Journal of Intelligent & Fuzzy Systems - Volume 46, issue 4

Authors: Zhao, Xiaoqing | Xu, Miaomiao | Li, Yanbing | Huang, Hao | Silamu, Wushour

Article Type: Research Article

Abstract:  This research focuses on Scene Text Recognition (STR), a crucial component in various applications of artificial intelligence such as image retrieval, office automation, and intelligent traffic systems. Recent studies have shown that semantic-aware approaches significantly improve the performance of STR tasks, with context-aware STR methods becoming mainstream. Among these, the fusion of visual and language models has shown remarkable effectiveness. We propose a novel method (PABINet) that incorporates three key components: a Visual-Language Decoder, a Language Model, and a Fusion Model. First, during training, the Visual-Language Decoder masks the original labels in the Transformer decoder using permutation masks, with each …mask being unique. This enhances word memorization and learning through contextual semantic information, resulting in robust semantic knowledge. During the inference stage, the Visual-Language Decoder employs autonomous Autoregressive model (AR) inference to generate results. Subsequently, the Language Model scrutinizes and corrects the output of the Visual-Language Encoder using a cloze mask approach, achieving context-aware, autonomous, bidirectional inference. Finally, the Fusion Model concatenates and refines the outputs of both models through iterative layers.Experimental results demonstrate that our PABINet performs exceptionally well when handling various quality images. When trained with synthetic data, PABINet achieves a new STR benchmark (average accuracy of 92.41%), and when trained with real data, it establishes new state-of-the-art results (average accuracy of 96.28%). Show more

Keywords: Scene text recognition, language model, visual-language decoder

DOI: 10.3233/JIFS-237135

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8605-8616, 2024

Authors: Arunagirinathan, Sumithara | Subramanian, Chitra

Article Type: Research Article

Abstract: This paper presents a hybrid approach for optimizing the maximum power point tracking of photovoltaic (PV) systems in electric vehicles. The hybrid technique involves the simultaneous utilization of the Gannet Optimization Algorithm (GOA) and Quantum Neural Network (QNN), collectively referred to as the GOA-QNN technique. The primary aim is to enhance the efficiency and maximize the power output of PV systems. The proposed hybrid methodology boosts the performance of the photovoltaic system by managing the power interface. A high step-up DC/DC converter is employed to adjust the photovoltaic source power and load, ensuring optimal power transfer under various operating conditions. …The proposed method optimally determines the duty cycle of the converter. Subsequently, the model is implemented in the MATLAB/Simulink platform, and its execution is evaluated using established procedures. The results clearly demonstrate the superiority of the proposed method over existing approaches in terms of power quality, settling time, and controller stability. The proposed technique achieves an impressive efficiency level of 95%, exceeding the efficiency of other existing techniques. Show more

Keywords: MPPT, Photovoltaic, high-gain converter, Gannet Optimization Algorithm, Quantum Neural Network, EV

DOI: 10.3233/JIFS-237734

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8617-8637, 2024

Authors: Karthika, K. | Rangasamy, Devi Priya

Article Type: Research Article

Abstract: In today’s digital era, the security of sensitive data such as Aadhaar data is of utmost importance. To ensure the privacy and integrity of this data, a conceptual framework is proposed that employs the Diffie-Hellman key exchange protocol and Hash-based Message Authentication Code (HMAC) to enhance the security. The proposed system begins with the preprocessing phase, which includes removing noise, standardizing formats and validating the integrity of the data. Next, the data is segmented into appropriate sections to enable efficient storage and retrieval in the cloud. Each segment is further processed to extract meaningful features, ensuring that the relevant information …is preserved while reducing the risk of unauthorized access. For safeguarding the stored Aadhaar data, the system employs the Diffie-Hellman key exchange protocol which allows the data owner and the cloud service provider to establish a shared secret key without exposing it to potential attackers. Additionally, HMAC is implemented to verify the identity of users during the login process. HMAC enhances security by leveraging cryptographic hash functions and a shared secret key to produce a distinct code for each login attempt. This mechanism effectively protects the confidentiality and integrity of stored data. The combination of Diffie-Hellman key exchange and HMAC authentication provides a robust security framework for Aadhaar data. It ensures that the data remains encrypted and inaccessible without the secret key, while also verifying the identity of users during the login process. This comprehensive approach helps preventing unauthorized access thereby protecting against potential attacks, instilling trust and confidence in the security of Aadhaar data stored in the cloud. Results of the article depict that the proposed scheme achieve 0.19 s of encryption time and 0.05 s of decryption time. Show more

Keywords: Hash based message authentication code (HMAC), cryptographic hash functions, Diffie Hellman, communications

DOI: 10.3233/JIFS-234641

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8639-8658, 2024

Authors: Wu, Chengding | Xu, Zhaoping | Liu, Liang | Yang, Tao

Article Type: Research Article

Abstract: There are limitations of personalization in Advanced Driver Assistance Systems (ADAS) that have a serious impact on driver acceptance and satisfaction. This study investigates driving style recognition method to achieve personalization of longitudinal driving behavior. Currently, driving style recognition algorithms for Personalized Adaptive Cruise Control (PACC) rely on integrated recognition. However, disturbances in the driving cycle may lead to changes in a driver’s integrated driving style. Therefore, the integrated driving style cannot accurately and comprehensively reflect the driver’s driving style. To solve this problem, a new driving style recognition method for PACC is proposed, which considers integrated driving style and …driving cycle. Firstly, the method calculates the constructed feature parameters of driving cycle and style, and then reduces the dimensionality of the feature parameter matrix by principal component analysis (PCA). Secondly, a two-stage clustering algorithm with self-organizing mapping networks and K-means clustering (SOM-K-means) is used to obtain the type labels. Then, a transient recognition model based on random forest (RF) is established and the hyperparameters of this model are optimized by sparrow search algorithm (SSA). Based on this, a comprehensive driving style recognition model is established using analytic hierarchy process (AHP). Finally, the validity of the proposed method is verified by a natural dataset. The method incorporates the driving cycle into driving style recognition and provides guidance for improving the personalization of adaptive cruise control system. Show more

Keywords: Personalized adaptive cruise control, SOM-K-means two-stage clustering, random forest (RF), sparrow search algorithm (SSA), driving style recognition

DOI: 10.3233/JIFS-235045

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8659-8675, 2024

Authors: Wan, Huanyu | Qiu, Dong

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-237319

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8677-8695, 2024

Authors: Wang, Jinxin | Wu, Zhanwen | Yang, Longzhi | Hu, Wei | Song, Chaojun | Zhu, Zhaolong | Guo, Xiaolei | Cao, Pingxiang

Article Type: Research Article

Abstract:  Distributed flexible flowshop scheduling is getting more important in the large-scale panel furniture industry. It is vital for a higher manufacturing efficiency and economic profit. The distributed scheduling problem with lot-streaming in a flexible flow shop environment is investigated in this work. Furthermore, the actual constraints of packaging collaborative and machine setup times are considered in the proposed approach. The average order waiting time for packaging and average order delay rate is used as objectives. Non-dominated sorting method is used to handle this bi-objective optimization problem. An improved encoding method was proposed to address the large-scale orders that need to …be divided into sub-lots based on genetic algorithm. The proposed approach is firstly validated by benchmark with other multi-objectives evolutionary algorithms. The results found that the proposed approach had a good convergence and diversity. Besides, the influence of the proportion of large-scale orders priority level and sub-lot size was investigated in a panel furniture manufacturing scenario. The results can be concluded that the enterprise could obtain shorter order average waiting time and delay rate when the sub-lot sizes were set as two and the order priority level was allocated in the proportion of 1:2:3:4:5. Show more

Keywords: Distributed flexible flow shop scheduling, Panel furniture manufacturing, Lot-streaming, Packaging collaborative, Setup time

DOI: 10.3233/JIFS-237378

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8697-8707, 2024

Authors: Qin, Xiwen | Zhang, Siqi | Dong, Xiaogang | Shi, Hongyu | Yuan, Liping

Article Type: Research Article

Abstract: The research of biomedical data is crucial for disease diagnosis, health management, and medicine development. However, biomedical data are usually characterized by high dimensionality and class imbalance, which increase computational cost and affect the classification performance of minority class, making accurate classification difficult. In this paper, we propose a biomedical data classification method based on feature selection and data resampling. First, use the minimal-redundancy maximal-relevance (mRMR) method to select biomedical data features, reduce the feature dimension, reduce the computational cost, and improve the generalization ability; then, a new SMOTE oversampling method (Spectral-SMOTE) is proposed, which solves the noise sensitivity problem …of SMOTE by an improved spectral clustering method; finally, the marine predators algorithm is improved using piecewise linear chaotic maps and random opposition-based learning strategy to improve the algorithm’s optimization seeking ability and convergence speed, and the key parameters of the spectral-SMOTE are optimized using the improved marine predators algorithm, which effectively improves the performance of the over-sampling approach. In this paper, five real biomedical datasets are selected to test and evaluate the proposed method using four classifiers, and three evaluation metrics are used to compare with seven data resampling methods. The experimental results show that the method effectively improves the classification performance of biomedical data. Statistical test results also show that the proposed PRMPA-Spectral-SMOTE method outperforms other data resampling methods. Show more

Keywords: Biomedical data, mRMR, spectral clustering, SMOTE, marine predators algorithm

DOI: 10.3233/JIFS-237538

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8709-8728, 2024

Authors: Ren, Shujun | Wang, Yuanhong

Article Type: Research Article

Abstract: Image segmentation is critical in medical image processing for lesion detection, localisation, and subsequent diagnosis. Currently, computer-aided diagnosis (CAD) has played a significant role in improving diagnostic efficiency and accuracy. The segmentation task is made more difficult by the hazy lesion boundaries and uneven forms. Because standard convolutional neural networks (CNNs) are incapable of capturing global contextual information, adequate segmentation results are impossible to achieve. We propose a multiscale feature fusion network (MTC-Net) in this paper that integrates deep separable convolution and self-attentive modules in the encoder to achieve better local continuity of images and feature maps. In the decoder, …a multi-branch multi-scale feature fusion module (MSFB) is utilized to improve the network’s feature extraction capability, and it is integrated with a global cooperative aggregation module (GCAM) to learn more contextual information and adaptively fuse multi-scale features. To develop rich hierarchical representations of irregular forms, the suggested detail enhancement module (DEM) adaptively integrates local characteristics with their global dependencies. To validate the effectiveness of the proposed network, we conducted extensive experiments, evaluated on the public datasets of skin, breast, thyroid and gastrointestinal tract with ISIC2018, BUSI, TN3K and Kvasir-SEG. The comparison with the latest methods also verifies the superiority of our proposed MTC-Net in terms of accuracy. Our code on https://github.com/gih23/MTC-Net. Show more

Keywords: Medical image segmentation, multi-scale features, detail enhancement, feature fusion, deep learning

DOI: 10.3233/JIFS-237963

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8729-8740, 2024

Authors: Yue, Lizhu | Wang, Qian

Article Type: Research Article

Abstract: With the rapid development of big data and continuous optimization of online shopping platforms, personalized recommendation has become a standard feature of recommendation methods. In order to effectively provide personalized recommendations to customers, improve recommendation accuracy, and customer satisfaction, it is necessary to consider customers’ preferences for multiple product attributes when making product recommendations. However, existing recommendation methods require precise calculation of product attribute weights, which is computationally expensive, complex, and often results in unstable weight values. This paper proposes a multi-attribute recommendation method based on consumer decision preference information that overcomes the need for weights and reflects personalized customer …preferences. Based on the acquisition of customer product attribute preference sequences, a partial order relation for recommended products is constructed using partial order set theory. Finally, the recommended products are determined through the partial order Hasse diagram, where the top layer elements of the Hasse diagram represent the recommended product set. This method addresses challenges that traditional content-based recommendations cannot overcome. The experiment in this paper uses a dataset of 30,000 records from Beeradvocate beer reviews. The experimental results show that, compared to traditional multi-attribute recommendation methods, this method only requires decision-maker preference information to complete product recommendations, requiring less information and having lower computational costs, resulting in more robust results. Show more

Keywords: Multi-attribute recommendation, partial order set, decision preference, hasse diagram, personalization

DOI: 10.3233/JIFS-231724

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8741-8754, 2024

Authors: Badshah, Noor | Begum, Nasra | Rada, Lavdie | Ashfaq, Muniba | Atta, Hadia

Article Type: Research Article

Abstract: Joint segmentation and registration of images is a focused area of research nowadays. Jointly segmenting and registering noisy images and images having weak boundaries/intensity inhomogeneity is a challenging task. In medical image processing, joint segmentation and registration are essential methods that aid in distinguishing structures and aligning images for precise diagnosis and therapy. However, these methods encounter challenges, such as computational complexity and sensitivity to variations in image quality, which may reduce their effectiveness in real-world applications. Another major issue is still attaining effective joint segmentation and registration in the presence of artifacts or anatomical deformations. In this paper, a …new nonparametric joint model is proposed for the segmentation and registration of multi-modality images having weak boundaries/noise. For segmentation purposes, the model will be utilizing local binary fitting data term and for registration, it is utilizing conditional mutual information. For regularization of the model, we are using linear curvature. The new proposed model is more efficient to segmenting and registering multi-modality images having intensity inhomogeneity, noise and/or weak boundaries. The proposed model is also tested on the images obtained from the freely available CHOAS dataset and compare the results of the proposed model with the other existing models using statistical measures such as the Jaccard similarity index, relative reduction, Dice similarity coefficient and Hausdorff distance. It can be seen that the proposed model outperforms the other existing models in terms of quantitatively and qualitatively. Show more

Keywords: Image segmentation, , , , , image registration, linear curvature (LC), conditional mutual information (CMI), Jaccard similarity index (JSI)

DOI: 10.3233/JIFS-233306

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 8755-8770, 2024