检索结果-内蒙古大学图书馆

EPM: Evolutionary Perception Method for Anomaly Detection in Noisy Dynamic Graphs

IEEE Transactions on Knowledge and Data Engineering 2025年

作者： Wang, Huan Chen, Junyang Wu, Yirui Leung, Victor C. M. Wang, Di King Abdullah University of Science and Technology Division of Computer Electrical and Mathematical Sciences and Engineering Saudi Arabia Huazhong Agricultural University College of Informatics China Shenzhen University College of Computer Science and Software Engineering China Hohai University College of Computer and Information China

With the rapid expansion of interactions across various domains such as knowledge graphs and social networks, anomaly detection in dynamic graphs has become increasingly critical for mitigating potential risks. However, existing anomaly detection methods often assume noise-free dynamic graphs, overlooking the prevalence of noisy dynamic graphs in real-world applications. Specifically, noisy dynamic graphs affected by structural noises-such as spurious and missing nodes and edges-struggle to consistently provide reliable structural evidence for anomaly detection. To tackle this challenge, we propose an Evolutionary Perception Method (EPM) for identifying anomalous nodes in noisy dynamic graphs by resisting the interference of structural noises. EPM primarily consists of two components: a dynamic fitter and a filtering reviser. The dynamic fitter characterizes the interaction dynamics of nodes that removes and generates links at each period as a multiple superposition state, utilizing various link prediction algorithms to fit evolutionary mechanisms. Additionally, the filtering reviser designs evolutional entropies to quantify the evolutional uncertainty in multiple superposition states, further designing the Kalman filter to optimize these entropies. Extensive experiments show that the proposed EPM method surpasses state-of-the-art approaches in detecting anomalous nodes in noisy dynamic graphs. © 1989-2012 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Temporal-guided Mixture-of-Experts for Zero-Shot Video Question Answering

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Qin, Yixin Zhao, Lei Gao, Lianli Zhang, Haonan Zeng, Pengpeng Shen, Heng Tao University of Electronic Science and Technology of China Center for Future Media School of Computer Science and Engineering Chengdu611731 China Sichuan Artificial Intelligence Research Institute Yibin644000 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China Tongji University Department of Information Engineering and Computer Science China

Video Question Answering (VideoQA) is a challenging task in the vision-language field. Due to the time-consuming and labor-intensive labeling process of the question-answer pairs, fully supervised methods are no longer suitable for the current increasing demand for data. This has led to the rise of zero-shot VideoQA, and some works propose to adapt large language models (LLMs) to assist zero-shot learning. Despite recent progress, the inadequacy of LLMs in comprehending temporal information in videos and the neglect of temporal differences, e.g., the different dynamic changes between scenes or objects, remain insufficiently addressed by existing attempts in zero-shot VideoQA. In light of these challenges, a novel Temporal-guided Mixture-of-Experts Network (T-MoENet) for zero-shot video question answering is proposed in this paper. Specifically, we apply a temporal module to imbue language models with the capacity to perceive temporal information. Then a temporal-guided mixture-of-experts module is proposed to further learn the temporal differences presented in different videos. It enables the model to effectively improve the capacity of generalization. Our proposed method achieves state-of-the-art performance on multiple zero-shot VideoQA benchmarks, notably improving accuracy by 5.6% on TGIF-FrameQA and 2.3% on MSRVTT-QA while remaining competitive with other methods in the fully supervised setting. The codes and models developed in this study will be made publicly available at https://***/qyx1121/T-MoENet. © 1991-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Category-Driven Contrastive Recovery Network for Double Incomplete Multi-view Multi-label Classification

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Yiming Li, Qun Chang, Dongxia Wen, Jie Xiao, Fu Zhao, Yao Nanjing University of Posts and Telecommunications School of Computer Science Nanjing China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Harbin Institute of Technology Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen China

In the field of multi-view multi-label learning, the challenges of incomplete views and missing labels are prevalent due to the complexity of manual labeling and data acquisition errors. These challenges significantly reduce the quality of latent representations and hinder prediction by multi-label classification. To address this issue, we propose a novel Category-driven Semi-supervised Contrastive Recovery (CSCR) framework in this study. Our framework aims to fully integrate existing label information into incomplete representation learning and classification. Specifically, to address the limitations posed by incomplete views and labels, we construct a label coincidence matrix based on existing labels, which serves as a similarity matrix in subsequent semi-supervised contrastive learning and multi-view classification. By leveraging this matrix, we design a semi-supervised multi-view contrastive learning module, which constructs sample pairs on the basis of inter-view correspondences and label similarity. It learns discriminative latent representations without the need for data augmentation. A weighted multi-label classification module is subsequently employed to integrate the predictions from each view to obtain the final classification result. Experimental evaluations on five challenging datasets demonstrate the superiority of our model over existing state-of-the-art methods. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Smart Facial Features for Real-Time Motorists Sleepiness Prediction and Alerting System Using Hybrid Deep Convolutional Neural Network in computer Vision 1st

A Novel Smart Facial Features for Real-Time Motorists Sleepi...

引用

1st International Conference on Innovation and Emerging Trends in Computing and information Technologies, IETCIT 2024

作者： Senthil, G.A. Prabha, R. Sridevi, S. Deepa, R. Shimona, S. Department of Information Technology Agni College of Technology Chennai India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Engineering Agni College of Technology Chennai India

ISBN: (纸本)9783031808388

Motorists Sleepiness prediction is a process of detecting when an Operator is experiencing Sleepiness or fatigue while driving a vehicle. This is an important safety feature, as Sleepy driving can lead to accidents and injuries. There are several methods used to predict Operator Sleepiness, including physiological monitoring, behavioural monitoring, and hybrid methods. Physiological monitoring methods like CNN involve measuring the Operator's physiological signals, such as image or video frame processing from a camera. These frames can provide information about the Operator's level of alertness and can be used to detect Sleepiness. Behavioural monitoring methods that are DCNN on the other hand, involve observing the Operator's behaviour, such as comparing the frames with the processed dataset. This information is mainly used to detect Sleepiness. Hybrid methods combine physiological and behavioural monitoring methods of CNN and DCNN and added to the fuzzy logic algorithm makes an HDCNN (Hybrid Deep Convolutional Neural Network) to provide a more comprehensive assessment of the Operator's level of Sleepiness and improves the accuracy. This article explains techniques to spot the lips and eyes in a video taken during a research project by the Indian Institute of Road Safety (IIROS). A footage of the transition from awake to fatigued to drowsy will be captured using the digital camera. The Proposed algorithm's function is to locate the face recognized in a captured video image. The face region is used mostly for its ability to act independently. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Graph-aware Reasoning and Bidirectional Selection for Vision-Language Navigation

Exploring Graph-aware Reasoning and Bidirectional Selection ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dongming Zhou Jinsheng Deng Zhengbin Pang Wei Li School of Computer Science National University of Defense Technology Changsha China College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha China School of Computer and Electronic Information Guangxi University Nanning China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Inspired by structured state space models and graph neural network modeling, we proposes a novel graph-aware reasoning (GAR) model to effectively solve the problem between memory utilization efficiency and reasoning navigation. First, we introduce graph networks into the navigation framework to enhance the model modeling ability for long sequence dependencies. It is integration graph neural networks into the state space to ensures that the agent can accurately find topological paths based on instructions and environmental interactions. Then, we design a bidirectional selective state space model to enhance the agent-aware of spatial information. When without relying on the attention network, we capture the context information in the image through position embedding. Finally, we fuison the features in the bidirectional state space and effectively compresses and improves the fine-grained image features by a residual connection methods. Our experimental results on R2R and REVERIE datasets show that GAR reduces GPU memory usage by 4.45% compared with the DUET baseline model.

关键词： Visualization Navigation Computational modeling Memory management Signal processing Transformers Cognition Graph neural networks Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Accelerating Medical Knowledge Discovery Through Automated Knowledge Graph Generation and Enrichment 6th

Accelerating Medical Knowledge Discovery Through Automated K...

引用

6th International Conference on Knowledge Graphs and Semantic Web, KGSWC 2024

作者： Khalid, Mutahira Rahman, Raihana Abbas, Asim Kumari, Sushama Wajahat, Iram Bukhari, Syed Ahmad Chan TIB - Leibniz Information Centre for Science and Technology Lower Saxony Hannover30165 Germany Department of Statistics Harvard University CambridgeMA United States School of Computer Science University of Birmingham Edgbaston Birmingham United Kingdom Routing and Planning Amazon BellevueWA United States Institute for Biotechnology St. John’s University New York United States Division of Computer Science Mathematics and Science St. John’s University New York United States

ISBN: (纸本)9783031812200

Knowledge graphs (KGs) serve as powerful tools for organizing and representing structured knowledge. While their utility is widely recognized, challenges persist in their automation and completeness. Despite efforts in automation and the utilization of expert-created ontologies, gaps in connectivity remain prevalent within KGs. In response to these challenges, we propose an innovative approach termed "Medical Knowledge Graph Automation (M-KGA)". M-KGA leverages user-provided medical concepts and enriches them semantically using BioPortal ontologies, thereby enhancing the completeness of knowledge graphs through the integration of pre-trained embeddings. Our approach introduces two distinct methodologies for uncovering hidden connections within the knowledge graph: a cluster-based approach and a node-based approach. Through rigorous testing involving 300 frequently occurring medical concepts in Electronic Health Records (EHRs), our M-KGA framework demonstrates promising results obtained 50% accuracy, 57% F1-score, 50% recall and 65% precision on a cluster base approach. Similarly, we achieve 85% accuracy, 87% F1-score, 89% recall and 88% precision on a node base approach indicating its potential to address the limitations of existing knowledge graph automation techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Distributed Fixed-Time Algorithms for Time-Varying Constrained Optimization Problems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： He, Xing Li, Yue Zhang, Meng Huang, Tingwen Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

In this paper, the distributed form of the zeroing neural network for solving time-varying optimal problems is put forward. Compared with traditional centralized algorithms, distributed algorithms possess better privacy and scalability. This paper initially proposes a centralized time-varying optimisation algorithm with fixed-time convergence and certain robustness, which is based on the integration-enhanced zeroing neural network. Subsequently, the algorithm is enhanced, and two distributed algorithms are designed separately. Both of these two algorithms have a fixed convergence time and certain robustness. Additionally, this paper utilizes the penalty function approach to handle time-varying optimization problems with inequality constraints, thereby making the algorithm more widely applicable. The effectiveness of the algorithm is verified through several numerical examples, and the applicability of the algorithm is demonstrated by solving the package-level state-of-charge balancing problem. © 2020 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

COMAT: A Cybersecurity Ontology based on MITRE ATT&CK

引用

IEEE Network 2025年

作者： Huang, Yi-Ting Vaitheeshwari, R. Chen, Meng Chang Lin, Ying-Dar Hwang, Ren-Hung Lin, Po-Ching Lai, Yuan-Cheng Wu, Eric Hsiao-Kuang Liao, Zi-Jie Chen, C.K. National Taiwan University of Science and Technology Department of Electrical Engineering Taipei Taiwan National Central University Department of Computer Science and Information Engineering Taoyuan Taiwan Academia Sinica Institute of Information Science Taipei Taiwan NationalYang Ming Chiao Tung University Department of Computer Science Hsinchu Taiwan National Yang Ming Chiao Tung University College of Artificial Intelligence Hsinchu Taiwan National Chung Cheng University Department of Computer Science and Information Engineering Chiayi Taiwan National Taiwan University of Science and Technology Department of Information Management Taipei Taiwan CyCraft Technology Research Division New Taipei City Taiwan

This article presents COMAT, a cybersecurity ontology based on the MITRE ATT&CK framework for enhanced knowledge access and analysis. COMAT derives inference paths to identify adversarial techniques and includes forward- and backward-query modules for efficient, comprehensive Cyber Threat Intelligence (CTI) analysis. © 1986-2012 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Orthogonal Multiple Access Based Multi-Objective Optimization in Emergency Task Offloading

Non-Orthogonal Multiple Access Based Multi-Objective Optimiz...

引用

IEEE Conference on Wireless Communications and Networking

作者： Caijuan Chen Chaofeng Zhang Gaolei Li Yuchen Liu The Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan Advanced Institute of Industrial Technology Tokyo Japan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science NC State University North Carolina US

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The escalating frequency of geological disasters, local conflicts, and public health crises necessitates robust emergency communication systems within Internet of Things (IoT) frameworks to ensure public safety. Employing Power-Domain NOMA (PD-NOMA) and Successive Interference Cancellation (SIC) enables effective multi-device communication that is crucial for emergency responses. However, the practical implementation of NOMA technologies in emergency scenarios is hindered by existing resource constraints and the requirement of prioritizing critical emergency information. To address these limitations, we propose a multi-objective optimization-based NOMA framework to maximize network throughput while ensuring quality of service (QoS) and energy efficiency. This framework incorporates a novel communication grouping algorithm based on queue penalty optimization and an Actor-Critic-based dynamic updating algorithm for multiple resource allocation. Our study proposes a practical approach to enhance emergency communication in disaster areas, ensuring efficient and reliable network performance under various constraints.

关键词： NOMA Interference cancellation Heuristic algorithms Disasters Quality of service Throughput Dynamic scheduling Internet of Things Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Compute Resource Sharing of RISC-V Packed-SIMD Using Simultaneous Multi-threading 30th

Efficient Compute Resource Sharing of RISC-V Packed-SIMD Us...

引用

30th International Conference on Parallel and Distributed Processing Techniques, PDPTA 2024, held as part of the World Congress in computer science, computer Engineering and Applied Computing, CSCE 2024

作者： Takata, Shogo Nakajo, Hironori Department of Electrical Engineering and Computer Science Graduate School of Engineering Tokyo University of Agriculture and Technology 2–24–16 Nakacho Tokyo Koganei-shi184–8588 Japan Division of Advanced Information Technology Computer Science Institute of Engineering Tokyo University of Agriculture and Technology 2–24–16 Nakacho Tokyo Koganei-shi184–8588 Japan

ISBN: (纸本)9783031856372

AI tasks are gaining popularity in the area of IoT and edge devices. To run such tasks on devices, QNNs are used because of their reduced size and ability to be computed with simple integer arithmetic. There have been many implementations to support such a network format. However, when considering thread-level parallelism to speedup the program, many often implement a multi-core architecture or clusters which needs to copy all resources for each core. In this paper, we introduce a new RISC-V Out-of-Order Simultaneous Multi-Threading core "B4SMT" with RISC-V Packed-SIMD extension for evaluation. We also show that even a single executor could increase the performance of a 1D median filter by over 100×, and a matrix multiplication by over 30 on more than 16 threads efficiently. Furthermore, we suggest that other infrequently used executors may be placed as a shared resource efficiently in an SMT core. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Median filters

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：