Neurocomputing最新文献_第6页

Multi-attribute balanced dataset generation framework AutoSyn and KinFace Channel-Spatial Feature Extractor for kinship recognition 用于亲属关系识别的多属性均衡数据集生成框架 AutoSyn 和 KinFace 通道空间特征提取器

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-20 DOI: 10.1016/j.neucom.2024.128750

Jia-Xuan Jiang , Hongsheng Jing , Ling Zhou , Yuee Li , Zhong Wang

{"title":"Multi-attribute balanced dataset generation framework AutoSyn and KinFace Channel-Spatial Feature Extractor for kinship recognition","authors":"Jia-Xuan Jiang , Hongsheng Jing , Ling Zhou , Yuee Li , Zhong Wang","doi":"10.1016/j.neucom.2024.128750","DOIUrl":"10.1016/j.neucom.2024.128750","url":null,"abstract":"<div><div>In the field of kinship verification, facial recognition technology is becoming increasingly vital due to privacy concerns, ethical disputes, and the high costs associated with DNA testing. We have developed a novel method, the AutoSyn framework, to synthesize facial images and enhance kinship image datasets, effectively addressing the challenges of scale and quality in existing datasets. By employing a strategy that mixes ages and genders in the synthesized images, we minimize the impact of these factors on kinship recognition tasks. We have enhanced the original KinFaceW-I dataset by integrating ten distinct styles, including diverse combinations of gender, ethnicity, and age. This enrichment significantly improves both the quality and quantity of the images. Furthermore, this paper introduces an efficient feature extractor for kinship tasks, KinFace-CSFE, within a siamese neural network framework. This model not only utilizes meticulously designed channel feature extraction but also incorporates mixed kernel size spatial attention mechanisms to better focus on local features. We have also integrated YOCO data augmentation techniques to simulate complex imaging conditions, enhancing the model’s robustness and accuracy. The effectiveness of these innovations has been validated through experiments on the KinFaceW-I, KinFaceW-II, and synthesized Syn-KinFaceW-I datasets, achieving accuracy rates of 82.7%, 94.1%, and 83.2% respectively. These results significantly surpass both traditional models and current advanced models.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

H3NI: Non-target-specific node injection attacks on hypergraph neural networks via genetic algorithm H3NI：通过遗传算法对超图谱神经网络进行非特定目标节点注入攻击

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128746

Heyuan Shi , Binqi Zeng , Ruishi Yu , Yulin Yang , Zijian Zouxia , Chao Hu , Ronghua Shi

{"title":"H3NI: Non-target-specific node injection attacks on hypergraph neural networks via genetic algorithm","authors":"Heyuan Shi , Binqi Zeng , Ruishi Yu , Yulin Yang , Zijian Zouxia , Chao Hu , Ronghua Shi","doi":"10.1016/j.neucom.2024.128746","DOIUrl":"10.1016/j.neucom.2024.128746","url":null,"abstract":"<div><div>Node injection attack is widely used in graph neural networks (GNNs) attacks, which misleads GNNs by injecting nodes. Though hypergraph neural networks (HNNs) are an extension of GNNs, node injection attacks have not yet been studied in HNNs. Since each edge of a hypergraph can connect more than two nodes, existing node injection methods designed for GNNs cannot effectively select the hyperedges connected to the injected nodes when applied to hypergraphs. In this paper, we propose a <u>H</u>ypergraph <u>N</u>eural <u>N</u>etwork <u>N</u>ode <u>I</u>njection attack method called H3NI, which utilizes a genetic algorithm and a predefined budget model to implement the first black-box node injection framework designed for HNNs attacks. We conducted experiments on the datasets of Cora co-authorship and co-citation. Experimental results show the effectiveness and superior performance of H3NI in attacking HNNs, which reduces the model accuracy by 18%–20% within 5% of the total injected nodes and achieves a 2-4X improvement compared to existing gradient-based node injection methods.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

3D skeleton aware driver behavior recognition framework for autonomous driving system 用于自动驾驶系统的三维骨骼感知驾驶员行为识别框架

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128743

Rongtian Huo , Junkang Chen , Ye Zhang , Qing Gao

{"title":"3D skeleton aware driver behavior recognition framework for autonomous driving system","authors":"Rongtian Huo , Junkang Chen , Ye Zhang , Qing Gao","doi":"10.1016/j.neucom.2024.128743","DOIUrl":"10.1016/j.neucom.2024.128743","url":null,"abstract":"<div><div>The recognition of the driver’s behaviors inside an autonomous vehicle can effectively address emergency handling in autonomous driving and is crucial for ensuring the driver’s safety. Driver behavior recognition is a challenging task due to factors such as variations, diversities, complexities, and strong interferences in behaviors. In this paper, to realize the application in the autonomous driving scenes, a novel 3D skeleton aware behavior recognition framework is proposed to recognize various driver behaviors in autonomous driving systems. First, a 3D human pose estimation network (Pose-GTFNet) with temporal Transformer and spatial graph convolutional network (GCN) is designed to infer 3D human poses from 2D pose sequences. Second, based on the obtained 3D human pose sequences, a behavior recognition network (Beh-MSFNet) with multi-skeleton feature fusion is designed to recognize driver behaviors. In the experiments, the Pose-GTFNet and Beh-MSFNet can get the best performance compared with most state-of-the-art (SOTA) methods on the Human3.6M human pose dataset, JHMDB and SHREC action recognition dataset, respectively. In addition, the proposed driver behavior recognition framework can achieve SOTA performance on the Drive&Act and Driver-Skeleton driver behavior datasets.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 accurate neighborhood- and self-information for higher-order relation prediction in Heterogeneous Information Networks 为异构信息网络中的高阶关系预测学习准确的邻接信息和自身信息

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128739

Jie Li , Xuan Guo , Pengfei Jiao , Wenjun Wang

{"title":"Learning accurate neighborhood- and self-information for higher-order relation prediction in Heterogeneous Information Networks","authors":"Jie Li , Xuan Guo , Pengfei Jiao , Wenjun Wang","doi":"10.1016/j.neucom.2024.128739","DOIUrl":"10.1016/j.neucom.2024.128739","url":null,"abstract":"<div><div>Heterogeneous Information Networks (HINs) are commonly employed to model complex real-world scenarios with diverse node and edge types. However, due to constraints in data collection and processing, constructed networks often lack certain relations. Consequently, various methods have emerged, particularly recently, leveraging heterogeneous graph neural networks (HGNNs) to predict missing relations. Nevertheless, these methods primarily focus on pairwise relations between two nodes. Real-world interactions, however, often involve multiple nodes and diverse types, extending beyond simple pairwise relations. For instance, academic collaboration networks may entail interactions among authors, papers, and conferences simultaneously. Despite their prevalence, higher-order relations are often overlooked. While HGNNs are effective at learning network structures, they may suffer from over-smoothing, resulting in similar representations for nodes and their neighbors. The learned inaccurate proximity among nodes impedes the discernment of higher-order relations. Furthermore, observed edges among a target group of nodes can provide valuable evidence for predicting higher-order relations. To address these challenges, we propose a novel model called Accurate Neighborhood- and Self-information Enhanced Heterogeneous Graph Neural Network (ANSE-HGN). Building upon HGNNs to encode network structure and attributes, we introduce a relation-based neighborhood encoder to capture information within multi-hop neighborhoods in heterogeneous higher-order relations. This enables the calculation of accurate proximity among target groups of nodes, thereby enhancing prediction accuracy. Additionally, we leverage self-information from observed higher-order relations as an auxiliary loss to reinforce the learning process. Extensive experiments on four real-world datasets demonstrate the superiority of our proposed method in higher-order relation prediction tasks.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Advances in vehicle re-identification techniques: A survey 车辆重新识别技术的进展：调查

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128745

Xiaoying Yi, Qi Wang, Qi Liu, Yikang Rui, Bin Ran

{"title":"Advances in vehicle re-identification techniques: A survey","authors":"Xiaoying Yi, Qi Wang, Qi Liu, Yikang Rui, Bin Ran","doi":"10.1016/j.neucom.2024.128745","DOIUrl":"10.1016/j.neucom.2024.128745","url":null,"abstract":"<div><div>The development of vehicle re-identification technology has significantly enhanced the operational efficiency of intelligent transportation systems and smart cities, attributed to the advancement of artificial intelligence technologies such as deep learning and transformer models. By accurately tracking and identifying the same vehicle under different cameras, the technology not only greatly enhances the ability of urban safety monitoring, traffic management and accident investigation, but also provides powerful technical support for the development of intelligent transportation. This paper explores the shift from traditional to deep learning approaches in vehicle re-identification, highlighting the rise of Transformer models. We assess both non-visual and vision-based re-identification technologies, with a special focus on the deep feature-based methods across supervised, unsupervised, and semi-supervised learning. And we summarize the performance of supervised and unsupervised methods on the VeRi-776 and VehicleID datasets. Finally, this paper outlines six directions for the future development of vehicle Re-ID technology, highlighting its potential applications in various areas such as smart city traffic management.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Practical consensus of T-S fuzzy positive multi-agent systems using linear programming 利用线性规划实现 T-S 模糊正多代理系统的实用共识

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128725

Junfeng Zhang , Chongxiang Yu , Baochen Zhang , Weidong Zhang

{"title":"Practical consensus of T-S fuzzy positive multi-agent systems using linear programming","authors":"Junfeng Zhang , Chongxiang Yu , Baochen Zhang , Weidong Zhang","doi":"10.1016/j.neucom.2024.128725","DOIUrl":"10.1016/j.neucom.2024.128725","url":null,"abstract":"<div><div>This paper presents the practical consensus of T-S fuzzy positive multi-agent systems with interval type-1 and type-2 fuzzy sets using observer-based control protocols. A fuzzy positive observer is first constructed for the systems. An observer-based fuzzy control protocol is designed, where an additional constant term is introduced. Some linear programming conditions are established to achieve the positivity of the original system and its observer. Then, the practical consensus of the original system is transformed into the stability of a dynamic system, where a set of new variables is defined by combining the constant term and the states of the agents. In the first step, the positivity of the new variables is guaranteed. In the second step, the stability of the dynamic system consisting new variables is addressed by using a fuzzy copositive Lyapunov function. The gain matrices of observer and control protocols are formulated based on a matrix decomposition approach. All positive and consensus conditions are described via linear programming. Finally, two examples are provided to verify the validity of the obtained results.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Threshold-optimized and features-fused semi-supervised domain adaptation method for rotating machinery fault diagnosis 用于旋转机械故障诊断的阈值优化和特征融合半监督域适应方法

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128734

Shenquan Wang , Fangyuan Zhao , Chao Cheng , Hongtian Chen , Yulian Jiang

{"title":"Threshold-optimized and features-fused semi-supervised domain adaptation method for rotating machinery fault diagnosis","authors":"Shenquan Wang , Fangyuan Zhao , Chao Cheng , Hongtian Chen , Yulian Jiang","doi":"10.1016/j.neucom.2024.128734","DOIUrl":"10.1016/j.neucom.2024.128734","url":null,"abstract":"<div><div>In the field of intelligent fault diagnosis, domain adaptation (DA) technology achieves significant breakthroughs, particularly in reducing reliance on large volumes of labeled samples. Despite these advancements, challenges persist when unlabeled data do not accurately represent actual application scenarios. Additionally, the impact of pseudo-labels on conditional domain adaptation raises concerns. To overcome the above challenges, a novel DA approach based on chaos sparrow search algorithm (CSSOA) optimized threshold parameters and feature fusion deep belief network (DBN) is proposed, named CSS-DADBN. Firstly, this method, by integrating pseudo-label updating with semi-supervised domain adaptation (SSDA) and employing confidence and entropy threshold parameters as corrective rules for pseudo-label filtering, along with the introduction of iterative conditions as an additional selection criterion, effectively alleviates the aforementioned issues. Furthermore, combining the feature extraction capabilities of DBN with a domain feature fusion strategy significantly enhances cross-domain feature learning, thereby substantially improving diagnostic accuracy. Ultimately, to validate the effectiveness and practicality of the CSS-DADBN method, a series of experiments conducted on the PT700 and Case Western Reserve University (CWRU) rolling bearing test platform clearly demonstrate its utility and efficiency in intelligent fault diagnosis.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Fixed-time output synchronization of multilayered coupled networks with quaternion: An exponential quantized scheme 用四元数实现多层耦合网络的固定时间输出同步：指数量化方案

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128742

Kailong Xiong , Cheng Hu

{"title":"Fixed-time output synchronization of multilayered coupled networks with quaternion: An exponential quantized scheme","authors":"Kailong Xiong , Cheng Hu","doi":"10.1016/j.neucom.2024.128742","DOIUrl":"10.1016/j.neucom.2024.128742","url":null,"abstract":"<div><div>In this article, the output synchronization of multi-layer coupled quaternion-valued neural networks with or without target state is discussed in fixed or prescribed time by developing a nonseparation approach and applying quantitative control. Firstly, considering the inaccessibility of network states and the diversity of individual functions, a type of quaternion-valued coupled networks with output coupling and multi-layer structure is introduced. In terms of fixed-time or preassigned-time controller design, an exponential quantization protocol without linear feedback is directly designed in the field of quaternion for the addressed networks with the presence of synchronous target, and a distributed quaternion-valued exponential control scheme with finite control gains is developed for the multilayered networks with the absence of synchronous target. In the process of convergence analysis, without utilizing the traditional separation method, some different forms of Lyapunov functions are directly constructed and the technique of Taylor expansion is used to derive the output synchronization criteria and the estimate of convergence time. One specific example is shown at last to verify the developed results.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Cross-view action recognition understanding from exocentric to egocentric perspective 从外中心视角到自我中心视角的跨视角动作识别理解

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128731

Thanh-Dat Truong, Khoa Luu

{"title":"Cross-view action recognition understanding from exocentric to egocentric perspective","authors":"Thanh-Dat Truong, Khoa Luu","doi":"10.1016/j.neucom.2024.128731","DOIUrl":"10.1016/j.neucom.2024.128731","url":null,"abstract":"<div><div>Understanding action recognition in egocentric videos has emerged as a vital research topic with numerous practical applications. With the limitation in the scale of egocentric data collection, learning robust deep learning-based action recognition models remains difficult. Transferring knowledge learned from the large-scale exocentric data to the egocentric data is challenging due to the difference in videos across views. Our work introduces a novel cross-view learning approach to action recognition (CVAR) that effectively transfers knowledge from the exocentric to the selfish view. First, we present a novel geometric-based constraint into the self-attention mechanism in Transformer based on analyzing the camera positions between two views. Then, we propose a new cross-view self-attention loss learned on unpaired cross-view data to enforce the self-attention mechanism learning to transfer knowledge across views. Finally, to further improve the performance of our cross-view learning approach, we present the metrics to measure the correlations in videos and attention maps effectively. Experimental results on standard egocentric action recognition benchmarks, i.e., Charades-Ego, EPIC-Kitchens-55, and EPIC-Kitchens-100, have shown our approach’s effectiveness and state-of-the-art performance.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Integrating reinforcement learning and supervisory control theory for optimal directed control of discrete-event systems 整合强化学习和监督控制理论，实现离散事件系统的最优定向控制

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-19 DOI: 10.1016/j.neucom.2024.128720

Yuhong Hu, Deguang Wang, Ming Yang, Jiahan He

引用次数: 0