IEEE Transactions on Emerging Topics in Computational Intelligence最新文献

IEEE Transactions on Emerging Topics in Computational Intelligence Information for Authors IEEE计算智能信息新主题汇刊

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-01-22 DOI: 10.1109/TETCI.2026.3651281

引用次数: 0

IEEE Computational Intelligence Society Information IEEE计算智能学会信息

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-01-22 DOI: 10.1109/TETCI.2026.3651279

引用次数: 0

2025 Index IEEE Transactions on Emerging Topics in Computational Intelligence 2025年IEEE计算智能新兴主题汇刊

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-12-02 DOI: 10.1109/TETCI.2025.3638911

引用次数: 0

IEEE Transactions on Emerging Topics in Computational Intelligence Information for Authors IEEE计算智能信息新主题汇刊

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-11-24 DOI: 10.1109/TETCI.2025.3629446

引用次数: 0

IEEE Computational Intelligence Society Information IEEE计算智能学会信息

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-11-24 DOI: 10.1109/TETCI.2025.3629444

引用次数: 0

Deep Neural Networks Internal Representation via Neuron Community Exploration 基于神经元群落探索的深度神经网络内部表征

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-11-07 DOI: 10.1109/TETCI.2025.3622647

Guipeng Lan;Shuai Xiao;Jiachen Yang;Wen Lu;Qinggang Meng;Xinbo Gao

{"title":"Deep Neural Networks Internal Representation via Neuron Community Exploration","authors":"Guipeng Lan;Shuai Xiao;Jiachen Yang;Wen Lu;Qinggang Meng;Xinbo Gao","doi":"10.1109/TETCI.2025.3622647","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3622647","url":null,"abstract":"Deep neural networks have demonstrated exceptional performance in extracting task-specific representations from datasets, earning widespread recognition and application. However, the internal representations often reside in abstract, high-dimensional spaces that are unsupervised and difficult to interpret. Additionally, their complex and tightly coupled structures hinder researchers' ability to understand the models effectively. To tackle these challenges, we introduce NeuronExplorer, an analytical framework that employs self-supervised techniques for learning high-dimensional information representations. NeuronExplorer analyzes the high-dimensional representations derived from the basic units, namely neurons, within the neural network, predicting the clusters to which these neurons belong. This process facilitates the ‘community’ of neurons, enhancing interpretability.Moreover, we refine this neuron community structure by assessing the causal effects of intervening in neuron outputs, allowing us to measure the impact on model performance. NeuronExplorer ultimately enables a deeper understanding of the internal information representation within deep neural networks. Comprehensive experiments conducted across multiple models demonstrate that NeuronExplorer effectively mines internal representations, thereby improving model transparency.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 1","pages":"1038-1049"},"PeriodicalIF":5.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Bi-Objective Optimization for Time-Dependent Preference-Driven Route Planning 时间依赖偏好驱动路径规划的双目标优化

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-11-03 DOI: 10.1109/TETCI.2025.3622664

Liping Gao;Feng Chu;Chao Chen

{"title":"Bi-Objective Optimization for Time-Dependent Preference-Driven Route Planning","authors":"Liping Gao;Feng Chu;Chao Chen","doi":"10.1109/TETCI.2025.3622664","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3622664","url":null,"abstract":"The development of intelligent transportation systems and the advancement of information technology bring new challenges to route planning, as shorter travel time may no longer be the travelers’ only preference for a route, and the preferences may also change over time which is overlooked in most prior work. In this paper, we study a new bi-objective planning problem with both time-dependent travel time and preference. The first objective is to maximize the total preference score and the second one is to minimize the total travel time. For the considered problem, an appropriate bi-objective integer linear model is formulated. Then, an exact <inline-formula><tex-math>$epsilon$</tex-math></inline-formula>-constraint method is proposed for small-sized instances, while a problem specific non-dominated sorting genetic algorithm-II (NSGA-II) is designed to handle large-sized instances. Specifically, novel region-based encoding and decoding methods are introduced to generate a set of solutions. Additionally, a feasibility condition and a repair strategy are incorporated to address cases where a chromosome is infeasible. We evaluate the proposed methods thoroughly based on 120 randomly generated road networks and 3 real-world road networks crawled via the OpenStreetMap platform. Results show that: (i) <inline-formula><tex-math>$epsilon$</tex-math></inline-formula>-constraint method obtains good performance on small-sized road networks; (ii) our problem-specific NSGA-II works well with large-sized road networks in obtaining the high-quality solutions while significantly saving computational time.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 1","pages":"1050-1068"},"PeriodicalIF":5.3,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

On-Policy Machine Learning Based-Disturbance Rejection Control for Grid-Tied PEC9 Inverter Under Parameters Mismatch and Distorted Grid Voltage 参数失配和电网电压畸变下并网PEC9逆变器的策略机器学习抗扰控制

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-11-03 DOI: 10.1109/TETCI.2025.3619574

Arman Fathollahi;Meysam Gheisarnejad;Mohammad Sharifzadeh;Eric Laurendeau;Björn Andresen;Kamal Al-Haddad

{"title":"On-Policy Machine Learning Based-Disturbance Rejection Control for Grid-Tied PEC9 Inverter Under Parameters Mismatch and Distorted Grid Voltage","authors":"Arman Fathollahi;Meysam Gheisarnejad;Mohammad Sharifzadeh;Eric Laurendeau;Björn Andresen;Kamal Al-Haddad","doi":"10.1109/TETCI.2025.3619574","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3619574","url":null,"abstract":"Thanks to higher power quality and performance efficiency, multilevel grid-tied inverters are the right choice for DC-to-AC conversion like the PV systems to the main power grid. However, the complexity of controlling the switching devices and capacitor voltages in these inverters presents significant stability challenges, particularly during grid-tied operation and when dealing with parameter mismatches. This paper proposes an optimized adaptive Active Disturbance Rejection Controller (ADRC) to stabilize the current of the grid-tied PEC9, serving as a multilevel inverter for PV applications. For this purpose, the PV system, connected to PEC9 as a main DC source to be integrated into the grid. The tunable coefficients of the ADRC controller are automatically adjusted using the on-policy reinforcement learning (RL) technique to effectively stabilize the grid-tied PEC9 with a PV inverter. In this approach, a reward function tailored to the inverter requirements guides the RL-agent in determining the optimal policy. Through maximizing the reward signal, the on-policy algorithm generates regulatory signals to adjust control gains accordingly. A laboratory prototype of PEC9 inverter is constructed by implementing OPAL-RT simulator to investigate the feasibility and applicability of suggested adaptive data-driven scheme. The experimental responses of grid-tied PEC9 equipped with the proposed adaptive ADRC demonstrate the effective performance under various operating conditions of grid-tied PV inverters, including change in the system’s references and parameter mismatches.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 1","pages":"1025-1037"},"PeriodicalIF":5.3,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Multi-Scale Shapley Adaptation Pruning: Realizing Backdoor Defense in Brain-Computer Interface With Shapley-Value-Based Neural Network Pruning 多尺度Shapley自适应剪枝：基于Shapley值的神经网络剪枝实现脑机接口后门防御

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-10-31 DOI: 10.1109/TETCI.2025.3619564

Fumin Li;Rui Yang;Hanjing Cheng;Mengjie Huang;Fanglue Zhang;Fuad E. Alsaadi;Zidong Wang

{"title":"Multi-Scale Shapley Adaptation Pruning: Realizing Backdoor Defense in Brain-Computer Interface With Shapley-Value-Based Neural Network Pruning","authors":"Fumin Li;Rui Yang;Hanjing Cheng;Mengjie Huang;Fanglue Zhang;Fuad E. Alsaadi;Zidong Wang","doi":"10.1109/TETCI.2025.3619564","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3619564","url":null,"abstract":"In the recent years, researchers made significant progress in electroencephalogram (EEG) classification tasks using deep neural networks, especially in brain-computer interface (BCI) systems. BCI systems rely on EEG signals for effective human-computer interaction, and deep neural networks have shown excellent performance in processing EEG signals. However, backdoor attack have a significant impact on the security of EEG-based BCI systems. In this paper, a novel multi-scale Shapley adaptation pruning (MSAP) method is proposed to solve the security problem caused by backdoor attack. In the proposed MSAP, the multi-scale Shapley segmented mapping method is used to accurately locate the backdoor weights. Subsequently, the cost function is utilized to adaptively prune the backdoor weights to ensure normal classification. Ultimately, the validity of the experiments is verified on the BCI competition public datasets (BCI-III-IVb, BCI-III-IVa, and BCI-IV-1a). The results show that the proposed MSAP method outperforms other pruning methods in defending EEG-based BCI systems against backdoor attack, maintaining a high baseline classification accuracy while reducing the attack success rate.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 1","pages":"967-981"},"PeriodicalIF":5.3,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Indeterminacy-Driven Trade-Off in Reinforcement Learning on Neutrosophic Fuzzy Hypergraphs for Explainable Item Recommendation With Path-Compliant Rewards 中性模糊超图上可解释项目推荐的不确定性驱动权衡

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2025-10-16 DOI: 10.1109/TETCI.2025.3616051

Mehbooba P Shareef;Babita Roslind Jose;Jimson Mathew;Ramkumar P. B.

{"title":"Indeterminacy-Driven Trade-Off in Reinforcement Learning on Neutrosophic Fuzzy Hypergraphs for Explainable Item Recommendation With Path-Compliant Rewards","authors":"Mehbooba P Shareef;Babita Roslind Jose;Jimson Mathew;Ramkumar P. B.","doi":"10.1109/TETCI.2025.3616051","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3616051","url":null,"abstract":"This paper presents a novel recommendation system designed to effectively suggest products to users by leveraging a neutrosophic fuzzy hypergraph structure, where users are represented as hyperedges and products as hypernodes. The approach incorporates a global partial order of items, derived from frequent pattern analysis, to establish an ordering framework over product recommendations. State vectors representing users are extracted and refined through a Graph Convolutional Neural Network (GCN), which captures the intricate relationships within the graph. Using a Deep Q Network (DQN)-based reinforcement learning model with indeterminacy-driven exploration-exploitation, the system learns optimal recommendation strategies from the feature representations of the neutrosophic fuzzy hypergraph. Reward signals are calculated by assessing how closely a new recommendation aligns with the partial ordering, as well as by using fuzzy rules generated from a domain-specific expert system. The recommendations are explained using paths extracted from the hypergraph. Our experimental evaluation on real-world datasets demonstrates that the proposed system outperforms state-of-the-art recommendation approaches in terms of Normalized Cumulative Discounted Gain(NDCG) and precision, indicating its strong suitability for practical applications in complex recommendation environments.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 1","pages":"996-1008"},"PeriodicalIF":5.3,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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