检索结果-内蒙古大学图书馆

Joint Task Partitioning and Resource Allocation in UAV-Enabled Vehicular Edge Computing Based on Deep Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年第11期12卷 15453-15466页

作者： Liang, Hongbin Zhang, Han Ale, Laha Hong, Xintao Wang, Lei Jia, Qiong Zhao, Dongmei Southwest Jiaotong University School of Transportation and Logistics National United Engineering Laboratory of Integrated and Intelligent Transportation National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu611756 China Southwest Jiaotong University School of Information Science and Technology Chengdu611756 China Chinese Academy of Sciences Laboratory of Noise and Vibration Research Institute of Acoustics Beijing100190 China McMaster University Department of Electrical and Computer Engineering HamiltonONL8S 4K1 Canada

Vehicle Edge Computing (VEC) leverages compact cloud computing at the mobile network edge to meet the processing and latency needs of vehicles. By bringing computation closer to the vehicles, VEC reduces data transmission, minimizes latency, and boosts performance for compute-intensive applications. However, during peak hours of urban road traffic, the scarce computational resources available at edge servers could pose challenges in fulfilling the processing needs of vehicles. Introducing Unmanned Aerial Vehicles (UAVs) as supplementary edge computing nodes could significantly mitigate the aforementioned issue. In this paper, we propose a flexible edge computing framework in which a fleet of UAVs function as mobile computational service providers, offering computation offloading services to multiple vehicles. We design and optimize a computation offloading model for the UAV-enabled vehicle edge computing environment. The proposed model tackles the task offloading challenge, aiming to optimize UAV revenue and task processing efficiency while considering the constraints of UAVs' restricted computational power and energy resources. Towards this end, our model jointly considers two key factors: task partitioning and computational resource allocation. To tackle the challenges posed by the aforementioned non-convex optimization problem, we construct a Markov Decision Process (MDP) model for the multi-UAV-enabled mobile edge computing system and introduce an innovative Multi-Agent Deep Reinforcement Learning (MADRL) framework addressing the decision-making challenge represented by MDP model. Comprehensive simulation outcomes illustrate that our devised task offloading technique outperforms other optimization methods. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Fundamental Diagram Modeling of Mixed Traffic Flow Considering Dedicated Lanes for Human-Driven Vehicles

引用

IEEE Transactions on Vehicular technology 2025年

作者： Wang, Yi Xu, Zeqi Wu, Yunxia Jiang, Yangsheng Yao, Zhihong Southwest Jiaotong University School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Sichuan610031 China

To mitigate the impact of human-driven vehicles (HDVs) on connected and automated vehicles (CAVs) in mixed traffic environments, the implementation of dedicated lanes has been proposed to achieve partial separation between CAVs and HDVs, thereby improving the operational efficiency of both CAVs and the road segment. The lane management policy, where dedicated lanes for HDV (HDLs) and general lanes (GLs) coexist on a road segment, is referred to as the (G, H) policy. This paper proposes a multi-lane fundamental diagram model for mixed traffic flow and aims to investigate the effects of HDL configuration on the efficiency of road segments under the (G, H) policy. Firstly, different car-following modes in mixed traffic flow are analyzed, and various car-following models are employed to characterize the mixed traffic flow. Secondly, two lane selection principles are introduced to describe the lane choice behavior of HDVs under the (G, H) policy. Based on these principles, five equilibrium states that may exist on the road segment under the (G, H) policy are analyzed. Subsequently, a multi-lane fundamental diagram model incorporating HDL is derived based on the lane selection principles of HDV. Finally, numerical analysis is conducted to investigate the influence of lane configuration schemes under the (G, H) policy on the distribution of equilibrium states, fundamental diagram, and capacity. The results indicate that: (1) Based on the lane choice behavior of vehicles, the equilibrium states of road segment can be classified into five types. The distribution of each equilibrium state under different traffic conditions only depends on the proportion of HDL to the total number of lanes on road segment. A higher number of HDL leads to a reduced applicability of the (G, H) policy under different traffic conditions. (2) Under different penetration rates, as density increases, the overall traffic volume of road segment initially increases and then decreases until reaching the

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Attaining the stabilizing solution of model unavailable modified algebraic Riccati equation using Q-learning algorithm

引用

Information Sciences 2025年 717卷

作者： Gao, Jie Feng, Tao Yan, Fei School of Information Science and Technology Southwest Jiaotong University Sichuan Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

This paper attempts first to solve the discrete-time modified algebraic Riccati equation (MARE) when the system model is completely unavailable. To achieve this, a new iterative algorithm is proposed to solve the MARE based on its equivalent discrete-time algebraic Riccati equation (DARE) which has an identical solution. The algorithm iterates between two steps: 1) the solution improvement of the equivalent DARE;2) the input weighting improvement. It is proved theoretically that the algorithm strictly converges to the stabilizing solution of the MARE. As an outstanding advantage over the existing methods, the initiation of the algorithm becomes fairly simple which can be initialized by an arbitrary positive input weighting for the single-input scenario or a pre-given input weighting matrix of a sufficiently large magnitude for the multi-input scenario. Furthermore, the proposed algorithm provides an iterative structure which is particularly suitable for developing the Q-learning (QL) algorithm where only the input/output data of the related linear quadratic regulator (LQR) problem is required, therefore the MARE can be solved successfully without using the system model. Finally, numerical simulation examples are given to verify the effectiveness of the theoretical results and the developed algorithm. © 2025 Elsevier Inc.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

LightST: A Simplifying Spatio-Temporal Graph Neural Network for Traffic Flow Forecasting

引用

IEEE Transactions on big data 2025年

作者： Hu, Jie Zheng, Taichuan Peng, Lilan Teng, Fei Du, Shengdong Li, Tianrui Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology China

Traffic flow forecasting task plays an essential role in intelligent transportation systems. Accurately capturing the intricate spatio-temporal dependencies in traffic network signals is the core of precise prediction. Recently, a paradigm that models spatio-temporal dependencies through graph neural networks and time series models has become one of the most promising methods to solve this problem. However, existing methods still have limitations due to ineffectively modeling dynamic spatial dependencies and high time and space complexity. To address these issues, we propose a simplifying and powerful general spatio-temporal traffic flow forecasting model called LightST. Specifically, LightST first embeds temporal covariates and spatial position information to enhance the spatio-temporal modeling capabilities. Then, stacked temporal linear layers are introduced to capture temporal dependencies efficiently. Finally,we propose a concise adaptive spatio-temporal embedding graph convolution method to extract implicit spatial dependencies over time via dynamic graph convolution with adaptive spatio-temporal embedding graph generation. Extensive experiment results on four public traffic flow datasets demonstrate the superiority of our LightST concerning computational efficiency and prediction performance. © 2025 IEEE. All rights reserved,

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

A Vertical Federated Multiview Fuzzy Clustering Method for Incomplete data

引用

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1510-1524页

作者： Li, Yan Hu, Xingchen Yu, Shengju Ding, Weiping Pedrycz, Witold Kiat, Yeo Chai Liu, Zhong National University of Defense Technology Laboratory for Big Data and Decision Changsha410073 China National University of Defense Technology School of Computer Changsha410073 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Nanyang Technological University College of Computing and Data Science 639798 Singapore

Multiview fuzzy clustering (MVFC) has gained widespread adoption owing to its inherent flexibility in handling ambiguous data. The proliferation of privatization devices has driven the emergence of new challenge in MVFC research works. Federated learning, a technique that can jointly train without directly using raw data, has gain significant attention in decentralized MVFC. However, their applicability depends on the assumptions of data integrity and independence between different views. In fact, while within distributed environments, data typically exhibits two challenging problems: 1) multiple views within a single client;2) incomplete data. Existing methods exhibit limitations in effectively addressing these challenges. Hence, in this study, we aim at achieving the effective clustering for incomplete data by a novel vertical federated MVFC framework. Specifically, a unified clustering framework is designed to capture both local client learning and global server training. For the local client learning, the data reconstruction strategy and prototype alignment strategy are introduced to ensure the preservation of data structure and refinement of clustering relationships, which mitigates the impact of incomplete data. Meanwhile, the global training process implements aggregation based on client-specific information. The whole process is realized based on the unified fuzzy clustering framework, promoting collaborative learning between client-specific and server information. Theoretical analyses and extensive experiments are carefully conducted to validate the effectiveness and efficiency of the proposed method from multiple perspectives. © 1993-2012 IEEE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

Life cycle assessment for rare earth production from ion-adsorption deposits: A comparative study of magnesium sulfate and ammonium sulfate leaching techniques

引用

Journal of Environmental Management 2025年 385卷 125627页

作者： Wang, Ying Gao, Feng Sun, Boxue Chen, Wenjuan Nie, Zuoren National Engineering Laboratory for Industrial Big-data Application Technology Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China

The production of rare earth elements, key raw materials for high-end technological innovation, is associated with considerable energy consumption and environmental pollution. This study focused on the mining of ion-adsorption deposits in southern China and examined two principal production processes: magnesium salt leaching and ammonium salt leaching. A life cycle inventory for the production of 1 kg of individual rare earth oxides and rare earth elements was compiled via field research and resource consumption allocation modeling of the hydrometallurgical system. The environmental impacts of these processes were assessed using the ReCiPe 2016 method. The scope of the assessment in this study included the rare earth oxide production chain of in situ leaching, solvent extraction, and oxidation roasting and the three major metal reduction processes: molten salt electrolysis, calcium thermal reduction, and cerium thermal reduction. The findings indicated that among the 15 rare earth oxides and elements, yttrium oxide and yttrium metal had the most pronounced environmental impacts. The in situ leaching stage exerted the most considerable environmental influence throughout the production process. A comparison of the magnesium salt leaching and ammonium salt leaching processes revealed that the former exhibited a significantly lower environmental impact than the latter, particularly regarding Terrestrial Eco-toxicity Potential (TETP), which was reduced by 87.55 %. This study elucidates the environmental challenges inherent to the production of rare earths and provides a scientific foundation for the optimization of the production process and reduction of environmental pollution. © 2025 Elsevier Ltd

关键词： Effluents

来源：评论

学校读者我要写书评

暂无评论

TAPFixer: automatic detection and repair of home automation vulnerabilities based on negated-property reasoning 24

TAPFixer: automatic detection and repair of home automation ...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Yinbo Yu Yuanqi Xu Kepu Huang Jiajia Liu National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Cybersecurity Northwestern Polytechnical University China and Research & Development Institute of Northwestern Polytechnical University in Shenzhen China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Cybersecurity Northwestern Polytechnical University China

ISBN: (纸本)9781939133441

Trigger-Action Programming (TAP) is a popular end-user programming framework in the home automation (HA) system, which eases users to customize home automation and control devices as expected. However, its simplified syntax also introduces new safety threats to HA systems through vulnerable rule interactions. Accurately fixing these vulnerabilities by logically and physically eliminating their root causes is essential before rules are deployed. However, it has not been well studied. In this paper, we present TAPFixer, a novel framework to automatically detect and repair rule interaction vulnerabilities in HA systems. It extracts TAP rules from HA profiles, translates them into an automaton model with physical and latency features, and performs model checking with various correctness properties. It then uses a novel negated-property reasoning algorithm to automatically infer a patch via model abstraction and refinement and model checking based on negated-properties. We evaluate TAPFixer on market HA apps (1177 TAP rules and 53 properties) and find that it can achieve an 86.65% success rate in repairing rule interaction vulnerabilities. We additionally recruit 23 HA users to conduct a user study that demonstrates the usefulness of TAPFixer for vulnerability repair in practical HA scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An M3RSMA-Based Roadside Cooperative Message Delivery Scheme for Complex Intersection

引用

IEEE Transactions on Wireless Communications 2025年

作者： Shi, Zhenjiang Liu, Jiajia School of Information Engineering Chang’an University Xi’an710064 China Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710072 China

Traditional single-vehicle intelligence system faces challenges such as blind spots and perception performance bottlenecks due to limitations in sensor perception angles, ranges, and accuracy, which are particularly pronounced in complex intersection. Vehicle-infrastructure cooperative mechanism has been widely recognized as a promising solution to address challenges faced by single-vehicle intelligence. However, against the backdrop of limited spectrum resources and the sharply rising in the number of connected vehicles, how to efficiently deliver cooperative messages from roadside unit to vehicles is often overlooked. Towards this end, we propose a roadside cooperative message delivery scheme based on multicarrier multigroup multicast rate-splitting multiple access, considering the rarely explored case of transmitting messages with limited size under delay constraint. Then we focus on the critical joint optimization problem of message size and power allocation, with consideration for imperfect channel state information at the transmitter. Subsequently, a multi-agent deep reinforcement learning based resource allocation algorithm is designed to solve this joint optimization problem, exhibiting robustness to dynamic changes in vehicle density and message size. Finally, we analyze through extensive numerical results the impacts of various factors on message delivery success probability. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution of Diffusion-Weighted Images via TDI-Conditioned Diffusion Model 15th

Super-Resolution of Diffusion-Weighted Images via TDI-Cond...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Ma, Jiquan Teng, Yujun Chen, Geng Jiang, Haotian Zhang, Kai Liu, Feihong Rekik, Islem Shen, Dinggang School of Computer Science and Technology Heilongjiang University Harbin China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering and State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai China School of Information Science and Technology Northwest University Xi’an China BASIRA Lab Imperial-X and Department of Computing Imperial College London London United Kingdom

ISBN: (纸本)9783031869198

Diffusion-Weighted Imaging (DWI) is a significant technique for studying white matter. However, it suffers from low-resolution obstacles in clinical settings. Post-acquisition Super-Resolution (SR) can enhance the resolution of DWIs and has gained increasing research interest in recent years. An advanced generative model, the Diffusion Model (DM), exhibits particularly promising performance in image SR. However, effective conditions are required to bootstrap the DM for DWI SR. To this end, we proposed the first DM-based DWI SR model with two effective conditions based on low-solution DWIs and Track Density Imaging (TDI) maps, which possess rich high-resolution prior knowledge Additionally, we consider another condition based on features from low-resolution DWIs. These two conditions are integrated into our model, which comprises three components: DWI Resolution Enhancer (DRE), DWI Feature Extractor (DFE), and TDI Feature Extractor (TFE). DRE combines low-resolution DWI features from DFE with TDI features from TFE to progressively generate high-resolution DWIs. We performed extensive experiments on DWIs of normal subjects from human connectome projects and patients with Parkinson’s disease. The results demonstrate that our model outperforms existing DWI SR models, both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Adaptive disentangled target representation for unsupervised domain adaptation in remote sensing segmentation

引用

engineering applications of Artificial Intelligence 2025年 156卷

作者： Lu, Runuo Dong, Shoubin Jia, Jianxin Wang, Xusheng Liu, Kai Chen, Jinsong Guo, Shanxin Zheng, Xiaorou Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou510641 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute EspooFI-02150 Finland Center for Geo-Spatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application Shenzhen518055 China

Due to the significant differences between the source and target domains, semantic segmentation models for remote sensing images trained on the source domain often struggle to generalize effectively to new target domains, leading to performance degradation. Most solutions disentangle features into domain-invariant features shared by both domains and domain-specific features unique to each domain, relying primarily on the domain-invariant features for model construction and inference. However, during this process, critical domain-specific features as essential information are often discarded as noise, leading to a reduction in segmentation accuracy. To address these issues, this study proposes an unsupervised domain adaptation, called ChameleonRS. ChameleonRS separates the domain-invariant features and the domain-specific features by disentanglement learning, and introduces a multi-level feature alignment module to enhance the representation of domain-invariant features. More importantly, it aligns predictions based on domain-invariant features with those based on fused invariant and specific features using contrastive learning, effectively capturing target-specific features. This study explores two cross-domain semantic segmentation tasks: (I) Geographic location variation. (II) Geographic location and imaging mode variation. Results show that under setting (I), ChameleonRS outperforms the state-of-the-art method by 4.79% in Intersection over Union (IoU) and 6.51% in the F1 score. Under setting (II), it achieves improvements of 4.46% and 4.82% in IoU and F1 score. Results demonstrate the superiority and adaptability of ChameleonRS under varying geographical and imaging conditions, effectively mitigating the generalization issues caused by distribution differences, and thereby promoting the development and application of remote sensing technologies in practical scenarios. © 2025 Elsevier Ltd

关键词： Semantic Segmentation

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

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

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：