检索结果-内蒙古大学图书馆

Graph-Tensor FISTA-Net: Edge Computing-Aided Deep Learning for Distributed Traffic Data Recovery

IEEE Transactions on network Science and Engineering 2025年

作者： Deng, Lei Liu, Xiao-Yang Zheng, Haifeng Feng, Xinxin Zhu, Ming Tsang, Danny H. K. Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou China Internet of Things Thrust Guangdong Guangzhou511400 China Columbia University Department of Electrical Engineering NY United States Chinese Academy of Sciences Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Hong Kong

In intelligent transportation systems, deep learning is a widely adopted technique for traffic data recovery. In city-wide traffic data recovery tasks, traditional centralized deep-learning-model training strategies become inapplicable because of the expensive storage costs for large-scale traffic datasets. In this scenario, edge computing emerges as a natural choice, allowing decentralized data storage and distributed training on edge nodes. However, there is still a challenge: distributed training on edge nodes suffers from high communication costs for parameter transmission. In this paper, we propose a communication-efficient Graph-Tensor Fast Iterative Shrinkage-Thresholding Algorithm-based neural network (GT-FISTA-Net) for distributed traffic data recovery. Firstly, we model the recovery task as a graph-tensor completion problem to better capture the low-rankness of traffic data. A recovery guarantee is also provided to characterize the performance bounds of the proposed scheme in terms of recovery error. Secondly, we propose a distributed graph-tensor completion algorithm and unfold it into a deep neural network called GT-FISTA-Net. GT-FISTA-Net requires small communication costs for distributed model training on edge nodes and thus it is applicable for city-wide traffic data recovery. Extensive experiments on real-world datasets show that the proposed GT-FISTA-Net can also provide excellent recovery accuracy compared with state-of-the-art distributed recovery methods. © 2013 IEEE.

关键词： distributed learning Edge computing Graph-tensor tensor completion traffic data recovery

来源：评论

学校读者我要写书评

暂无评论

Meta-path and Meta-schema Hierarchical Aggregation for Heterogeneous Graph Neural networks 10

Meta-path and Meta-schema Hierarchical Aggregation for Heter...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Gao, Pingping Guo, Kun Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

ISBN: (纸本)9798331520861

With deep learning's advancement in recent years, heterogeneous graph neural networks (HGNNs) have drawn a lot of interest. They are a group of deep learning models specifically designed for handling heterogeneous graph data, in which nodes and edges are of various types and all nodes are assumed to have either direct or indirect associations. A metaschema, which serves as a thorough and unified blueprint for the heterogeneous graph, elegantly connects varied node types to other heterogeneous nodes via multiple heterogeneous edges with rich sematincs. However, many existing methods that utilize meta-schema to mine heterogeneous information often focus on the different meta-relationships inside the schema, limiting the meta-schema to describing only the local relational semantics. To better utilize meta-schema for efficiently integrating different heterogeneous information, we organize them into a hierarchical structure(i.e., hierarchical meta-schema), with all types of nodes distributed across different layers. The layers are interconnected through heterogeneous relationships. The target type is placed at the final layer and others are arranged hierarchically in the front according to the heterogeneous relationships defined in the meta-schema. During information aggregation, according to the hierarchical meta-schema, the information of each layer is gradually aggregated to the target type on the final layer from far to near via the attention mechanism. Moreover, metapaths regularly begin and end with the same type and help to define complex structures and semantic. Therefore, we also consider the semantic information of neighbors based on metapaths within the proposed hierarchical meta-schema to enhance the complex semantics among nodes of the same-type that may be lacking in the meta-schema. Finally, we proposed a meta-path and meta-schema hierarchical aggregation for heterogeneous graph neural network model, named HGNN-MMHA. And we may allow the meta-schema to not

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

MOAL: Multi-view Out-of-distribution Awareness Learning

引用

Neural networks 2025年 190卷 107581页

作者： Xuzheng Wang Zihan Fang Shide Du Wenzhong Guo Shiping Wang College of Computer and Data Science Fuzhou University Fuzhou 350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou 350108 China

Multi-view learning integrates data from multiple sources to enhance task performance by improving data quality. However, existing approaches primarily focus on intra-distribution data learning and consequently fail to identify out-of-distribution instances effectively. This paper introduces a method to improve the perception of out-of-distribution data in multi-view situations. First, we employ multi-view consistency and complementarity principles to develop sub-view complementarity representation learning and multi-view consistency fusion layers, thereby enhancing the model’s perception ability to typical intra-distribution features. Additionally, we introduce a specialized multi-view training loss and an agent mechanism tailored for out-of-distribution scenarios, facilitating the ability to differentiate between known and new or anomalous instances effectively. The proposed approach enhances the recognition of out-of-distribution data by improving intra-distribution feature representations and minimizing the entropy associated with out-of-distribution instances. Experimental results on multiple multi-view datasets simulating out-of-distribution scenarios confirm the effectiveness of MOLA, which consistently outperforms all baselines with average accuracy improvements of over 5%.

关键词： Anomaly detection Deep learning Multi-view learning Out-of-distribution learning

来源：评论

学校读者我要写书评

暂无评论

Relative influence maximization in competitive social networks

引用

Science China(information Sciences) 2017年第10期60卷 252-254页

作者： Dingda YANG Xiangwen LIAO Huawei SHEN Xueqi CHENG Guolong CHEN College of Physics and Information Engineering Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Institute of Computing Technology Chinese Academy of Sciences

In many realistic scenarios,such as political election and viral marketing,two opposite opinions,i.e.,positive opinion and negative opinion,spread simultaneously in the same social networks[1,2].Consequently,to achiev... 详细信息

关键词： net RIM Relative influence maximization in competitive social networks Figure

来源：评论

学校读者我要写书评

暂无评论

A Chinese multimodal depression dataset with personality labeling for older adults with underlying medical conditions

引用

IEEE Transactions on Affective Computing 2025年

作者： Zhao, Yuliang Zhang, Huawei Li, Jian Song, Siyang Lian, Chao Liu, Yinghao Wang, Yulin Fu, Changzeng School of Information Science and Engineering Northeastern University Shenyang110819 China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinhuangdao066004 China Northeastern University SSTC NEU Hebei Key Laboratory of Marine Perception Network and Data Processing Hebei Qinhuangdao066004 China Osaka University Japan University of Cambridge AFAR Lab Department of Computer Science and Technology CambridgeCB3 0FT United Kingdom First Hospital of Qinhuangdao Qinhuangdao066004 China

Elderly individuals often suffer from underlying medical conditions, resulting in a significant decline in quality of life and a heightened susceptibility to depression. Presently, AI screening tools based on behavioral indicators offer an objective and effective approach to diagnosing depression. However, current AI depression screening tools are primarily tailored to adolescents and adults, exhibiting shortcomings in their applicability and accuracy for elderly individuals with underlying medical conditions. To address the above issues, firstly, this paper constructs a depression dataset for elderly people with underlying diseases by using semi-structured interviews. Secondly, based on cognitive science insights, it is recognized that personality factors significantly influence behavioral expressions and also determine the attitudes of elderly individuals toward current life circumstances/health issues. Therefore, besides annotating depression severity, the Big Five-10 personality scale was utilized to annotate participant personalities. Finally, a late fusion-based multi-task learning framework was proposed, and the effects of introducing gait information and personality annotation on the performance of depression assessment were investigated. The experimental findings affirm the importance of integrating gait information and personality assessment in improving depression detection effectiveness. This study provides valuable foundational resources, as well as beneficial references and insights, for the research on depression in the elderly. © 2010-2012 IEEE.

关键词： Depression Multimodal dataset Older adults Personality Underlying diseases

来源：评论

学校读者我要写书评

暂无评论

Output feedback robust model predictive control with unmeasurable model parameters and bounded disturbance

引用

Chinese Journal of Chemical Engineering 2016年第10期24卷 1431-1441页

作者： Baocang Ding Hongguang Pan Ministry of Education Key Lab For Intelligent Networks and Network Security Department of AutomationSchool of Electronic and Information EngineeringXi'an Jiaotong University

The output feedback model predictive control(MPC),for a linear parameter varying(LPV) process system including unmeasurable model parameters and disturbance(all lying in known polytopes),is *** previously developed tools,including the norm-bounding technique for relaxing the disturbance-related constraint handling,the dynamic output feedback law,the notion of quadratic boundedness for specifying the closed-loop stability,and the ellipsoidal state estimation error bound for guaranteeing the recursive feasibility,are merged in the control *** previous approaches are shown to be the special *** example of continuous stirred tank reactor(CSTR) is given to show the effectiveness of the proposed approaches.

关键词： Model predictive control Process systems Stability Recursive feasibility Uncertainty Norm-bounding technique

来源：评论

学校读者我要写书评

暂无评论

DualGOFiller: A Dual-Channel Graph Neural network with Contrastive Learning for Enhancing Function Prediction in Partially Annotated Proteins 29th

DualGOFiller: A Dual-Channel Graph Neural Network with Cont...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Wang, Shaojun Liu, Hancheng Zhai, Weiqi Zhu, Shanfeng Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Ministry of Education Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing and Shanghai Institute of Artificial Intelligence Algorithm Fudan University Shanghai200433 China Zhangjiang Fudan International Innovation Center Shanghai200433 China

ISBN: (纸本)9783031902512

Protein function prediction remains a critical and challenging task in the field of bioinformatics. Despite various existing computational methods, most focus on predicting functions for novel proteins, often overlooking those with incomplete annotations. Predicting missing Gene Ontology (GO) terms for these partially annotated proteins is also important for gaining a comprehensive understanding of their biological roles. To address this gap, we introduce DualGOFiller, a dual-channel graph neural network (GNN) model, which is a novel method specifically focused on predicting missing GO terms for partially annotated proteins. DualGOFiller integrates heterogeneous (protein-GO bipartite graph) and homogeneous (protein-protein interaction network and GO directed acyclic graph) network information, enriched with attribute data from protein sequences and GO term descriptions. It further employs graph contrastive learning (GCL) to strengthen the alignment across different views. Experiments demonstrate the superiority of DualGOFiller over state-of-the-art methods, including traditional recommendation system approaches and several protein function prediction methods. The ablation study further confirms the significant contributions of key component in DualGOFiller for boosting predictive performance. The source code is available at https://***/Zhulab-Fudan/DualGOFiller. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Robust MVDR beamforming based on covariance matrix reconstruction

引用

Science China(information Sciences) 2013年第4期56卷 28-39页

作者： MU PengCheng LI Dan YIN QinYe GUO Wei Ministry of Education Key Lab for Intelligent Networks and Network Security School of Electronics and Information EngineeringXi'an Jiaotong University

The minimum variance distortionless response(MVDR) beamformer has better resolution and much better interference rejection capability than the data-independent ***,the former is more sensitive to errors,such as the steering vector errors caused by direction of arrival mismatch,imprecise array calibration or any other possible factors,especially in the case of high signal-to-noise ratio(SNR).A new robust MVDR beamformer against the general steering vector errors is proposed in this *** method is based on the reconstruction of the covariance matrix which aims to reduce the power of the signal of interest(SOI) in the covariance *** eigenanalysis is used in the process of removing the SOI component and modifying the residual covariance *** results show that the proposed method has excellent signal-to-interference-plus-noise ratio(SINR) performance under the mismatch condition.

关键词： MVDR beamforming steering vector error eigenanalysis covariance matrix reconstruction signal-to-interference-plus-noise ratio

来源：评论

学校读者我要写书评

暂无评论

An improved method of multi-strategy ontology mapping

An improved method of multi-strategy ontology mapping

引用

2010 International Conference on Computer Modeling and Simulation, ICCMS 2010

作者： Lv, Gang Wang, Kunlun Liu, Dengsheng Key Laboratory of Network and Intelligent Information Processing Hefei University Hefei China

ISBN: (纸本)9780769539416

In this paper, an improved multi-strategy ontology mapping method is proposed to improve the accuracy of the ontology mapping. The structural characteristics of ontology and the effect of instance mapping upon the similarity of ontology are considered generally. Furthermore, our approach represents and measures the structure of the conceptual nodes through the design of a "code" method, and judges the similarity of the nodes via utilizing the similarity of their ancestor nodes within the influential domain. A 1:1 mapping method is also put forward when operating the selection of initial candidates. In this paper, the tools of WordNet, Jena, protégé, etc. are employed. Finally, the experimental results show the promise of our approach and improve the recall and precision of the retrieve. © 2010 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Self-selecting sub-secret keys sharing scheme: Based on polynomials over elliptic curve

Self-selecting sub-secret keys sharing scheme: Based on poly...

引用

5th International Conference on information Assurance and Security, IAS 2009

作者： Caimei, Wang Zhengmao, Li Hefei University Key Laboratory of Network and Intelligent Information Processing Hefei China

ISBN: (纸本)9780769537443

Traditional secret sharing scheme generally exists two shortages:each participant's sub-secret key is distributed by the certification center;the sub-secret keys can not be repeated to use. Both shortages brought to the practical application a lot of inconvenience, and n sub-secret keys can only be used to share a master key in terms of resources is a waste. This article based on the reference [6] proposed a scheme with sub-secret keys be selected by participants, and those sub-secret keys can be reused. The scheme based on the security of elliptic curve discrete most of the difficult nature is more practical than the reference [6], and the realization of the process can solve the problem about the authenticity of the sub-secret keys. © 2009 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：