检索结果-内蒙古大学图书馆

Bilateral Pricing for Dynamic Association in Federated Edge Learning

IEEE Transactions on Mobile computing 2025年第6期24卷 4684-4697页

作者： Pan, Bangqi Lu, Jianfeng Cao, Shuqin Liu, Jing Tian, Wenlong Li, Minglu Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China Dalian University of Technology Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence China University of South China School of Computer Science and Technology Hengyang421001 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China

Devices and servers in Federated Edge Learning (FEL) are self-interested and resource-constrained, making it critical to design incentives to improve model performance. However, dynamic network conditions raise energy consumption, while data heterogeneity undermines device cooperation. Current research overlooks the interplay between system efficiency and device clustering, resulting in suboptimal updates. To address these challenges, we develop BENCH, a bilateral pricing mechanism consisting of three core rules aimed at incentivizing participation from both devices and servers. Specifically, we first design a reward allocation rule, based on the Rubinstein bargaining model, which dynamically allocates rewards. Theoretically, we derive a closed-form solution for this rule, demonstrating BENCH achieves Nash equilibrium. Secondly, we design a device partitioning rule that leverages modularity to group similar devices, facilitating personalized edge aggregation to accelerate local data adaptation. Thirdly, we design an edge matching rule that employs the Kuhn-Munkres algorithm to balance the load at edge servers, thus minimizing the congestion. Together, these three rules enable hierarchical optimization of pricing and associations, effectively mitigating the impact of dynamic costs and device heterogeneity. Extensive experiments demonstrate BENCH's effectiveness in increasing device participation by 28.81% and improving model performance by 2.66% compared to state-of-the-art baselines. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A Cross-Scale Multi-Branch Feature Fusion Based Method for Smoke and Fire Detection in Warehouses 24

A Cross-Scale Multi-Branch Feature Fusion Based Method for S...

引用

13th International Conference on computing and Pattern Recognition, ICCPR 2024

作者： Bai, Yanbing Liu, Pengyu Liu, Weilong Deng, Yiyang Kong, Lili Chen, Shanji Chen, Jiali Yuan, Bowen School of Information Science and Technology Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University Of Technology Beijing China Information Technology Co. Ltd Dingzhou China Beijing-Dublin International College at BJUT Beijing University Of Technology Beijing China College of Physics and Electronic Information Engineering Qinghai Minzu University Qinghai China

ISBN: (纸本)9798400717482

To address the challenges of leakage, misdetection, and low accuracy caused by environmental complexity, object occlusion, and insufficient lighting in smoke and fire detection within warehouse scenarios, this paper proposes a cross-scale multi-branch feature fusion network for smoke and fire detection, named SF-YOLO. Firstly, a multi-branch feature enhancement module, Res2Net-C, is proposed to introduce an attention mechanism using a multi-branch feature fusion network, which not only extends the sensory field of the network, but also enhances the ability of extracting effective information, while effectively suppressing the interference of irrelevant information. It effectively improves detection performance under complex environmental conditions and in the presence of object occlusion. Secondly, a cross-scale feature fusion network structure, MSFPN, is proposed, which achieves effective complementation and fusion of high-level and low-level information by establishing hopping connections between features at different scales, and significantly improves the recognition accuracy of the type and location of the smoke and fire in low-light conditions. In addition, the added small target detection layer further improves the network's ability to detect small targets. Finally, in order to better adapt to pyrotechnic targets with variable morphology, EIoU is adopted as the bounding box loss function. Test results on a self-built dataset show that SF-YOLO achieves a mean accuracy rate (mAP) of 87.5% in the task of detecting smoke and fire under multiple environmental factors in a warehouse scenario, proving its effectiveness and usefulness. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Proportional-Integral Algorithms for Multiple Coalition Games under Limited Communication Resources

引用

IEEE Transactions on Signal and Information Processing over Networks 2025年 11卷 450-459页

作者： Liu, Jiaxun Wang, Dong Liu, Jiashuo Dong, Xiwang Ludong University School of Mathematics and Statistics Science Yantai264025 China Dalian University of Technology School of Control Science and Engineering Dalian116024 China Optimization for Industrial Equipment of Ministry of Education Key Laboratory of Intelligent Control China Beihang University Institute of Unmanned System Institute of Artificial Intelligence School of Automation Science and Electrical Engineering Beijing100191 China

This paper studies the algorithm design for multiple coalition games under limited communication resources, in which the players in the same coalition cooperatively optimize the summation of cost functions in this coalition and do not care about the costs of other coalitions. To address this game, we develop a distributed proportional-integral algorithm based on the coalition estimate strategy and the proportional-integral principle. Furthermore, when the communication resource is concretely quantified by bit rates in communication channels, we propose a coding-decoding-based distributed proportional-integral algorithm based on the distributed proportional-integral algorithm and coding-decoding rules for seeking the Nash equilibrium of multiple coalition games. It proves that both algorithms linearly and precisely converge to the Nash equilibrium in spite of limited communication resources. Then, the necessary and sufficient condition for the linear convergence of the proposed algorithm about the requirement of bit rates is presented. Moreover, the relationship between the bit rate and the convergence speed of the proposed algorithm is also theoretically explained. Lastly, the simulation in formation problems of unmanned vehicle swarms is presented to demonstrate the effectiveness of proposed algorithms. © 2015 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Online Credibility Assessment of Equipment Digital Twin for Discrete Manufacturing

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14763-14774页

作者： Lu, Han Zhang, Lin Deen, M. Jamal Wang, Kunyu Cheng, Hongbo Yang, Laurence T. Beihang University Hangzhou International Innovation Institute Zhejiang 311115 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing100854 China AI Atlas Inc Canada Zhengzhou University School of Computer and Artificial Intelligence School of Software Engineering Zhengzhou China St. Francis Xavier University Department of Computer Science Antigonish Canada

The equipment digital twins (EDTs) for discrete manufacturing should be calibrated quickly to avoid irreversible physical damage to the equipment caused by biased control commands. Therefore, an online credibility assessment method for EDTs is urgently needed. However, existing assessment approaches consume too much time, and thus could not reveal dynamic faults in time. In this paper, the dynamic relationship between online evolution and actual applications of EDTs is investigated. Then, two steps are proposed to accelerate the assessment process significantly. One involves pre-constructing a performance-deviation-agent (PDA), and the other involves dynamically fitting the application-time-window (ATW) probability distribution. The methodology is applicable to discrete manufacturing processes. The dynamic credibility of EDT evolution process can be updated after every iteration of the model evolution. Sorting manufacturing equipment was used as a case study to demonstrate the effectiveness of this method. The time consumption was reduced by 90% compared with traditional assessment methods in the case. © 2025 IEEE.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

EagerLog: Active Learning Enhanced Retrieval Augmented Generation for Log-based Anomaly Detection

EagerLog: Active Learning Enhanced Retrieval Augmented Gener...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Duan, Chiming Jia, Tong Yang, Yong Liu, Guiyang Liu, Jinbu Zhang, Huxing Zhou, Qi Li, Ying Huang, Gang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China Alibaba Cloud Computing Company Hangzhou China

ISBN: (纸本)9798350368741

Logs record essential information about system operations and serve as a critical source for anomaly detection, which has generated growing research interest. Utilizing large language models (LLMs) within a retrieval-augmented generation (RAG) framework for log-based anomaly detection is an effective approach due to its strong generalization capabilities and efficient few-shot performance. However, the effectiveness of this method hinges on the quality of the knowledge source, which can be impacted by noise and changes within the software systems. Facing these problems, in this paper, we propose a novel log-based anomaly detection method named EagerLog, employing active learning to choose the logs for humans to label, thereby adding them to the knowledge source, thus enhancing the knowledge source and maintaining its quality. Our experiments on three open datasets (BGL, Thunderbird, Zookeeper) and one industrial dataset demonstrate that EagerLog can achieve 93.65% F1 score with approximately 10 labeled log sequences, surpassing existing methods by 15.32%. © 2025 IEEE.

关键词： Active Learning Anomaly Detection Log Analysis Retrieval Augmented Generation

来源：评论

学校读者我要写书评

暂无评论

ILNet: Low-level Matters for Salient Infrared Small Target Detection

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Li, Haoqing Yang, Jinfu Wang, Runshi Xu, Yifei Faculty of Information Beijing University of Technology Beijing100124 China Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

Infrared small target detection is a technique for finding small targets from infrared clutter background. Previous deep-learning-based approaches have achieved promising results. However, the lack of high-level semantic information leads to a degradation of small infrared target features in the deeper layers of the neural network, resulting in suboptimal representation capabilities. To address this issue, we propose an Infrared Low-level Network (ILNet) that conceptualizes infrared small targets as salient regions characterized by limited semantic information. In contrast to other state-of-the-art methods, ILNet emphasizes low-level information more significantly, rather than treating it uniformly with high-level information. A lightweight feature fusion module, named Interactive Polarized Orthogonal Fusion module (IPOF), is proposed, which integrates more important low-level features from the shallow layers into the deep layers. A Dynamic One-Dimensional Aggregation layers (DODA) are inserted into the IPOF, to dynamically adjust the aggregation of low dimensional information according to the number of input channels. In addition, the idea of ensemble learning is used to design a Representative Block (RB) to dynamically allocate weights for shallow and deep layers. Experimental results on the challenging NUAA-SIRST (78.22% nIoU and 1.33 × 10−6Fa) and IRSTD-1k (68.91% nIoU and 3.23 × 10−6Fa) dataset demonstrate that the proposed ILNet can get better performances than other SOTA methods. Moreover, ILNet can obtain a greater improvement with the increasement of data volume. Training code are available at https://***/LiHaoqing/ILNet. © 1965-2011 IEEE ALL RIGHT RESERVED.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Position Guided Dynamic Receptive Field Network: A Small Object Detection Friendly to Optical and SAR Images

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Liuqian Li, Jiafeng Zhang, Jing Zhuo, Li Tian, Qi Beijing University of Technology School of Information Science and Technology Beijing100124 China Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China Huawei Inc Guangdong Shenzhen518129 China

Object detection in remote sensing images (RSIs), including optical and SAR images, has emerged as a rapidly advancing field. However, the abundance of small objects in RSIs poses a significant challenge in designing a network structure with effective receptive fields to support accurate localization and classification. In this paper, we propose a position guided dynamic receptive field network (PG-DRFNet) for small object detection friendly to optical and SAR images. Specifically, PG-DRFNet overcomes the problem of small objects vanishing or being submerged in features by establishing a positional guidance relationship of small objects between different feature layers. Then, we design a combination head structure that utilizes additional supervised information extracted from small objects to make the model more effective and flexible. Moreover, a dynamic perception algorithm based on feature construction are developed to dynamically optimize the perception regions and feature hierarchies of the model, while seeking the optimal tradeoff between model accuracy and inference speed. Without bells and whistles, our model is robust to two modalities of remote sensing data, and our experiments are conducted on four benchmark RSI datasets, including DOTA-v2.0, VEDAI, SSDD, and HRSID. The experimental results achieve competitive performance with 59.01%, 84.06%, 90.06%, and 80.59% mAP, respectively. Code and models are released at https://***/BJUT-AIVBD/PG-DRFNet. © 2025 IEEE.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Complex scene fall detection method based on improved YOLOv5 24

Complex scene fall detection method based on improved YOLOv5

引用

13th International Conference on computing and Pattern Recognition, ICCPR 2024

作者： Li, Yifan Liu, Pengyu Kong, Lili Deng, Yiyang Liu, Weilong Chen, Shanji Chen, Jiali Yuan, Bowen School of Information Science and Technology Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China Hebei Hongyi Environmental Protection Technology Co. Ltd Dingzhou Hebei China Beijing-Dublin International College at BJUT Beijing University of Technology Beijing China Information Technology Co. Ltd Dingzhou Hebei China College of Physics and Electronic Information Engineering Qinghai Minzu University Qinghai China

ISBN: (纸本)9798400717482

Aiming at the existing deep learning-based fall detection model in multiple complex scenes such as multi-person scenes, long-distance scenes, and occlusion scenes, there are problems such as leakage detection and false detection. In this paper, we take the falling person as the research object, construct a dataset containing multiple complex scenes such as multi-person scenes, long-distance scenes, and occlusion scenes, and propose a fall detection model based on improved YOLOv5. By improving the backbone network and neck network structure of the detection model, the problem of low accuracy of fall detection due to incomplete target deformation features and target detail features in complex scenes is solved. The proposed algorithm in this paper achieves an average accuracy of 92.78% for fall detection in complex scenes, and the detection speed reaches 36 frames/second. © 2024 Copyright held by the owner/author(s).

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

A Model-Agnostic Hierarchical Framework Towards Trajectory Prediction

引用

Journal of Computer Science and Technology 2025年第2期40卷 322-339页

作者： Qian, Tang-Wen Wang, Yuan Xu, Yong-Jun Zhang, Zhao Wu, Lin Qiu, Qiang Wang, Fei Domain-Oriented Intelligent System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Predicting the future trajectories of multiple agents is essential for various applications in real life, such as surveillance systems, autonomous driving, and social robots. The trajectory prediction task is influenced by many factors, including the individual historical trajectory, interactions between agents, and the fuzzy nature of the observed agents’ motion. While existing methods have made great progress on the topic of trajectory prediction, they treat all the information uniformly, which limits the effectiveness of information utilization. To this end, in this paper, we propose and utilize a model-agnostic framework to regard all the information in a two-level hierarchical view. Particularly, the first-level view is the inter-trajectory view. In this level, we observe that the difficulty in predicting different trajectory samples varies. We define trajectory difficulty and train the proposed framework in an "easy-to-hard" schema. The second-level view is the intra-trajectory level. We find the influencing factors for a particular trajectory can be divided into two parts. The first part is global features, which keep stable within a trajectory, i.e., the expected destination. The second part is local features, which change over time, i.e., the current position. We believe that the two types of information should be handled in different ways. The hierarchical view is beneficial to take full advantage of the information in a fine-grained way. Experimental results validate the effectiveness of the proposed model-agnostic framework. © Institute of computing Technology, Chinese Academy of Sciences 2025.

关键词： Hierarchical systems

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：