Information Sciences最新文献_第9页

Dual-channel dynamic event-triggered-based flocking control for nonlinear multi-agent systems with connectivity preservation 非线性多智能体系统的双通道动态事件触发群集控制

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-26 DOI: 10.1016/j.ins.2025.122459

Chengqing Liang , Lei Liu , Jinde Cao

{"title":"Dual-channel dynamic event-triggered-based flocking control for nonlinear multi-agent systems with connectivity preservation","authors":"Chengqing Liang , Lei Liu , Jinde Cao","doi":"10.1016/j.ins.2025.122459","DOIUrl":"10.1016/j.ins.2025.122459","url":null,"abstract":"<div><div>The flocking control problem of NMASs with network connectivity preserving under a <strong>d</strong>ual-channel <strong>d</strong>ynamic <strong>e</strong>vent-<strong>t</strong>riggered <strong>m</strong>echanism (DDETM) is investigated in this paper. Firstly, a novel DDETM is developed to minimize the transmission of redundant information. The communication and controller channels are equipped with an event monitoring mechanism. This approach not only minimizes the consumption of information transmission resources but also reduces the controller updates. In contrast to the single-channel ETM, incorporating two auxiliary variables increases the triggering intervals. Secondly, a novel network connectivity preservation mechanism via an improved potential function is designed to prevent flocking separation. This mechanism operates independently of the initial topology's connectivity. The DDETM framework integrates both the dual-channel scheme and the potential function. This integration constrains the distance between agents to avoid collisions and accelerate the convergence of the flocking behavior. Sufficient conditions for asymptotic flocking in NMASs are derived. Finally, a software verification platform for UAVs is established, and the software-in-the-loop (SIL) experiment of UAVs is conducted to showcase the feasibility and effectiveness of the proposed scheme.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122459"},"PeriodicalIF":8.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leader-following scaled consensus of multi-agent systems based on nonlinear parabolic PDEs via dynamic event-triggered boundary control 基于动态事件触发边界控制的非线性抛物型偏微分方程多智能体系统的领导者-跟随尺度共识

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-26 DOI: 10.1016/j.ins.2025.122449

Xinman Li , Haijun Jiang , Zhiyong Yu , Yue Ren , Tingting Shi , Shanshan Chen

{"title":"Leader-following scaled consensus of multi-agent systems based on nonlinear parabolic PDEs via dynamic event-triggered boundary control","authors":"Xinman Li , Haijun Jiang , Zhiyong Yu , Yue Ren , Tingting Shi , Shanshan Chen","doi":"10.1016/j.ins.2025.122449","DOIUrl":"10.1016/j.ins.2025.122449","url":null,"abstract":"<div><div>The aim of this work is to propose a dynamic event-triggered boundary control (DETBC) strategy to investigate the leader-following exponential scaled consensus (SC) problem for multi-agent systems (MASs) under the parabolic partial differential equations (PDEs) framework. Towards this aim, a novel DETBC protocol with Neumann-type boundary conditions is designed, which only needs the information of agents at the boundary <span><math><mi>x</mi><mo>=</mo><mi>l</mi></math></span> rather than the entire spatial domain. Moreover, the adoption of dynamic threshold in the event-triggered mechanism can effectively diminish the frequency of controller updates to bring down the communication loads and economize on control charges. Subsequently, several sufficient conditions to ensure the realization of leader-following SC are acquired in terms of linear matrix inequalities (LMIs) through the Lyapunov method and Wirtinger's inequality. Meanwhile, it is demonstrated that Zeno behavior can be excluded by the devised DETBC strategy. Eventually, some numerical experiments are framed to evaluate the theoretical results.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122449"},"PeriodicalIF":8.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Object recognition based on tactile information: A generalized recognition network combining wavelet transform and transformer model for small sample datasets 基于触觉信息的物体识别：小样本数据集小波变换与变压器模型相结合的广义识别网络

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-26 DOI: 10.1016/j.ins.2025.122464

Liang Li , Shengjie Qiu , Baojiang Li , Bin Wang , Haiyan Wang , Zizhen Yi , Chunbo Zhao

{"title":"Object recognition based on tactile information: A generalized recognition network combining wavelet transform and transformer model for small sample datasets","authors":"Liang Li , Shengjie Qiu , Baojiang Li , Bin Wang , Haiyan Wang , Zizhen Yi , Chunbo Zhao","doi":"10.1016/j.ins.2025.122464","DOIUrl":"10.1016/j.ins.2025.122464","url":null,"abstract":"<div><div>Tactile recognition is a crucial pathway for robots in perception and cognitive processing. While deep learning-based methods have shown excellent performance, training deep neural networks demands a substantial number of manually labeled samples. Unfortunately, current tactile recognition datasets lack the samples needed for robust training. To address this, we introduce a generalized tactile recognition method under low-sample conditions, Wave-Tactile-Transformer. Initially, we expand the tactile data using proposed TacGAN, avoiding traditional processes like rotation and cropping that create redundancy, which yields up to 5.8% accuracy improvement over traditional augmentation techniques. We also propose a Transformer framework integrated with multi-scale wavelet transforms, which is applicable to various tactile data formats. The wavelet transform enhances the model’s ability to discern details in tactile images, while the Transformer network refines the comprehension of feature relationships. This dual approach not only significantly reduces computational costs but also boosts object recognition accuracy. Our approach introduces an innovative framework that harmonizes the processing of tactile data across diverse formats. Cross-format tactile dataset experiments achieved a peak recognition accuracy of 96.7%, outperforming conventional CNN-based methods by up to 2.6%, surpassing previous methods. This generalized tactile recognition network offers innovative solutions for robotic tactile perception and grasp control.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122464"},"PeriodicalIF":8.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A noise-robust and generalizable framework for facial expression recognition 基于噪声鲁棒性的面部表情识别框架

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-26 DOI: 10.1016/j.ins.2025.122457

Jinglin Zhang , Qiangchang Wang , Jing Li , Yilong Yin

{"title":"A noise-robust and generalizable framework for facial expression recognition","authors":"Jinglin Zhang , Qiangchang Wang , Jing Li , Yilong Yin","doi":"10.1016/j.ins.2025.122457","DOIUrl":"10.1016/j.ins.2025.122457","url":null,"abstract":"<div><div>Facial Expression Recognition (FER) shows promising applicability in various real-world contexts, including criminal investigations and digital entertainment. Existing cross-domain FER methods primarily focus on spatial domain features sensitive to noise. However, these methods may propagate noise from the source domain to unseen target domains, degrading recognition performance. To address this, we propose a Noise-Robust and Generalizable framework for FER (NR-GFER), mainly comprising Residual Adapter (RA), Fourier Prompt (FP) modules, and a cross-stage unified fusion mechanism. Specifically, the RA module flexibly transfers the generalization ability of a visual-language large model to FER. Leveraging the residual mechanism improves the discriminative ability of spatial domain features. However, the domain gap may lead FER models to capture source domain-specific noise, which adversely affects performance on target domains. To mitigate this, the FP module extracts frequency domain features via the Fourier transform, integrates them with prompts, and reconstructs them back to the spatial domain through the inverse Fourier transform, thus reducing the negative impact of noise from the source domain. Finally, the cross-stage unified fusion mechanism that bridges intra-module and inter-module semantic priorities, simplifying hyperparameter optimization. Comprehensive evaluations across seven in-the-wild FER datasets confirm that our NR-GFER achieves state-of-the-art performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122457"},"PeriodicalIF":8.1,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Regenerative population strategy-I: A dynamic methodology to mitigate structural bias in metaheuristic algorithms 再生种群策略- 1：一种动态方法来减轻元启发式算法中的结构偏差

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-25 DOI: 10.1016/j.ins.2025.122444

Kanchan Rajwar , Kusum Deep

{"title":"Regenerative population strategy-I: A dynamic methodology to mitigate structural bias in metaheuristic algorithms","authors":"Kanchan Rajwar , Kusum Deep","doi":"10.1016/j.ins.2025.122444","DOIUrl":"10.1016/j.ins.2025.122444","url":null,"abstract":"<div><div>Structural bias in metaheuristic algorithms is a critical issue, characterized by an inherent tendency to excessively exploit certain regions of the search space, even when unsupported by the objective function. This bias can distort the exploration process, negatively impacting the efficiency and effectiveness of the algorithms. Although many studies focus on understanding and identifying structural bias, effective mitigation strategies remain scarce. To address this gap, this study introduces the Regenerative Population Strategy-I (RPS-I), a methodology designed to counteract structural bias by dynamically redistributing the population. RPS-I integrates seamlessly into existing metaheuristic frameworks without altering their core mechanisms, providing a practical solution to reduce structural bias. The effectiveness of RPS-I is demonstrated by applying it to six metaheuristic algorithms: Genetic Algorithm, Differential Evolution, Particle Swarm Optimization, Grey Wolf Optimizer, Whale Optimization Algorithm, and Harris Hawks Optimization. The Generalized Signature Test is used to quantify the structural bias of these algorithms after incorporating RPS-I. The results indicate that the RPS-I-enhanced versions exhibit a significant reduction in bias compared to their original counterparts. Furthermore, these enhanced versions are validated using the IEEE CEC 2022 benchmark functions and two classical engineering problems, where they demonstrate improved search capabilities. This study highlights the importance of mitigating structural bias in metaheuristic algorithms, preserving the strengths of existing methods while extending their applicability and robustness. The source code for RPS-I is publicly available at <span><span>https://github.com/kanchan999/RPS-I_Code.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122444"},"PeriodicalIF":8.1,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NodeHGAE: Node-oriented heterogeneous graph autoencoder NodeHGAE：面向节点的异构图自编码器

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-25 DOI: 10.1016/j.ins.2025.122448

Xiangkai Zhu , Chao Li , Yeyu Yan , Zhongying Zhao , Hua Duan , Qingtian Zeng

{"title":"NodeHGAE: Node-oriented heterogeneous graph autoencoder","authors":"Xiangkai Zhu , Chao Li , Yeyu Yan , Zhongying Zhao , Hua Duan , Qingtian Zeng","doi":"10.1016/j.ins.2025.122448","DOIUrl":"10.1016/j.ins.2025.122448","url":null,"abstract":"<div><div>Heterogeneous graph autoencoder (HGAE), as an unsupervised learning approach, aims to encode nodes and edges of heterogeneous graphs into low-dimensional vector representations, and simultaneously reconstruct the original graph structure from node representations. Existing heterogeneous graph encoders typically follow the metapath paradigm, encoding different semantic information and then employing decoders to reconstruct nodes attributes and edges information. However, the interaction between different semantic structures is underestimated which may lead to loss of semantic information. Moreover, employing graph-level unified attention mechanism to weigh the importance of different semantic structures of nodes is a suboptimal choice. Motivated by these challenges, a novel method named Node-oriented Heterogeneous Graph Autoencoder (NodeHGAE) is proposed. It first aggregates different semantic information based on node neighborhoods and utilizes the Chebyshev function to derive high-order neighborhood information of nodes. Then, low-rank matrix and parameter decoupling are proposed to assign node-specific attention and semantic information is integrated from different levels. Additionally, node-level and graph-level contrastive loss are proposed to redress the noise problem in the process of feature and topology coupling in HGAE. Experiments have shown that NodeHGAE outperforms state-of-the-art methods on four public heterogeneous graph datasets. The code of NodeHGAE can be found at Github.<span><span><sup>1</sup></span></span></div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122448"},"PeriodicalIF":8.1,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multimodal multi-objective evolutionary algorithm assisted by long short term memory 基于长短期记忆的多模态多目标进化算法

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-23 DOI: 10.1016/j.ins.2025.122443

Qianlong Dang , Shuai Yang , Tao Zhan

{"title":"A multimodal multi-objective evolutionary algorithm assisted by long short term memory","authors":"Qianlong Dang , Shuai Yang , Tao Zhan","doi":"10.1016/j.ins.2025.122443","DOIUrl":"10.1016/j.ins.2025.122443","url":null,"abstract":"<div><div>When solving multimodal multi-objective optimization problems, the exploration ability and exploitation ability of algorithms are important for searching the equivalent Pareto optimal solution set (PSs). However, most of the traditional algorithms adopt meta-heuristic operators to reproduce offspring, which have superior exploration ability but insufficient exploitation ability. This leads to the incomplete and uneven distribution of the obtained PSs. To solve the above problem, an evolutionary algorithm based on Long Short Term Memory (LSTM) is proposed, which processes the population information under different generations into time series and learns the evolution regular patterns through LSTM to predict future population distribution. Specifically, an LSTM-based prediction model is constructed to reproduce promising offspring, which improves exploitation ability. Based on this, a reproduction strategy based on meta-heuristic operators and LSTM is utilized to ensure good exploration and exploitation in the decision space. Moreover, a convergence vector is designed to preserves both global PSs and local PSs by calculating the convergence relationship. The experimental results on 62 MMOPs show that the proposed algorithm performs better eight advanced MMOEAs, and its performance in the decision space and objective space is improved by 14.32% and 11.35% compared with the closest competitors. Finally, the algorithm is employed to the map-based test problem in engineering, showing superior performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122443"},"PeriodicalIF":8.1,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144470737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An improved adaptive large neighborhood search for the home health care routing and scheduling problem with multiple mixed time windows 基于多混合时间窗的家庭医疗路径和调度问题的改进自适应大邻域搜索

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-23 DOI: 10.1016/j.ins.2025.122458

Wei Zhang , Wen Ma , Shengxiang Yang , Shengzong Chen , Jihui Zhang

{"title":"An improved adaptive large neighborhood search for the home health care routing and scheduling problem with multiple mixed time windows","authors":"Wei Zhang , Wen Ma , Shengxiang Yang , Shengzong Chen , Jihui Zhang","doi":"10.1016/j.ins.2025.122458","DOIUrl":"10.1016/j.ins.2025.122458","url":null,"abstract":"<div><div>The growing challenges posed by population aging and urbanization have intensified the need for efficient home health care (HHC) services to alleviate the great pressure on healthcare resources. This study addresses the Home Health Care Routing and Scheduling Problem (HHCRSP), which involves optimizing caregivers’ daily schedules while considering complex real-world constraints, including skill matching, mixed hard and soft time windows, synchronized services, and workload balancing. To address these challenges, a novel mixed-integer linear programming (MILP) model and an improved adaptive large neighbourhood search (IALNS) algorithm are proposed. The algorithm integrates an elite archive mechanism and introduces new removal and insertion operators, thus maintains archive diversity, and effectively explores the solution space through reconstruction, crossover, and mutation. Furthermore, it adopts a two-stage approach to ensure solution feasibility. Extensive computational experiments show the effectiveness of the proposed method and the competitiveness of the IALNS. Also, we examine the impact of the proportion of clients purchasing on-time services, time window penalty coefficients, and the number of available time windows on scheduling solutions. These findings underscore the proposed algorithm’s potential to reduce the cost of HHC services.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122458"},"PeriodicalIF":8.1,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TSINet: A temporal-channel factorized mixing and spectral enhanced interactive network for time series forecasting 时间序列预测的时间通道分解混合和频谱增强交互网络

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-20 DOI: 10.1016/j.ins.2025.122440

Junjie Lin, Dongsheng Liu, Tong Wu, Yangbo Xu, Yahui Chen

{"title":"TSINet: A temporal-channel factorized mixing and spectral enhanced interactive network for time series forecasting","authors":"Junjie Lin, Dongsheng Liu, Tong Wu, Yangbo Xu, Yahui Chen","doi":"10.1016/j.ins.2025.122440","DOIUrl":"10.1016/j.ins.2025.122440","url":null,"abstract":"<div><div>Time series forecasting is crucial in fields like energy, meteorology, and power systems, where accurately modeling both long-term and short-term dependencies is vital. While Transformer-based models are effective at capturing long-term patterns through self-attention, their performance is constrained by sensitivity to high-frequency noise and limited use of spectral information. To tackle these issues, this work presents a temporal-channel factorized mixing and spectral enhanced interactive network, named TSINet. Specifically, TSINet employs a <strong>T</strong>ime-channel factorized mixing module, which uses a factorization strategy to facilitate cross-dimensional interactions between time steps and channels, thereby reducing redundant noise; a <strong>S</strong>pectral information enhanced decomposition mixing module to enhance high-frequency spectral information and improve the extraction of key signal features; and an <strong>I</strong>nteractive representation shared-uniqueness prediction module that combines large and small convolutional kernels to jointly capture global trends and local variations. Through tailored fusion and separation strategies, TSINet effectively models the multi-level structure of time series data. Experimental outcomes reveal that TSINet consistently delivers superior forecasting results compared to leading models across seven real-world datasets in areas such as electricity, weather, and traffic.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122440"},"PeriodicalIF":8.1,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning functional data on-line: An evolving functional fuzzy-neural system approach 在线学习功能数据：一种进化的功能模糊神经系统方法

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-06-20 DOI: 10.1016/j.ins.2025.122442

Dongjiao Ge , Xiao-Jun Zeng

{"title":"Learning functional data on-line: An evolving functional fuzzy-neural system approach","authors":"Dongjiao Ge , Xiao-Jun Zeng","doi":"10.1016/j.ins.2025.122442","DOIUrl":"10.1016/j.ins.2025.122442","url":null,"abstract":"<div><div>Functional data analysis (FDA) has attracted great attention from the statistical community, but there are few fuzzy systems approaches. Therefore, this is a great opportunity for the fuzzy systems community. Focusing on the function-on-function (FOF) regression problem in FDA, the existing models are batch learning models with fixed model structure and parameters, which makes them unsuitable for solving the time-varying regression problem that requires the model to be updated dynamically and continuously with streams of functional data. Furthermore, as far as we are aware, there is no work on the online learning approach for FOF regression problems. To fill this gap, this paper proposes a nonlinear online FOF regression approach called evolving functional fuzzy-neural system (EFFNS) to learn functional data streams in real-time, with both input and output being functions. As a completely new type of evolving fuzzy system designed to learn from data represented as functions rather than vectors or matrices, EFFNS has a flexible model structure which could start from an empty rule base, expand and shrink the rule base, and tune the parameters dynamically depending on the knowledge learned from the rapidly coming functions. Various benchmark examples verify that EFFNS outperforms many of the state-of-the-art approaches.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122442"},"PeriodicalIF":8.1,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0