检索结果-内蒙古大学图书馆

An effective meta-heuristics for trajectory planning problem in UAV-assisted vessel emission detection system

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-21页

作者： Zhu, Jie Cui, Weizhi Huang, Haiping Zhu, Tao Sun, Yuzhong School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

With the development of the shipping industry, the pollution problem caused by vessel fuels is becoming increasingly severe. Due to the great mobility and on-demand service capability of Unmanned Aerial Vehicles (UAVs), UAVs have become effective tools for detecting pollution in Emission Control Areas (ECAs). How to obtain the effective trajectories of UAVs within the energy limitation and the time limitation is a difficult problem to solve. The paper investigates the trajectory planning problem in UAV-assisted vessel emission detection system. In the problem, the sailing vessels in a given area are taken as the detection tasks and multiple UAVs are ready to detect these vessels. Each vessel is assigned a different detecting weight and sails to the port at a different speed. The objective is to complete as many detection tasks as possible before the deadline and maximize the total weight of these completed tasks. A Genetic Algorithm (GA)-based trajectory planning algorithm framework is proposed for the problem under study. The framework consists of key components, such as the chromosome generation method to generate chromosomes of each generation, the feasible solution generation method to compute the feasible solution according to the sequence defined in a chromosome, and the chromosome reconstruction method to improve the quality of chromosomes based on history information. The experimental results show that the proposed algorithm outperforms the baseline algorithms in terms of effectiveness and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ENHANCING ROBUST FAIRNESS VIA CONFUSIONAL SPECTRAL REGULARIZATION

arXiv

引用

arXiv 2025年

作者： Jin, Gaojie Wu, Sihao Liu, Jiaxu Huang, Tianjin Mu, Ronghui The Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Beijing China Department of Computer Science University of Exeter Exeter United Kingdom Department of Computer Science University of Liverpool Liverpool United Kingdom

Recent research has highlighted a critical issue known as "robust fairness", where robust accuracy varies significantly across different classes, undermining the reliability of deep neural networks (DNNs). A common approach to address this has been to dynamically reweight classes during training, giving more weight to those with lower empirical robust performance. However, we find there is a divergence of class-wise robust performance between training set and testing set, which limits the effectiveness of these explicit reweighting methods, indicating the need for a principled alternative. In this work, we derive a robust generalization bound for the worst-class robust error within the PAC-Bayesian framework, accounting for unknown data distributions. Our analysis shows that the worst-class robust error is influenced by two main factors: the spectral norm of the empirical robust confusion matrix and the information embedded in the model and training set. While the latter has been extensively studied, we propose a novel regularization technique targeting the spectral norm of the robust confusion matrix to improve worst-class robust accuracy and enhance robust fairness. We validate our approach through comprehensive experiments on various datasets and models, demonstrating its effectiveness in enhancing robust fairness. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Power Consumption Model for GPU Data Centers with Time-VAE

A Comprehensive Power Consumption Model for GPU Data Centers...

引用

International Conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Wang, Senyao Wu, Jianhong Zhang, Ruozhu The School of Electrical and Computer Engineering The University of Sydney SydneyNSW2008 Australia The School of Electrical Engineering Shanghai University of Electric Power Shanghai200090 China State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power University Beijing102206 China

ISBN: (纸本)9789819618675

In this study, we propose and evaluate a comprehensive power consumption model for GPU-based data centers that integrates the energy consumption of various task types, including language processing, speech recognition, and image generation, along with the power consumption of other components such as the CPU, memory, network, and storage. Using real GPU power consumption data, we measured the server energy consumption. To compensate for the limited experimental data and ensure accurate evaluation of average power consumption per unit time after model convergence, we utilize the TimeVAE model to generate supplementary data. The PCA and t-SNE visualizations validate the effectiveness of the TimeVAE model in preserving data distribution and structure. Our comprehensive model provides valuable insights into the energy consumption patterns in GPU-based data centers and offers practical guidance for optimizing energy usage to improve overall efficiency and sustainability. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Data centers

来源：评论

学校读者我要写书评

暂无评论

Semantic Gaussian Mixture Variational Autoencoder for Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Li, Beibei Xiang, Tao Jin, Beihong Zheng, Yiyuan Zhao, Rui College of Computer Science Chongqing University Chongqing China Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Science Beijing China University of Chinese Academy of Sciences Beijing China

Variational AutoEncoder (VAE) for Sequential Recommendation (SR), which learns a continuous distribution for each user-item interaction sequence rather than a determinate embedding, is robust against data deficiency and achieves significant performance. However, existing VAE-based SR models assume a unimodal Gaussian distribution as the prior distribution of sequence representations, leading to restricted capability to capture complex user interests and limiting recommendation performance when users have more than one interest. Due to that it is common for users to have multiple disparate interests, we argue that it is more reasonable to establish a multimodal prior distribution in SR scenarios instead of a unimodal one. Therefore, in this paper, we propose a novel VAE-based SR model named SIGMA. SIGMA assumes that the prior of sequence representation conforms to a Gaussian mixture distribution, where each component of the distribution semantically corresponds to one of a user’s multiple interests. For multi-interest elicitation, SIGMA includes a probabilistic multi-interest extraction module that learns a unimodal Gaussian distribution for each interest according to implicit item hyper-categories. Additionally, to incorporate the multimodal interests into sequence representation learning, SIGMA constructs a multi-interest-aware ELBO, which is compatible with the Gaussian mixture prior. Extensive experiments on public datasets demonstrate the effectiveness of SIGMA. The code is available at https://***/libeibei95/SIGMA. acceptance. © 2025, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

An active power control of DFIG-based wind turbine generators for frequency regulation with expected dynamic performance

引用

Applied Energy 2025年 391卷

作者： Zhao, Teyang Liu, Hui Wang, Ni Su, Jinshuo Luo, Zhiqiang Ma, Siyu School of Electrical Engineering Guangxi University Nanning530004 China Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi University Nanning530004 China The State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of Macau 519000 China

The escalating wind power penetration presents a substantial challenge in ensuring the system frequency stability. Although wind turbine generators (WTGs) can offer rapid frequency support by the presetting power trajectory response (PPTR), it will result in a secondary frequency dip (SFD) while facing the demand of restoring rotor speed after frequency regulation. Moreover, the frequency overshoot will occur due to the fixed power increment provided by PPTR under minor disturbances. In this paper, an active power control strategy of DFIG-based WTGs is proposed for eliminating frequency overshoot and mitigating SFD while providing power support for the system frequency. A rotor-speed-based power increment and power attenuation trajectory are designed to enhance the primary frequency nadir while ensuring the operation stability of WTGs. After that, SFD will be mitigated by the proposed parabolic-formed compensation power. Moreover, a power increment control mode is proposed to eliminate the frequency overshoot by a membership-function-based global controller, which can smoothly switch the combined inertial response and the improved PPTR to provide a flexible power increment. Finally, the validity of the proposed strategy in improving frequency nadir, eliminating frequency overshoot, and mitigating SFD are verified by simulations under different wind power penetration levels, disturbances, and wind conditions. © 2025

关键词： Frequency stability

来源：评论

学校读者我要写书评

暂无评论

Resilient Cooperative Control of Multiple DC Microgrids With Interconnection Networks Against Cyber Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical systems 2025年 3卷 116-126页

作者： Xiao, Feng Liu, Shiyu Wei, Bo Fang, Fang Qin, Jiahu North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China North China Electric Power University New Energy Generation National Engineering Research Center Beijing102206 China University of Science and Technology of China Department of Automation Hefei230027 China

The two control objectives of voltage regulation and precise current sharing are conflicting in multi-bus DC microgrids. In this paper, a distributed control strategy is proposed, and it can achieve accurate current sharing and regulate the voltage of a critical node to the rated value. However, such a distributed control system is susceptible to potential cyber attacks that could deteriorate microgrids performances by corrupting communication links or actuators. To overcome these difficulties, we design the interconnected communication networks to establish a resilient cooperative system of multiple microgrids against unknown bounded injection attacks. The proposed resilient control strategy can achieve the control objectives of maintaining voltage regulation and current sharing within each microgrids under different operating conditions, and the interconnected system consisting of multiple microgrids cooperates to mitigate the adverse effect of cyber attacks. The dynamics and stability of the overall close-loop system of the DC microgrids are analyzed, in the present or absent of cyber attacks. Simulation results validate the effectiveness of the proposed approach in two 4-bus DC microgrids. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

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

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

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：