IEEE transactions on neural networks and learning systems最新文献_第6页

Physics-Guided Time-Interactive-Frequency Network for Cross-Domain Few-Shot Hyperspectral Image Classification. 跨域少镜头高光谱图像分类的物理制导时频交互网络。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-23 DOI: 10.1109/tnnls.2025.3608294

Jiaojiao Li,Hailong Wu,Rui Song,Haitao Xu,Yunsong Li,Qian Du

{"title":"Physics-Guided Time-Interactive-Frequency Network for Cross-Domain Few-Shot Hyperspectral Image Classification.","authors":"Jiaojiao Li,Hailong Wu,Rui Song,Haitao Xu,Yunsong Li,Qian Du","doi":"10.1109/tnnls.2025.3608294","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3608294","url":null,"abstract":"Recently, domain alignment and metric-based few-shot learning (FSL) have been introduced into hyperspectral image classification (HSIC) to solve the issues of uneven data distribution and scarcity of annotated data faced in practical applications. However, existing cross-domain few-shot methods ignore pivotal frequency priors of the complex field, which contribute to better category discrimination and knowledge transfer. To address this issue, we propose a novel physics-guided time-interactive-frequency network (PTFNet) for cross-domain few-shot HSIC, enabling the extraction of both frequency priors and spatial features (termed \"time domain\" following Fourier convention) simultaneously through a lightweight time-interactive-frequency module (TiF-Module) as a pioneering effort. Meanwhile, a spectral Fourier-based augmentation module (SFA-Module) is designed to decouple the frequency priors and enhance the diversity of distribution of physical attributes to imitate the domain shift. Then, the physics consistency loss is introduced to regularize the diverse embeddings to approximate the center of each category's physical attributes, guiding the network to excavate more transferable knowledge of source domain (SD). Furthermore, to fully exploit the discriminant time-frequency information and further improve the accuracy of boundary pixels, a set of multiorientation homogeneous prototypes is adopted to represent each class comprehensively, and an intuitive and flexible uncertainty-rectified bidirectional random walk strategy is applied to replace the Euclidean metric for more reliable classification. The experimental results on four public datasets demonstrate the prominent performance of the proposed PTFNet.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"80 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145127193","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

Reinforcement Learning-Based Boundary-Optimized Control of Flexible Manipulators Under Jointly Connected Switching Topologies. 联合连接切换拓扑下基于强化学习的柔性机械臂边界优化控制。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-23 DOI: 10.1109/tnnls.2025.3609134

Xiangqian Yao,Lin Li,Yu Liu

{"title":"Reinforcement Learning-Based Boundary-Optimized Control of Flexible Manipulators Under Jointly Connected Switching Topologies.","authors":"Xiangqian Yao,Lin Li,Yu Liu","doi":"10.1109/tnnls.2025.3609134","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3609134","url":null,"abstract":"This article pioneers the study of boundary-optimized fault-tolerant tracking control for flexible manipulators in a switching digraph with a heterogeneous linear leader. Compared with existing research, the proposed methods have several features. First, a distributed observer is designed to observe the leader's information in a general switching graph where communication can be interrupted. Second, a new partial differential equation (PDE)-based fault observer (FO) is designed to estimate unknown faults using only a few boundary states. Third, a novel long-term integral cost function is formulated to minimize angle-tracking errors, vibration deflections, and control energy in flexible manipulators. The ideal boundary optimal control laws are, then, derived and approximated using actor-critic neural networks (NNs) based on reinforcement learning (RL). Under the proposed fully distributed optimized fault-tolerant controllers, the closed-loop flexible manipulator's error states are proven uniformly ultimately bounded (UUB). Finally, the effectiveness of the proposed method is demonstrated through numerical simulation results.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"86 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145127195","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

Coupled Tensor Decomposition for Compact Network Representation 紧网络表示的耦合张量分解

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-22 DOI: 10.1109/tnnls.2025.3609797

Van Tien Pham, Yassine Zniyed, Thanh Phuong Nguyen

引用次数: 0

Contrastive Federated Learning for Graph Anomaly Detection 图异常检测的对比联邦学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-22 DOI: 10.1109/tnnls.2025.3601449

Hui Fang, Yang Gao, Peng Zhang, Sheng Zhou, Hongyang Chen, Jiajun Bu, Haishuai Wang

引用次数: 0

A Self-Supervised Learning Framework for Soft Robot Proprioception 软体机器人本体感觉的自监督学习框架

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-22 DOI: 10.1109/tnnls.2025.3610759

Delin Hu, Huazhi Dong, Francesco Giorgio-Serchi, Yunjie Yang

引用次数: 0

Vision Mamba: A Comprehensive Survey and Taxonomy 视觉曼巴：一个全面的调查和分类

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-22 DOI: 10.1109/tnnls.2025.3610435

Xiao Liu, Chenxu Zhang, Fuxiang Huang, Shuyin Xia, Guoyin Wang, Lei Zhang

引用次数: 0

Toward an Effective Action-Region Tracking Framework for Fine-Grained Video Action Recognition 一种用于细粒度视频动作识别的有效动作区域跟踪框架

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-19 DOI: 10.1109/tnnls.2025.3602089

Baoli Sun, Yihan Wang, Xinzhu Ma, Zhihui Wang, Kun Lu, Zhiyong Wang

引用次数: 0

Leveraging Semi-Supervised Learning and Meta-Learning for Re-Identification in Few-Shot Spatiotemporal Anomaly Detection 利用半监督学习和元学习在小样本时空异常检测中的再识别

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-19 DOI: 10.1109/tnnls.2025.3578642

Zhen Zhou, Ziyuan Gu, Pan Liu, Wenwu Yu, Zhiyuan Liu

引用次数: 0

Peak-Padding: Clustering by Padding Density Peaks With the Minimum Padding Cost 峰值填充：通过填充密度峰值以最小填充成本聚类

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-19 DOI: 10.1109/tnnls.2025.3606527

Junyi Guan, Bingbing Jiang, Weiguo Sheng, Yangyang Zhao, Sheng Li, Xiongxiong He

引用次数: 0

Restoring Noisy Demonstration for Imitation Learning With Diffusion Models 用扩散模型恢复模仿学习的噪声演示

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-17 DOI: 10.1109/tnnls.2025.3607111

Shang-Fu Chen, Co Yong, Shao-Hua Sun

引用次数: 0