Journal of Intelligent & Fuzzy Systems - Volume 45, issue 5

Authors: Wang, Tianxing | Wang, Wenjue | Huang, Bing | Li, Huaxiong

Article Type: Research Article

Abstract: Rule acquisition is significant in real life and extensively utilized in data mining. Currently, most studies have constructed rule acquisition algorithms based on the equivalence relation. However, these algorithms need to be more suitable for dominance-based decision systems and should consider applications in multi-scale environments. In this paper, we establish the dominance relation of the single-valued neutrosophic rough set model using the ranking method with the relative distance favorable degree. We then introduce this approach into a multi-scale environment to obtain the dominance relation of the multi-scale single-valued neutrosophic rough set model, resulting in two discernibility matrices and functions. We …propose the algorithm for lower approximation optimal scale reduction and further examine the method of rule acquisition based on the discernibility matrix. Finally, we apply these algorithms to four random data sets to verify their effectiveness. Show more

Keywords: Multi-scale, single-valued neutrosophic rough sets, rule acquisition, optimal scale reduction, dominance relation

DOI: 10.3233/JIFS-232849

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7353-7367, 2023

Authors: Ji, Mengting | Liu, Yongli | Chao, Hao

Article Type: Research Article

Abstract: Nowadays, multimodal multi-objective optimization problems (MMOPs) have received increasing attention from many researchers. In such problems, there are situations where two or more Pareto Sets (PSs) correspond to the same Pareto Front (PF). It is crucial to obtain as many PSs as possible without compromising the performance of the objective space. Therefore, this paper proposes an enhanced multimodal multi-objective genetic algorithm with a novel adaptive crossover mechanism, named AEDN_NSGAII. In the AEDN_NSGAII, the special crowding distance strategy can provide potential development opportunities for individuals with a larger crowding distance. An adaptive crossover mechanism is established by combining the simulated binary …crossover (SBX) operator and the Laplace crossover (LP) operator, which adaptively improves the ability to obtain Pareto optimal solutions. Meanwhile, an elite selection mechanism can efficiently get more excellent individuals as parents to enhance the diversity of the decision space. Then, the proposed algorithm is evaluated on the CEC2019 test suite by the Friedman method and discussed for its feasibility through ablation experiments and boxplot analysis of PSP indicators. Experimental results show that AEDN_NSGAII can effectively search for more PSs without weakening the diversity and convergence of objective space. Finally, the performance of AEDN_NSGAII on the multimodal feature selection problem is compared with that of the other four algorithms. The statistical analysis demonstrates that the proposed algorithm has great potential for resolving this issue. Show more

Keywords: Multimodal multi-objective optimization, genetic algorithm, novel adaptive crossover mechanism, feature selection

DOI: 10.3233/JIFS-233135

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7369-7388, 2023

Authors: Lakshminarasimha, Kasetty | Ponniyin Selvan, V.

Article Type: Research Article

Abstract: Recent years have seen a rise in interest in face anti-spoofing (FAS) owing to the critical function it plays in protecting face recognition systems against presentation assaults (PAs). Early-stage FAS approaches relying on handmade characteristics become inaccurate when steadily realistic PAs of unique sorts emerge. Thus, face anti-spoofing algorithms are gaining increasing relevance in such setups. A very innovative method called deep learning has shown remarkable success in difficult computer vision problems. The proposed method uses deep acquisition and transfer of learning to extract characteristics from people’s faces. This is why the authors of this study recommend using the Faster …RCNN classifier with a face-liveness detection approach. Two distinct components— the data augmentation module for assessing sparse information as well as the faster RCNN classifier module— make up the anti-spoofing approach. We may use any publicly accessible dataset to train our quicker RCNN classifier. We successively fused these two components and used the Android platform to create a basic face recognition app. The results of the tests demonstrate that the developed module can identify several types of face spoof assaults, such as those carried out with the use of posters, masks, or cell phones. Testing the proposed architecture both across and inside databases using three benchmarking (Idiap Replay Attack, CASIA- FASD, & 3DMAD) demonstrate its ability to deliver outcomes on par with cutting-edge techniques. Show more

Keywords: Data augmentation, face anti spoofing, CASIA face datasets, and faster RCNN

DOI: 10.3233/JIFS-233394

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7389-7405, 2023

Authors: Zhu, Chang-Sheng | Qin, Peng

Article Type: Research Article

Abstract: Aiming at the problems of traditional text abstract extraction algorithms for processing long text of Chinese patents and unsatisfactory results of long abstract generation, the PatBertSum algorithm is proposed, which enables the algorithm to process long (more than 1500 words) patent text with high efficiency and generate high-quality long (more than 200 words) text summaries. The method is based on the improved BertSum algorithm model, using the new CLTPDS patented text dataset, processing long texts by Head-Tail, transforming Chinese input representations, generating sentence vectors using a pre-trained model, and capturing internal text features and text structure features to extract summaries. …Experimentally, this paper demonstrates that the method has improved the recall and F-value of ROUGE by more than 8 percentage points compared with existing methods. Show more

Keywords: Natural language processing, automatic summarization, Bertsum algorithm, ROUGE index

DOI: 10.3233/JIFS-222966

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7407-7414, 2023

Authors: Thangaraj, K. | Sakthivel, M. | Balasamy, K. | Suganyadevi, S.

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-223242

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7415-7428, 2023

Authors: Chen, Dewang | Kong, Lingkun | Gao, Liangpeng

Article Type: Research Article

Abstract: To shorten the operating time of the high-dimensional problems on fuzzy systems, we proposed the width residual neuro fuzzy system (WRNFS) before, but the discussion on the structure of WRNFS was insufficient, especially on the divide-and-conquer strategies of the input dimensions. In previous research, the optimization methods for WRNFS were not discussed. In this paper we proposed the first optimization method for WRNFS, which is an improved scheme for grouping the input dimensions of WRNFS, using random feature selection(RFS) to find a better solution, so as to improve the overall capability of the system. We call the width residual neuro …fuzzy system based on random feature-selection as RFS-WRNFS. In this paper, the exhaustive experiment analysis and practical test of WRNFS and RFS-WRNFS are carried out on the reconstructed MG dataset, and the following conclusions are obtained: ding172 The performance of WRNFS is generally consistent when the structure of the WRNFS sub-systems and the input-output pairs are fixed; ding173 When searching for the optimal solution on the WRNFS, the time cost of exhaustive search is acceptable when the system remains in a small scale; ding174 In most cases, RFS-WRNFS carries out several random tests and produces better results than WRNFS. Furthermore, assuming that the input dimension is N and the times of attempts used to random feature selection for a better solution of WRNFS is M, we found:1) when M = 1 N, there is a certain probability to get an acceptable solution, and the system takes the shortest time; 2) When M = 2 N, there is a great chance to get an acceptable solution in a limited time; 3) When M = 3 N, best solution can be obtained with the longest search time. We suggest M = 2 N for the RFS-WRNFS for the comprehensive performance. Comparing the experiment results of exhaustive search and random feature selection, WRNFS always reaches the optimal solution by exhaustive search through a finite set in a limited time, while RFS-WRNFS in most time keeps a good balance between prediction precision and time efficiency. Show more

Keywords: Adaptive neuro fuzzy interference system, exhaustive experiment, random feature selection

DOI: 10.3233/JIFS-223421

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7429-7443, 2023

Authors: Hu, Zunmei | Huang, Yuwen | Yang, Yuzhen

Article Type: Research Article

Abstract: Aiming at the challenges that the traditional photoplethysmography (PPG) biometrics is not robust and precision of recognition, this paper proposes a dual-feature and multi-scale fusion using U2 -net deep learning model (DMFUDM). First, to obtain complementary information of different features, we extract the local and global features of one-dimensional multi-resolution local binary patterns (1DMRLBP) and multi-scale differential feature (MSDF). Then, to extract robust discriminant feature information from the 1DMRLBP and MSDF features, a novel two-branch U2 -net framework is constructed. In addition, a multi-scale extraction module is designed to capture the transition information. It consists of multiple convolution layers with …different receptive fields for capturing multi-scale transition information. At last, a two-level attention module is used to adaptively capture valuable information for ECG biometrics. DMFUDM can obtain the average subject recognition rates of 99.76%, 98.31%, 98.97% and 98.87% on four databases, respectively, and experiment results show that it performs competitively with state-of-the-art methods on all four databases. Show more

Keywords: ECG, biometric recognition, multiple scales, U2-net, attention module

DOI: 10.3233/JIFS-230721

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7445-7454, 2023

Authors: Shi, Hongkang | Zhu, Shiping | Chen, Xiao | Zhang, Jianfei

Article Type: Research Article

Abstract: Identifying the day instar of silkworms is a fundamental task for precision rearing and behavioral analysis. This study proposes a new method for identifying the day instar of adult silkworms based on deep learning and computer vision. Images from the first day of instar 3 to the seventh day of instar 5 were photographed using a mobile phone, and a dataset containing 7, 000 images was constructed. An effective recognition network, called CSP-SENet, was proposed based on CSPNet, in which the hierarchical kernels were adopted to extract feature maps from different receptive fields, and an image attention mechanism (SENet) was …added to learn more important information. Experiments showed that CSP-SENet achieved a recognition precision of 0.9743, a recall of 0.9743, a specificity of 0.9980, and an F1-score of 0.9742. Compared to state-of-the-art and related networks, CSP-SENet achieved better recognition performance with the advantage of computational complexity. The study can provide theoretical and technical references for future work. Show more

Keywords: Identification of day instar, CSPNet, feature fusion, image attention mechanism, silkworm

DOI: 10.3233/JIFS-230784

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7455-7467, 2023

Authors: Liu, Weijun | Qi, Jianming | Jin, Yu | Zhou, Zhiyong | Zhang, Xu

Article Type: Research Article

Abstract: To enhance profitability of production cycle, any manufacturer needs effective product design and evaluation procedures. This study proposed a novel approach combining fuzzy analytic hierarchy process (FAHP) and multi-layer fuzzy inference system (MFIS). It is based on consumer online comments to improve product design. This method possesses several advantages over traditional design evaluation methods. It can quickly acquire consumer preferences, effectively handle multi-criteria decision problems and integrate uncertain and fuzzy information. The Fuzzy Analytic Hierarchy Process–Multi-layer Fuzzy Inference System (FAHP-MFIS) involves the following steps: screening of factors, hierarchical modeling, quantification of qualitative factors, and conversion of these factors into quantitative …values. It is a knowledge-based system that uses logical rules. The quantity and levels of input variables directly correlates with the quantity of logical rules. However, with multi-factor and multi-level inference, the establishment of a rule base becomes impractical due to the overwhelming number of rules. To address this issue, the Taguchi orthogonal table is applied to reduce the number of logical rules. Taking a household oxygen generator for medical devices as an example, the proposed model is applied in real-time. In the first stage, web crawlers are used to collect user reviews of the household oxygen generators on large e-commerce platforms. Latent Dirichlet Allocation (LDA) models are used to screen for principal and sub-factors in the second stage. Then, sub-factors of the FAHP screening are used as inputs, and the principal factors are used as outputs. In the third stage, priority indicators are established based on principal factors such as Appearance, Basic Function, and Advanced Function. Established evaluation models are then used to rank the selected designs. The results show that the higher the priority index value of the product design scheme, the better the scheme, and vice versa. This study holds significant reference value in aiding enterprises to enhance the efficiency of their manufacturing cycle and determining the direction of product design and innovation with improved pace and accuracy. Moreover, it can be applied to other fields such as supply chain management, risk assessment, and investment decisions. Show more

Keywords: Product design, FAHP, multi-layer fuzzy inference system, LDA, web crawlers, design evaluation

DOI: 10.3233/JIFS-230906

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7469-7492, 2023

Authors: Ge, Xiaoxiang | Choi, Deokhwan | Yuan, Mengxian | Yang, Zeyun

Article Type: Research Article

Abstract: The swift ascension of the sports industry can be attributed to the advancements of the contemporary era, and serves as a significant indication of the industry’s progression towards a novel phase and pinnacle. Despite a delayed inception, China’s sports industry has experienced a swift evolution and has established a unique developmental framework, thereby establishing a firm groundwork for the prospective growth of China’s sports industry. The sports industry of China is currently encountering fresh prospects for growth in the contemporary era. However, it is also confronted with formidable obstacles and strains that necessitate careful handling. To attain novel breakthroughs and …advancements, it remains imperative to explore innovative perspectives and avenues. The assessment of the sports industry’s high-quality development in the new era is a classic Multiple Attribute Group Decision Making (MAGDM) problem. The TODIM and VIKOR methodologies have been employed in addressing Multiple Attribute Group Decision Making (MAGDM) challenges in current times. Fuzzy number intuitionistic fuzzy sets (FNIFS) serve as a valuable instrument in the characterization of uncertain information for the comprehensive assessment of the high-quality development of the sports industry in the contemporary era. The present manuscript introduces the construction of the fuzzy number intuitionistic fuzzy TODIM-VIKOR (FNIF-TODIM-VIKOR) method, which is designed to address multiple attribute group decision making (MAGDM) problems in the context of fuzzy number intuitionistic fuzzy sets (FNIFSs). Ultimately, a numerical case study is presented to comprehensively evaluate the high-quality development of the sports industry in the new era, in order to validate the proposed methodology. Show more

Keywords: Multiple attribute group decision making (MAGDM), fuzzy number intuitionistic fuzzy sets (FNIFS), TODIM, VIKOR, comprehensive evaluation of high-quality development

DOI: 10.3233/JIFS-231502

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 5, pp. 7493-7505, 2023