检索结果-内蒙古大学图书馆

Automatic collaborative water surface coverage and cleaning strategy of UAV and USVs

Digital Communications and Networks 2025年第2期11卷 365-376页

作者： Deng, Tianping Xu, Xiaohui Ding, Zeyan Xiao, Xiao Zhu, Ming Peng, Kai School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Smart Internet Technology Huazhong University of Science and Technology Wuhan430074 China

As the problem of surface garbage pollution becomes more serious, it is necessary to improve the efficiency of garbage inspection and picking rather than traditional manual methods. Due to lightness, Unmanned Aerial Vehicles (UAVs) can traverse the entire water surface in a short time through their flight field of view. In addition, Unmanned Surface Vessels (USVs) can provide battery replacement and pick up garbage. In this paper, we innovatively establish a system framework for the collaboration between UAV and USVs, and develop an automatic water cleaning strategy. First, on the basis of the partition principle, we propose a collaborative coverage path algorithm based on UAV off-site takeoff and landing to achieve global inspection. Second, we design a task scheduling and assignment algorithm for USVs to balance the garbage loads based on the particle swarm optimization algorithm. Finally, based on the swarm intelligence algorithm, we also design an autonomous obstacle avoidance path planning algorithm for USVs to realize autonomous navigation and collaborative cleaning. The system can simultaneously perform inspection and clearance tasks under certain constraints. The simulation results show that the proposed algorithms have higher generality and flexibility while effectively improving computational efficiency and reducing actual cleaning costs compared with other schemes. © 2022 Chongqing University of Posts and Telecommunications

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation

Generating Is Believing: Membership Inference Attacks agains...

引用

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

作者： Li, Yuying Liu, Gaoyang Wang, Chen Yang, Yang Key Laboratory of Intelligent Sensing System and Security Ministry of Education School of Artificial Intelligence Hubei University Wuhan China Hubei Key Laboratory of Smart Internet Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350368741

Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist in content generation. Existing research has demonstrated potential privacy risks associated with the LLMs of RAG. However, the privacy risks posed by the integration of an external database, which often contains sensitive data such as medical records or personal identities, have remained largely unexplored. In this paper, we aim to bridge this gap by focusing on membership privacy of RAG's external database, with the aim of determining whether a given sample is part of the RAG's database. Our basic idea is that if a sample is in the external database, it will exhibit a high degree of semantic similarity to the text generated by the RAG system. We present S2MIA, a Membership Inference Attack that utilizes the Semantic Similarity between a given sample and the content generated by the RAG system. With our proposed S2MIA, we demonstrate the potential to breach the membership privacy of the RAG database. Extensive experimental results demonstrate that S2MIA outperforms five existing MIAs, even when the system is protected by three representative defenses. © 2025 IEEE.

关键词： Large Language Models Membership Inference Attacks Retrieval-Augmented Generation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Electric Vehicles for Enhancing Power System Resilience: A Review of Strategies and Challenges

引用

Current Sustainable/Renewable Energy Reports 2025年第1期12卷 1-8页

作者： Pang, Songling Liu, Cong Zhang, Chenjia Zhang, Jinxi Zhang, Hongcai Joint Laboratory of Smart Grid and lsland Microgrid Electric Power Research Institute of Hainan Power Grid Co. Ltd Haikou China Zhuhai UM Science & Technology Research Institute Zhuhai China University of Macau State Key Laboratory of Internet of Things for Smart City China

Background: The increasing occurrence of extreme weather events and the rapid growth of renewable energy penetration are challenging the resilience of modern power systems. Electric vehicles (EVs), due to their bidirectional energy capabilities, present a novel opportunity to enhance power system resilience in both normal and emergency scenarios. Objective: This study aims to systematically review the potential of EVs, particularly through Vehicle-to-Grid (V2G) technology, in enhancing power system resilience. The paper seeks to understand their applications in grid services, pre-disaster planning, and disaster response, while identifying associated technical, economic, and policy challenges. Methods: A comprehensive literature review was conducted, examining recent studies and pilot projects on EV integration into power systems. The review categorizes the findings into four strategic areas: V2G in non-crisis conditions, pre-disaster planning, emergency response, and policy frameworks. The paper also discusses commonly used resilience assessment metrics and proposes directions for future research. Results: EVs have demonstrated significant contributions to frequency and voltage regulation, peak shaving, black start capability, and disaster recovery. Pre-disaster coordination strategies, including hierarchical and two-stage optimization frameworks, have shown effectiveness in enhancing grid flexibility and critical load restoration. Policy mechanisms such as dynamic pricing and equitable incentive schemes play a pivotal role in encouraging EV participation in resilience services. Conclusion: EVs offer significant promise as distributed energy resources for enhancing power system resilience. Their effective integration requires not only supportive infrastructure and regulatory frameworks but also solutions to key challenges such as battery degradation, economic viability, and policy uncertainty. Future research should focus on developing scalable coordination strategi

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

Category-integrated Dual-Task Graph Neural Networks for session-based recommendation

引用

Expert Systems with Applications 2025年 263卷

作者： Ding, Yuhan Zhang, Zizhuo Wang, Bang Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology Hubei Wuhan43097 China

Session-based recommendation (SBR) aims to predict the subsequent item a user may be interested in based on their behavior within a limited timeframe. Most existing approaches primarily harness item relations and overlook the significance of attribute information (e.g. category). Users’ interests in specific items could change frequently within a single session, yet may exhibit more stability at the category level. We argue that integrating category information into SBR models can help mitigating data sparsity challenges for promoting next-item prediction. In this paper, we propose a novel SBR methodology named Category-integrated Dual-Task Graph Neural Networks (CDT-GNN). It constructs a heterogeneous global graph encompassing all sessions and individual heterogeneous local graphs for each session to learn items’ and categories’ representations. A dual-task learning strategy is employed to involve next-category prediction which serves as an auxiliary task to bolster the major task of next-item prediction. Additionally, a user-selectable accessory feature is developed to enhance the utilization of the predicted category. Extensive experimental results on three real-world datasets validate the effectiveness of CDT-GNN. © 2024 Elsevier Ltd

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Very high cycle fatigue resistance improvement of Mg-Gd-Zn-Zr alloy by introducing curved long-period stacking ordered lamellae

引用

Journal of Magnesium and Alloys 2025年第3期13卷 1218-1231页

作者： Min Zhan Xinglin Yang Shoucheng Shi Yao Chen Lang Li Bing Xue Yongbo Li Wanshuang Yi Qingyuan Wang Chao He Key Laboratory of Deep Earth Science and Engineering Ministry of EducationCollege of Architecture and EnvironmentSichuan UniversityChengdu 610065China Failure Mechanics&Engineering Disaster Prevention and Mitigation Key Laboratory of Sichuan ProvinceSichuan UniversityChengdu 610065China Science and Technology Research Center China Yangtze Power Corp(CYPC)Yichang Hubei 443002China Hubei Technology Innovation Center for Smart Hydropower Wuhan Hubei 430000China School of Architecture and Civil Engineering Chengdu UniversityChengdu 610106China

Magnesium alloys with long-period stacking ordered(LPSO)structures are known for their impressive static mechanical strength,but the consistent occurrence of slip-cracking along the LPSO lamellae,which do not effectively impede the movement of basal dislocations,has prompted concerns about their very high cycle fatigue(VHCF)*** this study,an extruded Mg-Gd-Zn-Zr alloy was developed,showcasing exceptional VHCF resistance due to its bimodal structure comprisingﬁne grains and coarse grains consisting of curved LPSO *** investigation on the crack initiation mechanism revealed that slip-induced cracking predominantly occurs inﬁne-grained regions rather than in the interior of coarse *** extrusion process aligns the basal planes of most coarse grains parallel to the axial direction,and the presence of curved LPSO lamellae acts as barriers to the movement of basal dislocations,thereby effectively increasing the threshold for slip-cracking along the basal ***,fatigue damage manifests in the form of slip bands and micro-cracks within the interior ofﬁne grains,ultimately resulting in fatigue crack initiation,propagation andﬁnal fracture.

关键词： Very high cycle fatigue Mg-Gd-Zn-Zr alloy Crack initiation Curved LPSO lamellae Micro-cracks

来源：评论

学校读者我要写书评

暂无评论

Delay-Aware Joint Microservice Deployment and Request Routing in Multi-Edge Environments Based on Reinforcement Learning

引用

IEEE Transactions on Network and Service Management 2025年

作者： Peng, Kai Guo, Jialu Wang, Hao He, Jintao Zou, Zhiqing Deng, Tianping Hu, Menglan Huazhong University of Science and Technology Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Wuhan430074 China

The service modules of the traditional Mobile Edge Computing (MEC) are difficult to deploy, extend, and maintain in real networks because of the highly sophisticated systems. To promote the generalization, openness, and flexibility of the network edge environment, an increasing number of studies are exploring the integration of microservices with MEC. However, the existing work usually treats microservice deployment and request routing as two separate issues, ignoring the interaction between them. Therefore, this paper focuses on the joint optimization of microservice deployment and request routing in the multi-edge cloud scenarios. We establish a problem model for minimizing the average response latency, considering the transmission of requests across edge clouds. Then, in view of the complexity of the scene, this paper proposes a joint training strategy of microservice deployment and request routing based on deep reinforcement learning and Best Fit Decreasing algorithm. The algorithm takes the change of microservice deployment scheme as the action of the agent, introduces the Best Fit Decreasing algorithm to construct request routing based on the deployment scheme, and calculates rewards using the complete joint microservice deployment and request routing scheme for subsequent network training. Finally, experimental results show that the proposed algorithm can effectively reduce the response time delay and system running power compared with other algorithms. © 2004-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancement of bandwidth-efficiency capability in apodized grating couplers by improving mode matching at multi-wavelengths

Enhancement of bandwidth-efficiency capability in apodized g...

引用

2024 International Symposium on Silicon-based Optoelectronics, ISSBO 2024

作者： Huang, Shiyuan Hou, Jin Qu, Yu Long, Hao Yang, Chunyong Chen, Shaoping Hubei Key Laboratory of Intelligent Wireless Communications Hubei Engineering Research Center of Intelligent Internet of Things Technology College of Electronic and Information Engineering South-Central Minzu University Hubei Wuhan430074 China

ISBN: (数字)9781510687608

ISBN: (纸本)9781510687592

Broadband-efficient grating couplers serve as the key bridge connecting fiber and the chip in silicon photonics. Apodized grating couplers (AGC) have already demonstrated with high coupling efficiency, but almost all of them have been designed by only considering of mode matching coupling at single-wavelength, which resulting in a limited coupling bandwidth. Here, a multi-wavelengths mode matching method by calculating the root mean square error of effective-index and leakage-factor is proposed to design AGCs with both an enhancement bandwidth and a high coupling efficiency. Our investigation shows that, compared with the conventional single-wavelength SOI AGC, in an optimized multi-wavelengths AGC, the 3 dB bandwidth could be extended from 60 nm to 88 nm and the coupling efficiency could be enhanced from 67 % to 74 %. Moreover, when a metal reflector at the bottom of the AGC was furtherly adopted, both the 3 dB bandwidth and the coupling efficiency could be enhanced to an even more higher value of 92 nm and 91 % in an optimized multi-wavelengths AGC. These results would provide a new pathway to achieve broadband grating couplers by considering of multi-wavelengths mode matching. © 2025 SPIE.

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels

arXiv

引用

arXiv 2025年

作者： Tong, Yujia Wang, Yuze Yuan, Jingling Hu, Chuang Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things China State Key Laboratory of Internet of Things for Smart City University of Macau China

Model quantization enables efficient deployment of deep neural networks on edge devices through low-bit parameter representation, yet raises critical challenges for implementing machine unlearning (MU) under data privacy regulations. Existing MU methods designed for full-precision models fail to address two fundamental limitations in quantized networks: 1) Noise amplification from label mismatch during data processing, and 2) Gradient imbalance between forgotten and retained data during training. These issues are exacerbated by quantized models’ constrained parameter space and discrete optimization. We propose Q-MUL, the first dedicated unlearning framework for quantized models. Our method introduces two key innovations: 1) Similar Labels assignment replaces random labels with semantically consistent alternatives to minimize noise injection, and 2) Adaptive Gradient Reweighting dynamically aligns parameter update contributions from forgotten and retained data. Through systematic analysis of quantized model vulnerabilities, we establish theoretical foundations for these mechanisms. Extensive evaluations on benchmark datasets demonstrate Q-MUL’s superiority over existing approaches. 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

A High-Sensitivity Strain Sensor With Femtosecond Fiber Bragg Grating for Pipeline Deformation Monitoring

引用

IEEE Sensors Journal 2025年第9期25卷 14830-14841页

作者： Gong, Yongjian Guo, Yongxing Xiong, Li Liu, Chang Zhou, Wanhuan Hu, Zhongchun Li, Xiudong Zhang, Yu Wuhan University of Science and Technology Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan430081 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Civil and Environmental Engineering China China Academy of Safety Science and Technology Beijing100012 China China Railway 14th Bureau Group Corporation Ltd. Jinan250000 China

Structural health monitoring (SHM) of hydraulic pipelines plays a crucial role in preventing catastrophic failures, particularly when measuring large strains with high sensitivity. This study presents a novel high-sensitivity strain sensor utilizing femtosecond fiber Bragg grating (FS-FBG) technology to overcome the limitations of conventional monitoring techniques in extreme conditions. The sensor incorporates two key components: sensing and measuring members, featuring an innovative skeletonized sensitized shaft design. A pre-stressed FS-FBG is suspended axially within the structure. The relationship between fiber Bragg grating (FBG) wavelength displacement and pipe surface strain was validated using Bernoulli-Euler beam theory and finite element analysis. In order to accurately calibrate the performance of the sensor, a precision pipe deformation device was designed. Experimental results demonstrate that the sensor achieves a sensitivity of 4.19 pm/ μϵ, which is 3.4 times higher than that of the FBG sensor, in the range of 0-1650 μϵ of the pipe surface microstrain, and at the same time, it has excellent linearity, creep-resistant performance, and temperature compensation effect. The results provide a reliable solution for large strain monitoring of hydraulic pipelines under severe conditions. © 2001-2012 IEEE.

关键词： Fiber Bragg gratings

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：