International Journal of Network Dynamics and Intelligence最新文献

{"title":"Analysing the effect of a dynamic physical environment network on the travel dynamics of forcibly displaced persons in Mali","authors":"Boesjes Freek, Jahani Alireza, Ooink Bas, Derek Groen","doi":"10.53941/ijndi.2024.100003","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100003","url":null,"abstract":"Article\u0000Analysing the effect of a dynamic physical environment network on the travel dynamics of forcibly displaced persons in Mali\u0000\u0000Boesjes Freek 1, Jahani Alireza 2, Ooink Bas 3, and Derek Groen 2,*\u0000\u0000\u00001 Utrecht University, Heidelberglaan 8, Utrecht, Utrecht 3584 CS, the Netherlands\u00002 Computer Science Department, Brunel University London, Wilfred Brown Building, Kingston Lane, Uxbridge UB8 3PH, UK\u00003 Blue Team Intelligence, Jan Aertshof 3, Hoevelaken 3871 WH, the Netherlands\u0000* Correspondence: Derek.Groen@brunel.ac.uk\u0000 \u0000 \u0000Received: 7 September 2023\u0000Accepted: 30 January 2024\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: As of 2023, the world has approximately 100 million refugees, many of whom have been displaced by violent conflicts. Accurately predicting where these people may go can help non-government organisations (NGOs) and other support organisations to more effectively help these refugees. In this paper, we extend the existing flee migration forecasting model which models migration using intelligent agents with a dynamic network that represents the physical environment. In doing so, we integrate time-dependent data into four different characteristics from three public data sources. We obtain data from aspects such as the slope, drainage, soil and infrastructure, and use these aspects to systematically modify the movement preferences of forcibly displaced agents in the flee model. We showcase our approach by applying it to the 2012 northern Mali conflict. We find that numerous routes previously deemed traversable are actually inaccessible for prolonged periods according to sensor data, and a range of off-road routes are instead traversable for vehicles. We also perform a validation comparison with the original modelling approach, and find that our revised representation of travel routes leads to a reduction of 4.5% in the averaged relative difference. Our approach can be reused in other flee conflict contexts, of which five are present in the EU-funded ITFLOWS project alone. Our work provides the ability to represent a dynamic physical environment and potentially improves the simulation accuracy in a range of flee conflict situations.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"105 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140379631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliable Cost Prediction and Control for Intelligent Manufacture: A Key Performance Indicator Perspective","authors":"Hang Geng, Alireza Mousavi, N. Markatos, Kai Chen, Xuan Gou","doi":"10.53941/ijndi.2024.100001","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100001","url":null,"abstract":"Article\u0000Reliable Cost Prediction and Control for Intelligent Manufacture: A Key Performance Indicator Perspective\u0000\u0000Hang Geng 1,*, Alireza Mousavi 2, Nikolaos Grigorios Markatos 2, Kai Chen 1, and Xuan Gou 1\u0000\u0000\u00001 School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China\u00002 Department of Computer Science, Brunel University London, Uxbridge, Middlesex, UB8 3PH, United Kingdom\u0000* Correspondence: Hang.Geng@uestc.edu.cn\u0000 \u0000 \u0000Received: 10 July 2023\u0000Accepted: 11 October 2023\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: Intelligent manufacturing is facing significant challenges in adapting to the ever-changing equipment, instrumentation, process and economics. Such a trend together with the pressure to reliably control and contain production costs means that frequent adjusting decisions are required to adapt to incessant volatility imposed on manufacturing systems. Under this circumstance, cost-effective and quality-guaranteed manufacturing strategies would be the most logical route to reducing production costs. In this paper, a novel dynamical cost prediction and control (CPC) model is proposed to support collective decision-making in intelligent manufacturing, where the model output is the real-time prediction of possible manufacturing costs, while the inputs are generic manufacturing key performance indicators covering inventory, product quality, production efficiency, resource utilisation and environmental impact. This proposed CPC model distinguishes itself from existing ones for its capability to translate manufacturing data (at both the physical level and operation management level) into financial metrics that contribute to forming a common language between engineering, financial and administrative departments of an enterprise. The case study about the assembly line of optoelectronic devices demonstrates that, although different enterprise departments have different priorities, our CPC model helps them to achieve certain consensus on intended production that finally creates satisfactory profitability for the company at controlled manufacturing costs.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"101 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140381154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Output Feedback Tracking Control for Nonlinear Systems with Unknown Growth Rate","authors":"Manman Yuan, Wei Qian","doi":"10.53941/ijndi.2024.100002","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100002","url":null,"abstract":"Article\u0000Adaptive Output Feedback Tracking Control for Nonlinear Systems with Unknown Growth Rate\u0000\u0000Manman Yuan 1,2,*, and Wei Qian 1,2,*\u0000\u0000\u00001 School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China\u00002 Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment, Jiaozuo 454003, China\u0000* Correspondence: ymmamhappy@163.com; qwei@hpu.edu.cn\u0000 \u0000 \u0000Received: 4 September 2023\u0000Accepted: 7 November 2023\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: In this paper, the problem of adaptive output feedback tracking is considered for a class of nonlinear systems with lower-triangular structures. A novel dynamic gain is introduced to deal with the unknown growth rate. By coupling the dynamic gain with the observer and the controller, an adaptive output tracking controller is developed, which can guarantee that all signals of the closed-loop system are globally bounded. Finally, the effectiveness of the presented control scheme is illustrated by a numerical example.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"107 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140379471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning Regression Distribution: Information Diffusion from Template to Search for Visual Object Tracking","authors":"Shuo Hu, Jinbo Lu, Sien Zhou","doi":"10.53941/ijndi.2024.100006","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100006","url":null,"abstract":"Article\u0000Learning Regression Distribution: Information Diffusion from Template to Search for Visual Object Tracking\u0000\u0000Shuo Hu *, Jinbo Lu, and Sien Zhou\u0000\u0000\u00001 School of Electrical Engineering, Yanshan University, Qinhuangdao 066000, China\u0000* Correspondence: hus@ysu.edu.cn\u0000 \u0000 \u0000Received: 5 July 2023\u0000Accepted: 19 October 2023\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: The general paradigm of traditional Siamese networks involves using cross-correlations to fuse features from the backbone, and this paradigm is limited by the inductive bias of the convolution kernel, resulting in the lack of global information. In this paper, we propose the Siamese learning regression distribution (SiamLRD) to address the local limitations of traditional cross-correlation operations on feature fusion and weak self-connections between features within different branches. The SiamLRD uses the cross-attention mechanism to replace cross-correlations between the features of the target region of interest and the template so as to enhance flexibility. Firstly, the original transformer structure is improved to be suitable for convolutional Siamese networks. The improved transformer architecture is then used to replace cross-correlation operations, resulting in more comprehensive feature fusion between branches. Secondly, we introduce a new decoder structure into the novel fusion strategy to enhance the correlation between classification scores and regression accuracy during decoding. Multiple benchmarks are used to test the proposed SiamLRD approach, and it is verified that the proposed approach improves the baseline with 5.8% in terms of AO and 9.7% in terms of SR0.75 on the GOT-10K dataset.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"124 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140378945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parameter Learning of Probabilistic Boolean Control Networks with Input-Output Data","authors":"Hongwei Chen, Qi Chen, Bo Shen, Yang Liu","doi":"10.53941/ijndi.2024.100005","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100005","url":null,"abstract":"Article\u0000Parameter Learning of Probabilistic Boolean Control Networks with Input-Output Data\u0000\u0000Hongwei Chen 1,*, Qi Chen 1, Bo Shen 1, and Yang Liu 2\u0000\u0000\u00001 College of Information Science and Technology, Donghua University, Shanghai 201620, China\u00002 School of Mathematical Sciences, Zhejiang Normal University, Jinhua 321004, China\u0000* Correspondence: hongwei@dhu.edu.cn\u0000 \u0000 \u0000Received: 23 September 2023\u0000Accepted: 27 November 2023\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: This paper investigates the parameter learning problem for the probabilistic Boolean control networks (PBCNs) with input-output data. Firstly, an algebraic expression of the PBCNs is obtained by taking advantage of the semi-tensor product technique, and then, the parameter learning problem is transformed into an optimal problem to reveal the parameter matrices of a linear system in a computationally efficient way. Secondly, two recursive semi-tensor product based algorithms are designed to calculate the forward and backward probabilities. Thirdly, the expectation maximization algorithm is proposed as an elaborate technique to address the parameter learning problem. In addition, a useful index is introduced to describe the performance of the proposed parameter learning algorithm. Finally, two numerical examples are employed to demonstrate the reliability of the proposed parameter learning approach.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"114 51","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140379171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fault-tolerant formation consensus control for time-varying multi-agent systems with stochastic communication protocol","authors":"Chunyu Li, Yifan Liu, Ming Gao, Li Sheng","doi":"10.53941/ijndi.2024.100004","DOIUrl":"https://doi.org/10.53941/ijndi.2024.100004","url":null,"abstract":"Article\u0000Fault-tolerant formation consensus control for time-varying multi-agent systems with stochastic communication protocol\u0000\u0000Chunyu Li, Yifan Liu, Ming Gao, and Li Sheng *\u0000\u0000\u00001 College of Control Science and Engineering, China University of Petroleum (East China), Qingdao 266580, China\u0000* Correspondence: E-mail: shengli@upc.edu.cn\u0000 \u0000Received: 4 September 2023\u0000Accepted: 8 November 2023\u0000Published: 26 March 2024\u0000 \u0000\u0000Abstract: This paper is concerned with the problem of fault-tolerant formation consensus control for linear time-varying (LTV) multi-agent systems (MASs) with stochastic communication protocol (SCP). The SCP is introduced to schedule the signal transmission, and only one neighbouring agent is allowed to transmit data at one instant. The purpose of this work is to design a fault-tolerant controller for each agent, so that, for all probabilistic scheduling behaviors, MASs can achieve the formation consensus performance. The state and fault are augmented into a new vector, meanwhile, each agent system is written as a singular one and a state observer is designed. By utilizing the estimated information of states and faults, the designed time-varying compensation term can reduce the impacts of unknown external disturbances and faults. Then, a sufficient condition is obtained to guarantee the performance constraint over the finite horizon for closed-loop systems. The parameters of observers and controllers are derived by solving coupled backward recursive Riccati difference equations. Finally, a numerical example is given to validate the effectiveness of the proposed fault-tolerant control scheme.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"78 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140377786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Scheduling for Large-Scale Flexible Job Shop Based on Noisy DDQN","authors":"Tingjuan Zheng, Yongbing Zhou, Mingzhu Hu, Jian Zhang","doi":"10.53941/ijndi.2023.100015","DOIUrl":"https://doi.org/10.53941/ijndi.2023.100015","url":null,"abstract":"Article\u0000Dynamic Scheduling for Large-Scale Flexible Job Shop Based on Noisy DDQN\u0000\u0000Tingjuan Zheng 1,2, Yongbing Zhou 1, Mingzhu Hu 1, and Jian Zhang 1,*\u0000\u0000\u00001 Institute of Advanced Design and Manufacturing, School of Mechanical Engineering Southwest Jiaotong University, Chengdu 610031, China\u00002 Guizhou Aerospace Electric Co., Ltd., Guiyang 550009, China\u0000* Correspondence: Jerrysmail@263.net\u0000 \u0000 \u0000Received: 3 July 2023\u0000Accepted: 8 October 2023\u0000Published: 21 December 2023\u0000 \u0000\u0000Abstract: The large-scale flexible job shop dynamic scheduling problem (LSFJSDSP) has a more complex solution space than the original job shop problem because of the increase in the number of jobs and machines, which makes the traditional solution algorithm unable to meet the actual production requirements in terms of the solution quality and time. To address this problem, we develop a dynamic scheduling model of a large-scale flexible job shop based on noisynet-double deep Q-networks (N-DDQNs), which takes the minimum expected completion time as the optimization objective and thoroughly takes into account the two dynamic factors (the new job arrival and the stochastic processing time). Firstly, a Markov decision process model is constructed for dynamic scheduling of a large-scale flexible workshop, and the corresponding reasonable state space, action space and reward function are designed. To address the problems (of solution stability and unsatisfactory scheduling strategy selection) in the conventional exploration method of DDQNs, learnable noise parameters are added to the DDQNs to create the N-DDQN algorithm framework, where the uncertainty weight is added. Secondly, the learnable noise parameters are added to the DDQNs to form the N-DDQN algorithm framework, and the uncertainty weight is added to realize automatic exploration. Hence, the issue is solved that the traditional DDQN exploration method may result in unsatisfactory solution stability and scheduling strategy selection. The proposed method, which has significant flexibility and efficacy, is demonstrated (by experimental findings) to be superior to the conventional method based on compound scheduling rules in tackling large-scale flexible job shop dynamic scheduling problems.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"20 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138948422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling and Causality Analysis of Human Sensorimotor Control System Based on NVAR Method","authors":"Jiyu Tan, Yurong Li, Qiurong Xie, Xiaoling Wang","doi":"10.53941/ijndi.2023.100014","DOIUrl":"https://doi.org/10.53941/ijndi.2023.100014","url":null,"abstract":"Article\u0000Modeling and Causality Analysis of Human Sensorimotor Control System Based on NVAR Method\u0000\u0000Jiyu Tan 1,2, Yurong Li 1,2,*, Qiurong Xie 3, and Xiaoling Wang 3\u0000\u0000\u00001 College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China\u00002 Fujian Key Lab of Medical Instrument and Pharmaceutical Technology, Fuzhou University, Fuzhou 350116, China\u00003 College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China\u0000* Correspondence: liyurong@fzu.edu.cn\u0000 \u0000 \u0000Received: 2 September 2023\u0000Accepted: 19 October 2023\u0000Published: 21 December 2023\u0000 \u0000\u0000Abstract: Neuromuscular disorders (such as stroke and spinal cord injuries) can lead to nerve damage that profoundly affects a patient's ability to control limb movements. Analyzing and modeling the human sensorimotor control system can establish a neurophysiological foundation for both fundamental research and clinical rehabilitation assessment. Electroencephalogram (EEG) signals provide insights into how the cerebral cortex regulates limb movements, while electromyogram (EMG) signals reveal how muscles respond to motor commands. Utilizing these signals, cortical-muscular models can be developed to facilitate the quantification and assessment of the human sensorimotor control system. This study proposes a method based on the nonlinear vector autoregression model and coiflets wavelet packet decomposition to perform multivariate time-frequency Granger causality analysis. The objective of this analysis is to compute the cortical-muscular causality matrix during elbow extension in stroke patients and construct a cortical-muscular causal network. The result reveals a frequency-dependent directed information flow pattern in the cortical-muscle causality matrix during elbow extension. Specifically, the GC values of EEG→EMG (down) and EMG→EEG (up) in the alpha and beta bands are significantly higher than those in the gamma band. The cortical-muscular causal network of stroke patients does not have small-world properties. The result indicates that the proposed method is able to characterize functional connections of brain myoelectric synchronization in different frequency bands within the time-frequency domain. It also uncovers the causal association that inherently exists in the human sensorimotor control system, providing a theoretical basis for further evaluation and quantification of the human sensorimotor control system.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"54 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138949774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predefined Time Fuzzy Adaptive Control of Switched Fractional-Order Nonlinear Systems with Input Saturation","authors":"Lusong Ding, Weiwei Sun","doi":"10.53941/ijndi.2023.100019","DOIUrl":"https://doi.org/10.53941/ijndi.2023.100019","url":null,"abstract":"Article\u0000Predefined Time Fuzzy Adaptive Control of Switched Fractional-Order Nonlinear Systems with Input Saturation\u0000\u0000Lusong Ding, and Weiwei Sun *\u0000\u0000\u00001 Institute of Automation, Qufu Normal University, Qufu 273165, China\u0000* Correspondence: wwsun@hotmail.com\u0000 \u0000 \u0000Received: 31 August 2023\u0000Accepted: 31 October 2023\u0000Published: 21 December 2023\u0000 \u0000\u0000Abstract: This article investigates the predefined-time fuzzy adaptive tracking control problem for a class of nonlinear switched fractional-order systems with input saturation and external disturbances under a nonstrict feedback structure. By combining the backstepping technique and the common Lyapunov function method, a predefined-time switching control method is constructed based on a novel fractional-order auxiliary function. The fuzzy logic system and the adaptive method are introduced to identify unknown compounded continuous functions. Moreover, the issue of calculating explosion and the problem of singularity are tackled through the newly proposed predefined-time and filter-based dynamic surface control. Especially, the construction of a continuous term in the controller eliminates possible chattering. The developed control strategy achieves that the closed-loop system is practically predefined-time stable under arbitrary switchings, where the upper bound of the settling-time can be defined by users in advance. Finally, two simulation examples are illustrated to prove the feasibility and effectiveness of the presented scheme.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"58 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138951727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Improved Generative Adversarial Network with Feature Filtering for Imbalanced Data","authors":"Jun Dou, Yan Song","doi":"10.53941/ijndi.2023.100017","DOIUrl":"https://doi.org/10.53941/ijndi.2023.100017","url":null,"abstract":"Article An Improved Generative Adversarial Network with Feature Filtering for Imbalanced Data Jun Dou 1, and Yan Song 2,* 1 Department of Systems Science, University of Shanghai for Science and Technology, Shanghai 200093, China 2 Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China * Correspondence: sonya@usst.edu.cn;Tel.:+86-21-55271299; fax:+86-21-55271299     Received: 7 October 2023 Accepted: 31 October 2023 Published: 21 December 2023   Abstract: Generative adversarial network (GAN) is an overwhelming yet promising method to address the data imbalance problem. However, most existing GANs that are usually inspired by computer vision techniques have not yet taken the significance and redundancy of features into consideration delicately, probably producing rough samples with overlapping and incorrectness. To address this problem, a novel GAN called improved GAN with feature filtering (IGAN-FF) is proposed, which establishes a new loss function for the model training by replacing the traditional Euclidean distance with the Mahalanobis distance and taking the ℓ1,2-norm regularization term into consideration. The remarkable merits of the proposed IGAN-FF can be highlighted as follows: 1) the utilization of the Mahalanobis distance can make a fair evaluation of different attributes without neglecting any trivial/small-scale but significant ones. In addition, it can mitigate the disturbance caused by the correlation between features; 2) the embedding of ℓ1,2-norm regularization term into the loss function contributes greatly to the feature filtering by guaranteeing the data sparsity as well as helps reduce risk of overfitting. Finally, empirical experiments on 16 well-known imbalanced datasets demonstrate that our proposed IGAN-FF performs better at most evaluation metrics than the other 11 state-of-the-art methods.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"8 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139167817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}