检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Software Reuse: Optimization and Comparative Performance Analysis

AI-Driven Software Reuse: Optimization and Comparative Perfo...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Aditya Pai H Chandrappa S Guru Prasad M S Atul Thakare Sharon Christa Pratik Kumar MIT School of Computing MIT Art Design and Technology University Pune India School of Computer Science and Engineering JAIN Deemed to be University Bengaluru India Dept. of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Application Graphic Era (Deemed-to-be University) Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Software reuse improves productivity and ensures that there is less time delivered to the market by enabling the proper usage of reusable code from the software repositories. The study provides the collaboration between the AI techniques, which includes Convolution Neural Networks (CNN), Random Forest (RF), and Support Vector Machines (SVM), to predict software components' reusability. The comparative analysis shows the effectiveness of different AI- driven algorithms, where CNN has shown the highest accuracy of 92%, thus reducing the human effort in finding the reusable modules. The Case studies in e-commerce and health care show the benefit of using AI-driven reuse of software; this means that the development time is reduced by 25%, and the maintenance cost is decreased by 20%. The paper highlights how different AI algorithm integration with software engineering has some limitations. The findings show that AI has greatly revolutionized software reuse. Thus bringing innovation and efficiency in software engineering.

关键词： Support vector machines Computational modeling Medical services Software Data models Convolutional neural networks Artificial intelligence Software reusability Random forests Software engineering

来源：评论

学校读者我要写书评

暂无评论

Research on Older Adults’ Interaction with E-Health Interface Based on Explainable Artificial Intelligence

arXiv

引用

arXiv 2024年

作者： Huang, Xueting Zhang, Zhibo Guo, Fusen Wang, Xianghao Chi, Kun Wu, Kexin Faculty of Art Design Guangdong College of Commerce Guangzhou China School of Engineering and Information Technology University of New South Wales Canberra Australia School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia College of Engineering Computing and Cybernetics Australian National University Canberra Australia College of Professional Studies Northeastern University NJ United States Department of Computer Science Cornell University NY United States

This paper proposed a comprehensive mixed-methods framework with varied samples of older adults, including user experience, usability assessments, and in-depth interviews with the integration of Explainable Artificial Intelligence (XAI) methods. The experience of older adults’ interaction with the E-health interface is collected through interviews and transformed into operatable databases whereas XAI methods are utilized to explain the collected interview results in this research work. The results show that XAI-infused e-health interfaces could play an important role in bridging the age-related digital divide by investigating elders’ preferences when interacting with E-health interfaces. Furthermore, the study identifies important design factors, such as intuitive visualization and straightforward explanations, that are critical for creating efficient Human-Computer Interaction (HCI) tools among older users. Furthermore, this study emphasizes the revolutionary potential of XAI in e-health interfaces for older users, emphasizing the importance of transparency and understandability in HCI-driven healthcare solutions. This study’s findings have far-reaching implications for the design and development of user-centric e-health technologies, intending to increase the overall well-being of older adults. © 2024, CC BY.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Optimal AoI-based Block Propagation and Incentive Mechanism for Blockchain Networks in Web 3.0

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Wen, Jinbo Kang, Jiawen Xiong, Zehui Du, Hongyang Yang, Zhaohui Niyato, Dusit Shen, Meng Jiao, Yutao Zhang, Yang Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China Guangdong University of Technology School of Automation China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore Hong Kong University Department of Electrical and Electronic Engineering Hong Kong Zhejiang University College of Information Science and Electronic Engineering China Nanyang Technological University College of Computing and Data Science Singapore Beijing Institute of Technology School of Cyberspace Science and Technology China Army Engineering University of PLA College of Communications Engineering China

Web 3.0 is regarded as a revolutionary paradigm that enables users to securely manage data without a centralized authority. Blockchains, which enable data to be managed in a decentralized and transparent manner, are key technologies for achieving Web 3.0 goals. However, blockchain-based Web 3.0 is still in its infancy, such as ensuring block freshness and optimizing block propagation to improve blockchain performance. In this paper, we develop a freshness-aware block propagation optimization framework for Web 3.0. We first propose a novel metric called Age of Block Information (AoBI) based on the concept of age of information to quantify block freshness. AoBI measures the time elapsed from the freshest transaction generation to the completion of block consensus. To make block propagation optimization tractable, we classify miners into five different states and propose a block propagation model for public blockchains inspired by epidemic models. Moreover, considering that the miners are bounded rational, we propose an incentive mechanism based on the evolutionary game for block propagation to improve block propagation efficiency. Numerical results demonstrate that compared with other block propagation mechanisms in public blockchains, the proposed scheme has a higher block forwarding probability, which improves block propagation efficiency and decreases the minimum value of average AoBI. © 2015 IEEE.

关键词： age of information block propagation evolutionary game Web 3.0 wireless networks

来源：评论

学校读者我要写书评

暂无评论

Bounded-DWA: An Efficient Local Planner for Ackermann-driven Vehicles on Sandy Terrain

Bounded-DWA: An Efficient Local Planner for Ackermann-driven...

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Ke Gong Zhiyuan Xu Xinyu Zhang Shanghai Key Laboratory of Trustworthy Computing Engineering Research Center of Software/Hardware Co-Design Technology and Application (MoE) and School of Software Engineering East China Normal University Shanghai Midea Group China

We present a new dynamic window approach (DWA) for mobile vehicles equipped with Ackermann steering geometry that adheres to Ackermann kinematic constraints. By integrating these constraints with the sampling window in DWA, we can further reduce and bound the sampling range and enhance the efficiency of the DWA when a mobile vehicle moves on sandy terrain. Furthermore, we improve the evaluation function to optimize the selected trajectory. Our algorithm is successfully validated in ROS and Gazebo through comparison with other existing local planner such as the original DWA and TEB algorithms. We also successfully deploy our Bounded-DWA in the application of coverage path planning, where tree-planting robots traverse on sandy terrain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Management System for Smart Cities Utilizing Reinforcement Learning Algorithm

Intelligent Traffic Management System for Smart Cities Utili...

引用

2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2022

作者： Rajan, Karthick Kumar, K Sampath Kannapiran, Thirunavukkarasu Khan, Shahnawaz Al-Dmour, Ayman Sharef, Baraa T. School of Computing Science and Engineering Galgotias University Greater Noida India Unitedworld School of Computational Intelligence Karnavati University Gujarat India Bahrain Polytechnic Faculty of Engineering Design and Information and Communications Technology Isa Town Bahrain College of Arts and Science Applied Science University Al Eker Bahrain College of Information Technology Ahlia University Manama Bahrain

ISBN: (数字)9781665469197

ISBN: (纸本)9781665469197

Traffic congestion on roadways or at intersections can occur for a variety of reasons, including increased vehicle queues, slow driving, and so on. When multiple emergencies occur at the same time, traffic gridlock may occur. An adaptive traffic control system is a traffic management method that allows signals to adapt to the current traffic demand in real time. Adaptive traffic signals work by synchronizing software and hardware. Q-learning necessitates the creation of accurate natural environment forms prior to taking action. Instead, a dynamic communication system was developed to explore the interplay between state, action, and rewards in that particular setting. The current traffic signal functions are based on predetermined traffic flow information to extract short time expectations, making it easier to calculate the signal management system's conclusion. If a certain model is used, then customizable traffic light management agents will have to collect photos of the current traffic situation and generate control signals at regular intervals. To improve the algorithm's stability, replay, occurrence, and ideal techniques have been implemented. The primary goal of the algorithm is to regulate congested traffic, which is accomplished by combining the dynamic network with the linear signal layout. © 2022 IEEE.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wireless Networks with Attention Mechanisms: Insights from Mobile Crowdsensing

arXiv

引用

arXiv 2024年

作者： Yang, Yaoqi Du, Hongyang Xiong, Zehui Niyato, Dusit Jamalipour, Abbas Han, Zhu College of Communications Engineering Army Engineering University of PLA Nanjing210000 China College of Computing and Data Science NTU Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Electrical and Computer Engineering University of Sydney SydneyNSW2006 Australia Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States

The increasing demand for sensing, collecting, transmitting, and processing vast amounts of data poses significant challenges for resource-constrained mobile users, thereby impacting the performance of wireless networks. In this regard, from a case of mobile crowdsensing (MCS), we aim at leveraging attention mechanisms in machine learning approaches to provide solutions for building an effective, timely, and secure MCS. Specifically, we first evaluate potential combinations of attention mechanisms and MCS by introducing their preliminaries. Then, we present several emerging scenarios about how to integrate attention into MCS, including task allocation, incentive design, terminal recruitment, privacy preservation, data collection, and data transmission. Subsequently, we propose an attention-based framework to solve network optimization problems with multiple performance indicators in large-scale MCS. The designed case study have evaluated the effectiveness of the proposed framework. Finally, we outline important research directions for advancing attention-enabled MCS. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Machine Learning (ML) and Internet of Things (IoT): A Scientometric Review

Analysis of Machine Learning (ML) and Internet of Things (Io...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Samuel-Soma M. Ajibade Muhammed Basheer Jasser Rosıe Fe B. Legaspıno Anabella R. Gımeno Leomar A. Ypanto Jeem Clyde C. Baird Anthonia Oluwatosin Adediran Department of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Malaysia Cebu Technological University Moalboal Cebu Philippines Faculty of Architecture and Urban Design Federal University of Uberlandia Uberlândia Brazil

ISBN: (数字)9798350382310

ISBN: (纸本)9798350382327

The objective of this paper is to critically examine the publication’s trends and research landscape on the Internet of Things and Machine Learning (Io T-ML) research through bibliometric analysis (BA). The Elsevier Scopus database was selected to identify, screen, and analyze the published documents on IoT-ML. The publication trends and major stakeholders on the topic were subsequently. BA was performed to examine the co-authorships, keyword occurrences, and citations using VOSviewer software. Lastly, a systematic literature review was performed to summarize the scientific and technological advancements. Results revealed that the publications on IoT-ML largely comprise articles, conference proceedings, and reviews, whereas the publication trends showed an increase from 2 to 105 between 2015 and 2021. The top researchers on IoT-ML are S. Baskar, M. Guizani, and A. Souri, whereas the top institution is the Vellore Institute of Technology (India). However, the top country and research funder are; India, and National Natural Science Foundation (China), respectively. BA showed that the research landscape on IoT-ML comprises numerous networks of co-authors and countries working on related themes. The most impactful publication is Mahdavinejad et al. (2018) which has 479 citations, whereas the most prestigious journal is the IEEE Io T journal with 9 published documents in Scopus. Keyword analysis revealed IoT-ML has potential applications in health care, medicine, computer security and data analytics etc. Overall, IoT-ML has significant socio-economic and research impacts, and as such, the field will witness geometric techno-scientific growth and development in the future, particularly in the areas of network security and big data analytics.

关键词： Systematics Reviews Databases Bibliometrics Machine learning Network security Market research

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation for Non-Cooperative Spacecraft Based on Deep Learning

SSRN

引用

SSRN 2024年

作者： Gao, Xiang Liu, Chang Liu, Jia Hu, Weiduo Shenzhen Aerospace Dongfanghong Satellite Ltd Guangdong Shenzhen518052 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518052 China Beihang University Beijing100191 China Total Design Department Institute of Advanced Computing and Digital Engineering Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing China School of Astronautics

This paper proposes an end-to-end pose estimation framework for spacecraft. The framework can run on full-size images and jointly calculate translation and rotation parameters based on shared features of convolutional network. In addition, we introduce the method of label normalization. In the training stage, images and labels are normalized and then input into the neural network architecture for training. In the test stage, the normalized images are input to the trained framework, and the corresponding predicted pose is obtained after the output parameters are reversely normalized. Then we use the local optimization method to optimize the predicted pose. The effectiveness of our method is verified by a large number of experiments. © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Optimised Energy Management System for Microgrids

Artificial Intelligence-Based Optimised Energy Management Sy...

引用

International Universities Power engineering Conference (UPEC)

作者： Muhammad Majid Hussain Mian Hammad Nazir Muhammad Naveed Akhtar Waqas Javed Abdul Razaq Ahmad Hesham Pasha School of Engineering & Physical Sciences Heriot-Watt University Edinburgh UK Faculty of Computing Engineering & Science University of South Wales Cardiff UK Department of Electrical Engineering Rachna College of Engineering & Technology Gujranwala Pakistan James Watt School of Engineering University of Glasgow Glasgow UK School of Design and Informatics Abertay University Dundee UK

Electric power consistency is one of the essential variables in the social and economic growth of a smart city. In contrast, innovative energy sources and intelligent electricity networks are the primary components in making a city smart. This study describes an artificial neural network (ANN)- based controller for increasing power supply consistency by employing a dynamic voltage restorer. The optimisation approach particle swarm optimisation (PSO) is also discussed in this work, used to compute the maximum power point tracking (MPPT) of wind/photovoltaic hybrid power systems. The proposed PSO and ANN techniques can detect load, wind velocity, and solar irradiation fluctuations to optimise generating device power output, allowing hybrid power systems to function steadily, safely, and economically. This paper predicts and compares results with two cases using PSO and ANN to show the greater robustness and comparability of microgrid hybrid energies, namely photovoltaic and wind power. The simulation results show that the ANN-based controller with the PSO technique gives better performance as compared to the fuzzy controller. Further, the simulation results show that the converter can follow the hybrid system's maximum power point.

关键词：

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：