some FF aggregation operators and their application in MCGDM. Second, we extend the divergence measure of FFS to order σ for calculating the variance of decision information and accordingly develop an exponential FF entropy measure to measure the uncertainty of decision information. Then, the reliability of decision information is defined, which accounts for the degree of variance of decision information across criteria from the criterion dimension and the uncertainty of the decision information from the alternative dimension. Following that, an integrated MCGDM framework is completed. Finally, the applications to a numerical example and comparisons with previous approaches are conducted to illustrate the validity of the established approach. Show more

Keywords: Multi-criteria group decision making, Fermatean fuzzy set, Divergence measure, Entropy measure, Supplier selection

DOI: 10.3233/JIFS-223014

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10337-10356, 2023

Authors: Upendra Raju, K. | Amutha Prabha, N.

Article Type: Research Article

Abstract: Reversible data hiding (RDH) based on Steganography is considered as one of the future related aspects in the field of security for the information hiding paradigm. Existing research work has been carried out based on secure data transmission as well as reducing the dataloss from one user to other users. But due to encryption data expansion over non-linear transformation, complexity in attacking caused due to keyspace, ineffective image compression, poor embedding ratio, poor quality, overflow/underflow problems, data loss etc., leads to inefficient data transmission causing a security risk. This paper proposes a novel method named Triple Secured Data Hiding Steganography …Model which provides solutions to the above challenges. This work is initiated with Hyper Chaos 2D Compressive Sensing that performs image compression and encryption simultaneously. It provides control over low dimension chaos system bearing secure risks with suffering from data encrypted expansion while adopt non-linear transformation. In addition to reduce the error rate and providing signal synchronization as well as system reliability over the transmission channel, Manchester Encoder/Decoder is initiated. To cope up with data embedding and extraction our work has proposed Circular Queue Exploiting Modification Direction(CQEMD). Thus, overall proposed model enhances effective secure data transmission under RDH by inhabiting a triple secured system. Show more

Keywords: Circular Queue Exploiting Modification Direction (CQEMD), Hyper Chaos 2D Compressive Sensing (CS), ManchesterEncoder/Decoder, Reversible Data Hiding (RDH), steganography

DOI: 10.3233/JIFS-223131

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10357-10367, 2023

Authors: Cabrera-Ponce, Aldrich A. | Martin-Ortiz, Manuel | Martinez-Carranza, Jose

Article Type: Research Article

Abstract:  Geo-localisation from a single aerial image for Uncrewed Aerial Vehicles (UAVs) is an alternative to other vision-based methods, such as visual Simultaneous Localisation and Mapping (SLAM), seeking robustness under GPS failure. Due to the success of deep learning and the fact that UAVs can carry a low-cost camera, we can train a Convolutional Neural Network (CNN) to predict position from a single aerial image. However, conventional CNN-based methods adapted to this problem require off-board training that involves high computational processing time and where the model can not be used in the same flight mission. In this work, we explore the …use of continual learning via latent replay to achieve online training with a CNN model that learns during the flight mission GPS coordinates associated with single aerial images. Thus, the learning process repeats the old data with the new ones using fewer images. Furthermore, inspired by the sub-mapping concept in visual SLAM, we propose a multi-model approach to assess the advantages of using compact models learned continuously with promising results. On average, our method achieved a processing speed of 150 fps with an accuracy of 0.71 to 0.85, demonstrating the effectiveness of our methodology for geo-localisation applications. Show more

Keywords: Continual learning, geo-localisation, aerial image, GPS

DOI: 10.3233/JIFS-223627

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10369-10381, 2023

Authors: Westarb, Gustavo | Stefenon, Stefano Frizzo | Hoppe, Aurélio Faustino | Sartori, Andreza | Klaar, Anne Carolina Rodrigues | Leithardt, Valderi Reis Quietinho

Article Type: Research Article

Abstract:  This paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.

Keywords: Drug interaction, graph neural network, communities detection

DOI: 10.3233/JIFS-223656

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10383-10395, 2023

Authors: Li, Dan | Gao, Fei

Article Type: Research Article

Abstract: Slime mould algorithm (SMA) is a novel meta-heuristic algorithm with fast convergence speed and high convergence accuracy. However, it still has some drawbacks to be improved. The exploration and exploitation of SMA is difficult to balance, and it easy to fall into local optimum in the late iteration. Aiming at the problems existing in SMA, a multistrategy slime mould algorithm named GCSMA is proposed for global optimization in this paper. First, the Logistic-Tent double chaotic map approach is introduced to improve the quality of the initial population. Second, a dynamic probability threshold based on Gompertz curve is designed to balance …exploration and exploitation. Finally, the Cauchy mutation operator based on elite individuals is employed to enhance the global search ability, and avoid it falling into the local optimum. 12 benchmark function experiments show that GCSMA has superior performance in continuous optimization. Compared with the original SMA and other novel algorithms, the proposed GCSMA has better convergence accuracy and faster convergence speed. Then, a special encoding and decoding method is used to apply GCSMA to discrete flexible job-shop scheduling problem (FJSP). The simulation experiment is verified that GCSMA can be effectively applied to FJSP, and the optimization results are satisfactory. Show more

Keywords: Slime mould algorithm, double chaotic map, Gompertz dynamic probability, Cauchy mutation, flexible job shop scheduling problem

DOI: 10.3233/JIFS-223827

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10397-10415, 2023

Authors: Shan, Chuanhui | Ou, Jun | Chen, Xiumei

Article Type: Research Article

Abstract: As one of the main methods of information fusion, artificial intelligence class fusion algorithm not only inherits the powerful skills of artificial intelligence, but also inherits many advantages of information fusion. Similarly, as an important sub-field of artificial intelligence class fusion algorithm, deep learning class fusion algorithm also inherits advantages of deep learning and information fusion. Hence, deep learning fusion algorithm has become one of the research hotspots of many scholars. To solve the problem that the existing neural networks are input into multiple channels as a whole and cannot fully learn information of multichannel images, Shan et al. proposed …multichannel concat-fusional convolutional neural networks. To mine more multichannel images’ information and further explore the performance of different fusion types, the paper proposes new fusional neural networks called multichannel cross-fusion convolutional neural networks (McCfCNNs) with fusion types of “R+G+B/R+G+B/R+G+B” and “R+G/G+B/B+R” based on the tremendous strengths of information fusion. Experiments show that McCfCNNs obtain 0.07-6.09% relative performance improvement in comparison with their corresponding non-fusion convolutional neural networks (CNNs) on diverse datasets (such as CIFAR100, SVHN, CALTECH256, and IMAGENET) under a certain computational complexity. Hence, McCfCNNs with fusion types of “R+G+B/R+G+B/R+G+B” and “R+G/G+B/B+R” can learn more fully multichannel images’ information, which provide a method and idea for processing multichannel information fusion, for example, remote sensing satellite images. Show more

Keywords: Information fusion, fusion type “R+G+B/R+G+B/R+G+B”, fusion type “R+G/G+B/B+R”, CNN, McCfCNN

DOI: 10.3233/JIFS-224076

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10417-10436, 2023