检索结果-内蒙古大学图书馆

Energy-efficient computation offloading via deep reinforcement learning in mobility-aware multi-access edge computing systems with diverse users

引用

Expert Systems with Applications 2025年 286卷

作者： Wu, Haixing Jin, Shunfu School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Multi-access Edge Computing (MEC) has been a promising solution that enables Internet of Things (IoT) devices to support computation-intensive applications by offloading some tasks to the network edge. However, most existing offloading methods in MEC systems are based on the premise of scenarios with either single-type or stable users, which is not aligned with the practical situations of users’ diversity and mobility. In addition, these methods always ignore energy saving strategies in MEC systems, which inevitably degrades Utility Energy Efficiency (UEE). To tackle these issues, considering personalized requirements from diverse users and idle energy consumption in MEC servers, we propose a novel computation offloading architecture with adaptive sleeping mechanism and heterogeneous MEC servers. Based on the architecture, we investigate energy-efficient computation offloading in mobility-aware MEC systems with diverse users. Under the Deep Reinforcement Learning (DRL) framework, we propose a Twin Delayed Deep Deterministic Policy Gradient Algorithm with Bursty Traffic (TD3-BT), in which the inherent correlation of task arrivals is taken into account to capture the behavior of correlated traffic and provide rational metrics estimation within one time slot. A long-term system cost minimization problem is formulated to optimize computation offloading for the trade-off between system delay and UEE. Assisted by TD3-BT, the formulated problem is effectively solved and the decision making in each time slot is provided for diverse users. Experimental results demonstrate that our TD3-BT algorithm achieves superior performance under various offloading scenarios compared to some benchmarks. © 2025 Elsevier Ltd

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Network Coding Techniques for Resource Allocation in Wireless Relay Networks 3

Network Coding Techniques for Resource Allocation in Wireles...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Khanna, Lalit Ranganathaswamy, M.K. Balamurugan, V. Maharishi, Ankita Agarwal Saini, Rajat Nanda, Sarmistha Chitkara Centre for Research and Development Chitkara University Himachal Pradesh Baddi174103 India Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India Department of Computer Applications Odisha Bhubaneswar India

ISBN: (纸本)9798331542375

Network coding is an applicable technique to enhance the performance of wireless relay networks, in which intermediate nodes are utilized to expand the coverage range and increase communication reliability. The utilization of network coding in these networks should be well addressed by resource allocation such as bandwidth and power allocation. Among them, network coding for resource allocation in wireless relay networks is the most attractive research work. In particular, dynamic network coding is a strategy that varies how we code data according to current conditions in the network so as to achieve the maximum possible throughput during relaying. Dual-joint power and resource combinations have relatively better performance gains due to the efficient channel gain with an additional level of resource utilization for enhanced resource allocation. In addition, network coding schemes, including opportunistic and homomorphic network coding, have been introduced to perform well in an environment with fading channels and enhance data transmitting reliability. These techniques take advantage of the intrinsic diversity in wireless pathways to improve overall network throughput and reduce latency. © 2025 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Channel Estimation Techniques for 5G Communications 3

Machine Learning Based Channel Estimation Techniques for 5G ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Patil, Nagaraj Aranganathan, A. Yadav, Dhananjay Kumar Khurana, Saniya Mohapatra, Sarita Sharma, Divya Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India Department of Computer Applications Odisha Bhubaneswar India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh Baddi174103 India

ISBN: (纸本)9798331542375

There has been a high demand for efficient and accurate channel estimation techniques to satisfy the need for 5G, which is moving towards high data rates and low latency applications. Most of the conventional methods, like Least Squares (LS) and Minimum Mean Square Error (MMSE), have yet to be able to meet these requirements. Due to this, an increase in the popularity of Machine Learning (ML) based channel estimation for 5G communications can be seen. Instead of using mathematical models, the ML-based channel estimation techniques make use of the strong computational power of ML algorithms to learn the behavior of the channel from training data. These techniques have been shown to be superior in accuracy and efficiency compared to classic methods, thus allowing better channel estimation and, as a result, a performance improvement at the system level. Additionally, due to the flexibility of ML-based methods, they can adapt to time-variant channel conditions and decrease computational complexity. Abstract: This paper discusses the different Machine Learning ML-based channel estimation techniques for 5G communications, which include deep learning approaches like neural network implementation, support vector machines, and Reinforcement learning. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Role of Flexible Batteries in Enabling Electric Vehicle Adoption 3

The Role of Flexible Batteries in Enabling Electric Vehicle ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Rekha, K. Bhanu Singh, B.P. Kaur, Prabhjot Mahalat, Mahabub Hasan Ahluwalia, Gunveen Premkumar, R. Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre for Interdisciplinary Research for Business and Technology Centre of Research Impact and Outcome Punjab Rajpura140417 India Department of Computer Science and Information Technology Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi174103 India Karnataka Bangalore India

ISBN: (纸本)9798331542375

Flexible batteries, also known as thin-movie batteries, have emerged as a promising technology in the race toward the giant adoption of electrical automobiles (EVs). These batteries provide several blessings over conventional lithium-ion batteries, which currently electricity most EVs, including decreased weight, advanced safety, and better electricity garage capability. One of the foremost demanding situations dealing with EV adoption is the restrained use variety presented through conventional batteries, which require frequent recharging. This has been a major barrier for ability customers, who may have yet to get admission to charging stations or may be deterred by the prolonged charging process. Bendy batteries, with their lightweight and excessive electricity storage potential, can appreciably grow the use of a variety of EVs, making them an extra feasible opportunity for fuel-powered motors. Moreover, bendy batteries may be incorporated into the design of the car, making it possible to create extra aerodynamic and space-green EVs. This allows for greater flexibility in car design and reduces the general value of production. Similarly, as EVs become more extensively used, the call for bendy batteries will grow due to economies of scale and doubtlessly decrease the fee of manufacturing even in addition. © 2025 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Optimized User Scheduling for Full-Duplex Communications in Wireless Networks 3

Optimized User Scheduling for Full-Duplex Communications in ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Roy, Debabrata Garg, Mohan Ezhilarasan, G. Selvaraj, Barani Das, Neeraj Singh, Manpreet Department of Computer Applications Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi174103 India Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India

ISBN: (纸本)9798331542375

Full duplex communication allows a user to transmit and receive data at the same time, and it has been seen as a promising technique to increase the efficiency and throughput of wireless networks. This, in turn, causes new kinds of problems like self-interference and intra-post interference, causing unfairness to other users. In this paper, we present an optimized user scheduling method for full-duplex communications in wireless networks to address these issues and further improve system throughputs. The schematic of our schedule adjusts the time and frequency for flexibility to obtain suitable resource appointments along with channel conditions and user traffic demand. We also conduct simulations to show that the proposed scheme significantly improves system throughput and fairness over existing scheduling schemes. The proposed scheme will also decrease the self-interference level and enhance the robustness of interference to neighboring networks. The main takeaway from our scheme is to realize the full potential of FD communication in wireless networks, hence providing a more reliable and efficient network for users. © 2025 IEEE.

关键词： Frequency Full Duplex Receive Data Robustness Self-Interference

来源：评论

学校读者我要写书评

暂无评论

6G Communication New Paradigm: The Integration of Unmanned Aerial Vehicles and Intelligent Reflecting Surfaces

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Ning, Zhaolong Li, Tengfeng Wu, Yu Wang, Xiaojie Wu, Qingqing Yu, Fei Richard Guo, Song Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai Shanghai200240 China Carleton University School of Information Technology OttawaONK1S 5B6 Canada The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

With the continuous development of Intelligent Reflecting Surfaces (IRSs) and Unmanned Aerial Vehicles (UAVs), their combination has become foundational technologies to complement the terrestrial network by providing communication enhancement services for large-scale users. This article provides a comprehensive overview of IRS-assisted UAV communications for 6th-Generation (6G) networks. First, the applications supported by IRS-assisted UAV communications for 6G networks are introduced, and key issues originated from applications supported by IRSs and UAVs for 6G networks are summarized and analyzed. Then, prototypes and main technologies related to the integration of IRSs and UAVs are introduced. Driven by applications and technologies of IRS-assisted UAV communications, existing solutions in the realms of energy-constrained communications, secure communications, and enhanced communications are summarized, and corresponding empirical lessons are provided. Finally, we discuss some research challenges and open issues in IRS-assisted UAV communications, offering directions for the future development. © 1998-2012 IEEE.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

Provable causal distributed two-time-scale temporal-difference learning with instrumental variables

引用

Expert Systems with Applications 2025年 287卷

作者： Ma, Yanan Feng, Jiamei Wu, Qingtao Zheng, Ruijuan Zhu, Junlong Xi, Jiangtao Zhang, Mingchuan School of Information Engineering Henan University of Science and Technology Luoyang471023 China Longmen Laboratory Luoyang471023 China School of Electrical Computer and Telecommunications Engineering University of Wollongong WollongongNSW2522 Australia

Temporal-difference (TD) learning is one of the most popular methods for policy evaluation in reinforcement learning. Nevertheless, existing distributed TD learning may suffer from an estimation bias with respect to rewards during the interactive process between the generation and analysis of data, which leads to failure in the finding process of optimal policy. To correct this bias, we propose a novel distributed two-time-scale TD algorithm by leveraging instrumental variables (IVs) techniques, referred to as D-IV-TD(0). Furthermore, we generalize the D-IV-TD(0) algorithm to a distributed two-time-scale stochastic approximation (SA) approach, referred to as D-IV-SA. We establish finite-time error bounds of D-IV-SA are O(lnt/tκ) and O(lnt/tδ) for two-time-scale parameters respectively, where t is the number of iterations, κ and δ are constants with 0−κC) and O(t−δC) with probability no less than 1−CθT−κ˜lnT and 1−CωT−δ˜lnT, where κC∈[0,κ−1/2) and δC∈[0,δ−1/2). Finally, we verify the performance of the proposed algorithm through the small ball collision experiment, and the experimental results show that the D-IV-TD(0) algorithm converges quickly and has an error value close to 0. © 2025 Elsevier Ltd

关键词： Time measurement

来源：评论

学校读者我要写书评

暂无评论

Key Components of Participatory Design Workshops for Digital Health Solutions: Nominal Group Technique and Feasibility Study

引用

Journal of Healthcare Informatics Research 2025年 1-21页

作者： Denecke, Kerstin Rivera-Romero, Octavio Giunti, Guido Van Holten, Karin Gabarron, Elia Department of Engineering and Computer Science Institute Patient-Centered Digital Health Bern University of Applied Sciences Quellgasse 21 Biel2502 Switzerland Electronic Technology Department Universidad de Sevilla Seville Spain Universidad de Sevilla Seville Spain School of Medicine Trinity College Dublin Dublin Ireland Faculty of Medicine University of Oulu Oulu Finland School of Health Professions Competence Centre Participatory Health Care Bern University of Applied Sciences Bern Switzerland Department of Education ICT and Learning Østfold University College Halden Norway

Participatory design (PD) is an essential method in the development of digital health solutions since it promises to increase acceptance, usability, and trust in the developed solution. Although careful planning and preparation is crucial for the success of PD workshops, a framework of key components to consider is still missing. The objective of this work is to develop such framework enriched with examples for aspects to be considered when planning and conducting PD workshops for designing and developing digital interventions in healthcare. We applied the nominal group technique with four participants with backgrounds in computer science, health informatics, psychology, and social anthropology to identify key components of PD workshops. The resulting framework was applied by an expert in PD to a case of a digital health solution for fatigue self-management for multiple sclerosis. The feasibility and applicability of the framework and its shortcomings were assessed. As a result, a framework consisting of five main categories and a total of 36 factors were assigned and defined in relation to the categories. The categories are participatory process, involved persons and their roles, workshop definition, setting, privacy and ethics, including regulations. The application of the framework to the test case demonstrated the feasibility and applicability of the suggested framework as well as the shortcomings of the analyzed PD process. This framework provides practical guidance while highlighting the complexity of PD workshops, encouraging their broad adoption, critical reflection, and continuous refinement. It has potential to improve the conduct of PD workshops and, in this way, potential to improve usability, acceptance, and usefulness of digital health solutions. In future work, the user perspective could be used to extend the framework. © The Author(s) 2025.

关键词： Laws and legislation

来源：评论

学校读者我要写书评

暂无评论

Triple Point Masking

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Liu, Jiaming Kong, Linghe Wu, Yue Gong, Maoguo Li, Hao Miao, Qiguang Ma, Wenping Qin, Can The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The College of Mathematics Science Inner Mongolia Normal University Hohhot010022 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug- and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. © 2025 IEEE. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Analysis of Sensor Technologies for Structural Health Monitoring in Civil engineering Applications 3

Analysis of Sensor Technologies for Structural Health Monito...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Agarwal, Trapty Gandhi, Ayush Mohapatra, Yogomaya Singh, Jagtej Bahri, Dimple Reddy, V. Venkata Ramesh Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India Department of Computer Science and Engineering Odisha Bhubaneswar India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh Baddi174103 India Department of Civil Engineering Karnataka Bangalore India Presidency University Sponsored Research Karnataka Bangalore India

ISBN: (纸本)9798331542375

Civil engineering is considered complete with structural health monitoring SHM, a continuous process in which structures are tested for their health and integrity, ensuring they remain safe and reliable. Recent advancements in sensor technologies for SHM have improved the empirical side of structural performance. The advancement of sensor technologies for SHM is largely related to implementing wireless and smart sensors. It is easily fixable and provides real-time information on the strain, temperature, vibration, etc. Wireless and smart sensors can also be deployed in difficult-to-access or non-safe areas, allowing for an increased size of monitored structures. In addition, the emergence of sensor technologies has resulted in smart algorithms and data analytics methods suitable for SHM. Such algorithms process huge amounts of data and detect potential structural problems or anomalies before any expected maintenance intervention. © 2025 IEEE.

关键词： Structural Mechanics

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：