IEEE transactions on neural networks and learning systems最新文献_第9页

A Structurally Regularized CNN Architecture via Adaptive Subband Decomposition 通过自适应子带分解实现结构正规化的 CNN 架构

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-08 DOI: 10.1109/tnnls.2024.3486181

Pavel Sinha, Ioannis Psaromiligkos, Zeljko Zilic

引用次数: 0

Few-Shot Image Generation via Style Adaptation and Content Preservation. 通过风格适配和内容保存生成短镜头图像

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3477467

Xiaosheng He, Fan Yang, Fayao Liu, Guosheng Lin

引用次数: 0

Adaptive Neural Network Control for Fixed-Wing UAV With Disturbance Observer Under Switching Disturbance. 固定翼无人机的自适应神经网络控制与切换干扰下的干扰观测器

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3477745

Zhengguo Huang, Mou Chen, Peng Shi, Hao Shen

{"title":"Adaptive Neural Network Control for Fixed-Wing UAV With Disturbance Observer Under Switching Disturbance.","authors":"Zhengguo Huang, Mou Chen, Peng Shi, Hao Shen","doi":"10.1109/TNNLS.2024.3477745","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3477745","url":null,"abstract":"The adaptive neural network (NN) control for the fixed-wing unmanned aerial vehicle (FUAV) under the unmodeled dynamics and the time-varying switching disturbance (TVSD) is investigated in this article. To better describe the TVSD induced by the change in the flight area of the FUAV, a switching augmented model (SAM) based on the known information about the TVSD is proposed first. The parameter adaptation technique is used to estimate the related TVSD. Thereafter, the time-varying disturbance that cannot be described by the SAM is estimated by the disturbance observer (DO). The radial basis function NN (RBFNN) is adopted to approximate the unknown unmodeled dynamics. The coupling terms derived from the co-design of DO and the parameter adaptation (PA) are separated by some inequality techniques. Then, the separated unknown terms are eliminated by designing the parameters of the controller and that of the adaptive law. The separated known terms are tackled by adding robust control terms to the controller. In addition, to improve the estimation performance for the TVSD and RBFNN, the auxiliary system in the DO form is designed. Sufficient stable conditions about the closed-loop switched system (CLSS) are obtained with and without the inequality about the switching times. Finally, an illustrative example is given to show the feasibility and advantage of the proposed control strategy by the attitude model of the FUAV.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590725","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

AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection. AO-DETR：用于 X 射线违禁品检测的反重叠 DETR。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3487833

Mingyuan Li, Tong Jia, Hao Wang, Bowen Ma, Hui Lu, Shuyang Lin, Da Cai, Dongyue Chen

{"title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection.","authors":"Mingyuan Li, Tong Jia, Hao Wang, Bowen Ma, Hui Lu, Shuyang Lin, Da Cai, Dongyue Chen","doi":"10.1109/TNNLS.2024.3487833","DOIUrl":"10.1109/TNNLS.2024.3487833","url":null,"abstract":"Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590736","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

Unpaired Multiview Clustering via Reliable View Guidance. 通过可靠的视图引导进行非配对多视图聚类。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3479777

Like Xin, Wanqi Yang, Lei Wang, Ming Yang

{"title":"Unpaired Multiview Clustering via Reliable View Guidance.","authors":"Like Xin, Wanqi Yang, Lei Wang, Ming Yang","doi":"10.1109/TNNLS.2024.3479777","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3479777","url":null,"abstract":"This article focuses on unpaired multiview clustering (UMC), a challenging problem, where paired observed samples are unavailable across multiple views. The goal is to perform effective joint clustering using the unpaired observed samples in all views. In incomplete multiview clustering (IMC), existing methods typically rely on sample pairing between views to capture their complementary. However, this is not applicable in the case of UMC. Hence, we aim to extract the consistent cluster structure across views. In UMC, two challenging issues arise: the uncertain cluster structure due to the lack of labels and the uncertain pairing relationship due to the absence of paired samples. We assume that the view with a good cluster structure is the reliable view, which acts as a supervisor to guide the clustering of the other views. With the guidance of reliable views, a more certain cluster structure of these views is obtained while achieving alignment between the reliable views and the other views. Then, we propose reliable view guided UMC with one reliable view (RG-UMC) and reliable view guided UMC with multiple reliable views (RGs-UMC). Specifically, we design alignment modules with one reliable view and multiple reliable views, respectively, to adaptively guide the optimization process. Also, we utilize the compactness module to enhance the relationship of samples within the same cluster. Meanwhile, an orthogonal constraint is applied to the latent representation to obtain discriminate features. Extensive experiments show that both RG-UMC and RGs-UMC outperform the best state-of-the-art method by an average of 24.14% and 29.42% in normalized mutual information (NMI), respectively.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590760","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 Cost-Aware Utility-Maximizing Bidding Strategy for Auction-Based Federated Learning. 基于拍卖的联合学习的成本意识效用最大化投标策略。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3474102

Xiaoli Tang, Han Yu

{"title":"A Cost-Aware Utility-Maximizing Bidding Strategy for Auction-Based Federated Learning.","authors":"Xiaoli Tang, Han Yu","doi":"10.1109/TNNLS.2024.3474102","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3474102","url":null,"abstract":"Auction-based federated learning (AFL) has emerged as an efficient and fair approach to incentivize data owners (DOs) to contribute to federated model training, garnering extensive interest. However, the important problem of helping data consumers (DCs) bid for DOs in competitive AFL settings remains open. Existing work simply treats that the actual cost paid by a winning DC (i.e., the bid cost) is equal to the bid price offered by that DC itself. However, this assumption is inconsistent with the widely adopted generalized second-price (GSP) auction mechanism used in AFL, including in these existing works. Under a GSP auction, the winning DC does not pay its own proposed bid price. Instead, the bid cost for the winner is determined by the second-highest bid price among all participating DCs. To address this limitation, we propose a first-of-its-kind federated cost-aware bidding strategy () to help DCs maximize their utility under GSP auction-based federated learning (FL). It enables DCs to efficiently bid for DOs in competitive AFL markets, maximizing their utility and improving the resulting FL model accuracy. We first formulate the optimal bidding function under the GSP auction setting, and then demonstrate that it depends on utility estimation and market price modeling, which are interrelated. Based on this analysis, jointly optimizes in a novel end-to-end framework, and then executes the proposed return on investment (ROI)-based method to determine the optimal bid price for each piece of the data resource. Through extensive experiments on six commonly adopted benchmark datasets, we show that outperforms eight state-of-the-art methods, beating the best baseline by 4.39%, 4.56%, 1.33%, and 5.43% on average in terms of the total amount of data obtained, number of data samples per unit cost, total utility, and FL model accuracy, respectively.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590706","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 Spatial-Temporal Predictive Transformer Network for Level-3 Autonomous Vehicle Decision-Making. 用于三级自动驾驶汽车决策的时空预测变压器网络。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3487838

Hongbo Gao, Xiao Zheng, Qingchao Liu, Lin Zhou, Chao Huang, Mingmao Hu, Chengbo Wang, Keqiang Li, Danwei Wang, Deyi Li

{"title":"A Spatial-Temporal Predictive Transformer Network for Level-3 Autonomous Vehicle Decision-Making.","authors":"Hongbo Gao, Xiao Zheng, Qingchao Liu, Lin Zhou, Chao Huang, Mingmao Hu, Chengbo Wang, Keqiang Li, Danwei Wang, Deyi Li","doi":"10.1109/TNNLS.2024.3487838","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3487838","url":null,"abstract":"This study explores the effect of takeover time (TOT) on decision-making for Level-3 autonomous vehicles (L3-AVs). The existing research on L3-AV lacks an in-depth analysis of the mechanisms affecting TOT, ignores the importance of spatial and temporal variations in features for TOT prediction, and also lacks consideration of TOT in downstream trajectory planning tasks. This study proposed an exponential smoothing transformers (ETS) former model for TOT prediction, and then, the spatial-temporal predictive transformer (ST-Preformer) was employed to forecast the trajectories of surrounding vehicles, assess lane availability, and determine lane-changing probabilities. Ultimately, these evaluations contribute to the decision-making process of L3-AVs. The findings showed that the ETSformer was able to explain more than 83% of the characteristics of the TOT distribution in the TOT prediction task, effectively reducing the absolute percentage error by 0.7%, based on which the decision-making framework was able to make safe and comfortable optimal decisions. Decision-making is closely related to driving conditions and the surrounding traffic state, and TOT has a critical impact on the safety and stability of decision-making. A comprehensive understanding the impact of TOT on decision-making can help improve the safety of autonomous driving and provide guidance for improving decision-making techniques.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590722","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 H_∞ Control of 2-D Markov Jump Roesser Systems With Optimal Disturbance Attenuation. 基于强化学习的 H∞ 控制二维马尔可夫跃迁 Roesser 系统与最佳干扰衰减。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3487760

Jiacheng Wu, Bosen Lian, Hongye Su, Yang Zhu

{"title":"Reinforcement Learning-Based H∞ Control of 2-D Markov Jump Roesser Systems With Optimal Disturbance Attenuation.","authors":"Jiacheng Wu, Bosen Lian, Hongye Su, Yang Zhu","doi":"10.1109/TNNLS.2024.3487760","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3487760","url":null,"abstract":"This article investigates model-free reinforcement learning (RL)-based H∞ control problem for discrete-time 2-D Markov jump Roesser systems ( 2 -D MJRSs) with optimal disturbance attenuation level. This is compared to existing studies on H∞ control of 2-D MJRSs with optimal disturbance attenuation levels that are off-line and use full system dynamics. We design a comprehensive model-free RL algorithm to solve optimal H∞ control policy, optimize disturbance attenuation level, and search for the initial stabilizing control policy, via online horizontal and vertical data along 2-D MJRSs trajectories. The optimal disturbance attenuation level is obtained by solving a set of linear matrix inequalities based on online measurement data. The initial stabilizing control policy is obtained via a data-driven parallel value iteration (VI) algorithm. Besides, we further certify the performance including the convergence of the RL algorithm and the asymptotic mean-square stability of the closed-loop systems. Finally, simulation results and comparisons demonstrate the effectiveness of the proposed algorithms.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590744","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

Wavelet-Based Dual-Task Network. 基于小波的双任务网络

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3486330

Fuzhi Wu, Jiasong Wu, Chen Zhang, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji

{"title":"Wavelet-Based Dual-Task Network.","authors":"Fuzhi Wu, Jiasong Wu, Chen Zhang, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji","doi":"10.1109/TNNLS.2024.3486330","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3486330","url":null,"abstract":"In image processing, wavelet transform (WT) offers multiscale image decomposition, generating a blend of low-resolution approximation images and high-resolution detail components. Drawing parallels to this concept, we view feature maps in convolutional neural networks (CNNs) as a similar mix, but uniquely within the channel domain. Inspired by multitask learning (MTL) principles, we propose a wavelet-based dual-task (WDT) framework. This novel framework employs WT in the channel domain to split a single task into two parallel tasks, thereby reforming traditional single-task CNNs into dynamic dual-task networks. Our WDT framework integrates seamlessly with various popular network architectures, enhancing their versatility and efficiency. It offers a more rational approach to resource allocation in CNNs, balancing between low-frequency and high-frequency information. Rigorous experiments on Cifar10, ImageNet, HMDB51, and UCF101 validate our approach's effectiveness. Results reveal significant improvements in the performance of traditional CNNs on classification tasks, and notably, these enhancements are achieved with fewer parameters and computations. In summary, our work presents a pioneering step toward redefining the performance and efficiency of CNN-based tasks through WT.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590763","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

Multistage Graph Convolutional Network With Spatial Attention for Multivariate Time Series Imputation. 多级图卷积网络与多变量时间序列推算的空间注意力

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-11-06 DOI: 10.1109/TNNLS.2024.3486349

Qianyi Chen, Jiannong Cao, Yu Yang, Wanyu Lin, Sumei Wang, Youwu Wang

{"title":"Multistage Graph Convolutional Network With Spatial Attention for Multivariate Time Series Imputation.","authors":"Qianyi Chen, Jiannong Cao, Yu Yang, Wanyu Lin, Sumei Wang, Youwu Wang","doi":"10.1109/TNNLS.2024.3486349","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3486349","url":null,"abstract":"In multivariate time series (MTS) analysis, data loss is a critical issue that degrades analytical model performance and impairs downstream tasks such as structural health monitoring (SHM) and traffic flow monitoring. In real-world applications, MTS is usually collected by multiple types of sensors, making MTS and correlations between variates heterogeneous. However, existing MTS imputation methods overlook the heterogeneous correlations by manipulating heterogeneous MTS as a homogeneous entity, leading to inaccurate imputation results. Besides, correlations between different data types vary due to ever-changing environmental conditions, forming dynamic correlations in MTS. How to properly learn the hidden correlation from heterogeneous MTS for accurate data imputation remains unresolved. To solve the problem, we propose a multistage graph convolutional network with spatial attention (MSA-GCN). In the first stage, we decompose heterogeneous MTS into several clusters with homogeneous data collected from identical sensor types and learn intracluster correlations. Then, we devise a GCN with spatial attention to explore dynamic intercluster correlations, which is the second stage of MSA-GCN. In the last stage, we decode the learned features from previous stages via stacked convolutional neural networks. We jointly train these three-stage models to predict the missing data in MTS. Leveraging this multistage architecture and spatial attention mechanism makes MSA-GCN effectively learn heterogeneous and dynamic correlations among MTS, resulting in superior imputation performance. We tested MSA-GCN with the monitoring data from a large-span bridge and Wetterstation weather dataset. The results affirm its superiority over baseline models, demonstrating its enhanced accuracy in reducing imputation errors across diverse datasets.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590741","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