检索结果-内蒙古大学图书馆

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Dou, Chenglong Huang, Ning Wu, Yuan Qian, Liping Quek, Tony Q.S. University of Macau State Key Laboratory of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519301 China Zhejiang University of Technology College of Information Engineering Hangzhou310023 China Singapore University of Technology and Design 487372 Singapore

ISBN: (纸本)9798350351255

Integrated sensing and communication (ISAC) networks constitute a crucial paradigm for facilitating numerous advanced services in future wireless networks. This paper investigates the joint bandwidth and power allocations for device-to-device (D2D) communications aided ISAC in which D2D pairs complete their data transmissions by using the bandwidth allocated by the base station (BS) while providing sensing services for the BS. To this end, we formulate a joint optimization of bandwidth allocation and power allocations for both the target sensing and data transmission of each D2D pair, with the objective of maximizing a system-wise gain that accounts for both performances of target sensing and D2D data transmission. Despite the formulated optimization problem is strictly non-convex, we develop an efficient algorithm based on Lagrangian duality and sequential convex programming for solving it. Simulation results demonstrate that our proposed D2D communications aided ISAC is both accurate and efficient over several benchmark schemes. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Model Considering External Factors for Accurate Short-Term Traffic Flow Prediction 23

A Hybrid Deep Learning Model Considering External Factors fo...

引用

4th International Conference on Computing, Networks and internet of things, CNIOT 2023

作者： Xiang, Jun Xiang, Jianwen Li, Guanjie Wang, Yongsheng Lu, Liping Hubei Key Laboratory of Transportation of Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China and Wuhan University of Technology Chongqing Research Institute Chongqing China School of Information Engineering Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400700705

With the rapid development of Intelligent Transportation Systems (ITS), accurate short-term traffic flow prediction is becoming more and more vital for both traffic management authorities and residents, since it can improve traffic management efficiency and personal travel experience. However, many existing prediction methods rely solely on traffic flow data, neglecting the effects of some external factors (e.g., specific dates and actual road conditions on traffic flow), which limit to achieve accurate prediction. Therefore, this paper proposes a deep learning-based AT-Conv-GRU (Attention Convolutional-Gated Recurrent Unit) model, which takes historical traffic flow data and external factors as input data simultaneously, and takes the traffic flow at predicted moment as output. Firstly, the historical traffic flow data of the current moment is input into the Conv-GRU (Convolutional-Gated Recurrent Unit) module with attention mechanism to extract features from both spatial and temporal dimensions. The historical traffic flow data of the same moment of the previous day and the last week is input into the Bi-GRU (Bi-directional GRU) module to extract time-dependent and periodic features. Meanwhile, the hidden features of external factors are extracted using CNN (Convolutional Neural Network). Finally, the extracted features of each module are concatenated by feature fusion layer and eventually output by fully connected layer. Extensive experimental results show that the prediction accuracy of the AT-Conv-GRU model significantly outperforms traditional methods and other deep learning-based methods. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Smart LPG Monitoring System: Enhanced Safety with Leakage Detection 2

Smart LPG Monitoring System: Enhanced Safety with Leakage De...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Hotur, Varsha P. Prianka, R.R. Lynsha Helena Pratheeba, H.P. Padmavathi, M. Ramaraj, Kottaimalai Thilagaraj, M. MVJ College of Engineering Department of Electronics and Communication Engineering Bengaluru India New Horizon College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India CMR Institute of Technology Department of Computer Science and Engineering Bengaluru India Dayananda Sagar College of Engineering Department of Electronics and Communication Engineering Bengaluru India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India MVJ College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350367461

Gas leaks can lead to significant accidents causing both material damage and harm to individuals. Two significant factors that contribute to gas leaks are inadequate upkeep of systems and inadequate public awareness. Therefore, the detection of Liquefied Petroleum Gas (LPG) leaks is crucial in order to prevent accidents and safeguard human lives. LPG cylinders are so important to our everyday existence, making it essential for users to keep track of their gas levels to manage consumption effectively. Monitoring usage not only helps users stay informed about their LPG levels but also ensures timely booking of a new cylinder when needed. Given the high flammability of LPG, gas leakage poses serious risks, leading to accidents with potential loss of lives and property damage. To address these concerns, this project introduces a comprehensive LPG level monitoring system with leakage detection. These systems often utilize advanced sensors that can quickly and accurately identify the release of LPG. Additionally, smart systems may integrate with other technologies, such as communication modules, to alert users or authorities in real-time when leakage of gas is identified. Employing a load cell, the equipment constantly monitors the gas content of the cylinder and uses a GSM module to notify the consumer when the replacement needs to be scheduled. Upon receiving confirmation, the device takes appropriate action. Additionally, the system features gas sensors to detect LPG leakage, notifying the user via a GSM module, while activating alarms and exhaust mechanisms for added safety. © 2024 IEEE.

关键词： Liquefied petroleum gas

来源：评论

学校读者我要写书评

暂无评论

Enhanced Handover Management in 5G Networks using Machine Learning in Fading Scenarios 2

Enhanced Handover Management in 5G Networks using Machine Le...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Upadhyay, Deepak Rallapalli, Sreekanth Hussain, Zakir Venu, Nookala Sharma, Rashmi Shukla, Shipra Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of MCA Nitte Meenakshi Institute of Technology Bengaluru India Centre for Internet of Things Madhav Institute of Technology & Science Deemed University Gwalior India Nagpur Campus Pune India G. L. Bajaj Institute of Technology and Management Greater Noida India

ISBN: (纸本)9798331530389

This study explores the use of machine learning (ML) to improve initial handover performance for 5G networks by analysing fading-affected scenarios. In this study, we assess the ability of ML models to predict optimal handover decisions compared with conventional methods. In this study, simulation results show that our ML-based methods can reduce the handover inaccuracy by 50%, decrease latency up to 10 times and stabilize network performance. We accompany our assessment with a series of graphical analyses to show how ML algorithms change their behaviour dynamically in response to deteriorating link intensity due user mobility and increasing h/o frequency, thereby degrading the network performance. The results clearly illustrate that ML enabled handover optimization is significantly more effective than traditional methods in accommodating fading-channel dynamics, thereby improving both the network performance and user experience of future generation wireless networks. © 2025 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Resource Scheduling for Deterministic Communication and Computation Integration

Two-Stage Resource Scheduling for Deterministic Communicatio...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Weiting Tang, Nian Zhang, Chuan Guo, Ruibin Li, Mingyan Ying, Chenhao Jin, Jian Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Chongqing University College of Computer Science Chongqing400044 China Shanghai Jiao Tong University Department of Computer Science Shanghai200030 China Caict Research Institute of Industrial Internet of Things Beijing100095 China

ISBN: (纸本)9798350351255

In this paper, we investigate a resource orchestration and transmission scheduling problem for data-intensive services with diversified service requirements. A three-layer collaborative architecture is presented to support dynamic networking and computing resource allocation. To obtain optimal orchestration and scheduling policies, we formulate a constrained resource scheduling problem with the objective to maximizing resource utilization and scheduling success ratio. Since the complicated coupled constraints among decisions, we decouple the problem into a two-stage sub-problems of resource orchestration and transmission scheduling. To realize cross-domain resource orchestration and deterministic transmission of large-scale computing tasks, a two-stage resource scheduling scheme is proposed. Specifically, the first stage makes the resource orchestration decision by a greedy algorithm, and the second stage makes the transmission scheduling decision based on a deep reinforcement learning algorithm. Simulation results show that the proposed solution can effectively improve resource utilization and scheduling success ratio while satisfying diversified service requirements, as compared with benchmarks. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DAT: improving adversarial robustness via generative amplitude mix-up in frequency domain 24

DAT: improving adversarial robustness via generative amplitu...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Fengpeng Li Kemou Li Haiwei Wu Jinyu Tian Jiantao Zhou State Key Laboratory of Internet of Things for Smart City University of Macau Department of Computer Science City University of Hong Kong Faculty of Innovation Engineering Macau University of Science and Technology

ISBN: (纸本)9798331314385

To protect deep neural networks (DNNs) from adversarial attacks, adversarial training (AT) is developed by incorporating adversarial examples (AEs) into model training. Recent studies show that adversarial attacks disproportionately impact the patterns within the phase of the sample's frequency spectrum—typically containing crucial semantic information—more than those in the amplitude, resulting in the model's erroneous categorization of AEs. We find that, by mixing the amplitude of training samples' frequency spectrum with those of distractor images for AT, the model can be guided to focus on phase patterns unaffected by adversarial perturbations. As a result, the model's robustness can be improved. Unfortunately, it is still challenging to select appropriate distractor images, which should mix the amplitude without affecting the phase patterns. To this end, in this paper, we propose an optimized Adversarial Amplitude Generator (AAG) to achieve a better tradeoff between improving the model's robustness and retaining phase patterns. Based on this generator, together with an efficient AE production procedure, we design a new Dual Adversarial Training (DAT) strategy. Experiments on various datasets show that our proposed DAT leads to significantly improved robustness against diverse adversarial attacks. The source code is available at https://***/Feng-peng-Li/DAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

System-level Security Solution for Heterogeneous D2D-underlaid Cellular Network 15

System-level Security Solution for Heterogeneous D2D-underla...

引用

15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

作者： Feng, Shaohan Lu, Xiao Niyato, Dusit Wu, Yuan Wang, Wenbo Zhejiang Gongshang University School of Information and Electronic Engineering Hangzhou China Ericsson Research and Development Canada Nanyang Technological University School of Computer Science and Engineering Singapore University of Macau State Key Laboratory of Internet of Things for Smart City China Kunming University of Science and Technology School of Mechanical and Electrical Engineering Kunming China

ISBN: (纸本)9798350324662

This paper focuses on the problem of secure communications in a D2D-underlaid cellular network, where device-to-device (D2D) communication operates in a hybrid manner using both millimeter-wave (mmWave) and microwave frequency bands. To combat vigilant adversaries, we employ the technique of covert communication to conceal the presence of legitimate D2D transmissions. The D2D transmitters employ power control, communication-mode switching, and leverage the cellular signals to evade detection by adversaries. The conflict situation between the D2D transmitters and the adversaries is modeled as a Stackelberg game. To mathematically characterize the network's spatial configuration, we utilize the stochastic geometry modeling and consider a large-scale D2D-underlaid network, enabling a system-level analysis of communication strategies. We analyze the game equilibrium and thereafter search for equilibrium by using a bi-level algorithm. Insightful findings are drawn from numerical simulation results. © 2023 IEEE.

关键词： covert communication hybrid device-to-device communication stochastic geometry Wireless security

来源：评论

学校读者我要写书评

暂无评论

Prepartition: Load Balancing Approach for Virtual Machine Reservations in a Cloud Data Center

引用

Journal of computer science & technology 2023年第4期38卷 773-792页

作者：田文洪徐敏贤周光耀吴逵须成忠 Rajkumar Buyya School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu 610054China Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Department of Computer Science University of VictoriaVictoriaBCV8W 3P6Canada State Key Laboratory of Internet of Things for Smart City University of MacaoMacao 999078China School of Computing and Information Systems University of MelbourneMelbourne 3010Australia

Load balancing is vital for the efficient and long-term operation of cloud data *** virtualization,post(reactive)migration of virtual machines(VMs)after allocation is the traditional way for load balancing and consoli***,it is not easy for reactive migration to obtain predefined load balance objectives and it may interrupt services and bring ***,we provide a new approach,called Prepartition,for load *** partitions a VM request into a few sub-requests sequentially with start time,end time and capacity demands,and treats each sub-request as a regular VM *** this way,it can proactively set a bound for each VM request on each physical machine and makes the scheduler get ready before VM migration to obtain the predefined load balancing goal,which supports the resource allocation in a fine-grained *** with real-world trace and synthetic data show that our proposed approach with offline version(PrepartitionOff)scheduling has 10%–20%better performance than the existing load balancing baselines under several metrics,including average utilization,imbalance degree,makespan and Capacity_*** also extend Prepartition to online load *** results show that our proposed approach also outperforms state-of-the-art online algorithms.

关键词： cloud computing physical machine(PM) virtual machine(VM) reservation load balancing Prepartition

来源：评论

学校读者我要写书评

暂无评论

Literature Review of Circulating Current of Parallel Voltage Source Converters

Literature Review of Circulating Current of Parallel Voltage...

引用

PELS Students and Young Professionals Symposium (SYPS), IEEE

作者： Haoyu Zhang Man-Chung Wong Department of Electrical and Computer Engineering Faculty of Science and Technology State Key Laboratory of Internet of Things for Smart City University of Macau Macau China Department of Electrical Computer Engineering Faculty of Science and Technology State Key Laboratory of Internet of Things for Smart City University of Macau Macao China

To increase the power density of voltage source converters (VSC) usually use parallel structures. However, parallel VSC will easily introduce circulating current, which can cause a power efficiency decline. This paper gives a review of the circulating current and the solutions of it. Through the analysis of the principle of circulating current generation and the detail of the solutions, this paper gives an overview of the current research stage of circulating current. The technology can be divided into hardware solutions and software solutions are then analyzed and evaluated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Red Piranha Optimization Based Fast and Robust Fuzzy C-Means Clustering for Precise Glioma Segmentation in Therapeutic Applications 10

Red Piranha Optimization Based Fast and Robust Fuzzy C-Means...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Sophia, G. Ramaraj, Kottaimalai Karthikeyan, K. Prasath Alias Surendhar, S. Ambika, B. Thilagaraj, M. Mv J College of Engineering Department of Computer Science and Engineering Bengaluru India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamil Nadu Krishnankoil India Ramco Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Rajapalayam India Aarupadai Veedu Institute of Technology Department of Biomedical Engineering Tamil Nadu Chennai India Thiagarajar College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350384369

Gliomas have cells that resemble glial cells., which are normal brain cells. They are the prevalent kind of tumors;however., in patients with several years to live., they may be a lesser threat., or in patients with only two years to live., they may be more deadly. Chemotherapy and radiation are able to be utilized to decrease the development of brain tumors which are unable to be practically taken away even though medical intervention is still the preferred therapy for these tumors. Magnetic resonance imaging (MRI) for tumor diagnosis because they offer comprehensive images of the structure of the brain. Accurately segmenting tumors from MRls is crucial for both preparing for surgery and diagnostic purposes. Further investigations may not be able to justify manual tumor segmentation. Furthermore., tumor delineation can significantly influence the scheduling of treatment., rate of growth forecasting., and better diagnosis. The present study uses an integrated segmentation algorithm that combines optimization and clustering techniques. One method for creating clusters or groups of identical pixels is fuzzy C-means (FCM) clustering., an unsupervised learning technique. Fast and Robust FCM (FRFCM) addresses the drawbacks of traditional method. Red Piranha Optimization (RPO) is a recently introduced optimization technique that draws inspiration from nature and emulates the community-based hunting act of red piranhas. The suggested RPO-based FCM method was evaluated on a number of BraTS challenge datasets to guarantee its effectiveness. The results of the dissection are contrasted with the corresponding ground truth images. The enhanced dice score value of 92 % is obtained using the developed method. Medical professionals can use findings to help schedule surgical procedures., diagnose patients promptly, and treat them. © 2024 IEEE.

关键词： Chemotherapy

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：