检索结果-内蒙古大学图书馆

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification Approaches for Intrusion Detection in IoT-Driven Aerial Computing Environment

Multiclass Classification Approaches for Intrusion Detection...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Saksham Mittal Amit Kumar Mishra Mohammad Wazid D. P. Singh Ashok Kumar Das Sachin Shetty Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad India Department of Modeling Simulation and Visualization Engineering Virginia Modeling Analysis and Simulation Center Center for Cybersecurity Education and Research Old Dominion University Suffolk VA USA

Aerial Computing is one of the applications of Internet of Things (IoT) which makes use of autonomous aerial devices, such as drones and unmanned aerial vehicles (UAVs). The ubiquitous nature of IoT and aerial computing is poised to revolutionize our daily lives by enabling seamless real-time information sharing among interconnected objects. However, ensuring the safety and security of such network is crucial in preventing potential threats and attacks. The purpose of this study is to develop a sophisticated intrusion detection system that is effective, efficient, and intelligent using complex machine learning models trained on relevant intrusion detection datasets. In this article, the multiclass classification approaches for intrusion detection in IoT-driven aerial computing environment are presented (in short, MCA-IDAC). In the comparative study, it has been observed that proposed MCA-IDAC performs significantly better than the other existing competing schemes, in terms of important performance parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Fixed Broadband Wireless Access in mmWave Band in 5G

Performance Analysis of Fixed Broadband Wireless Access in m...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Soumya Banerjee Sarada Prasad Gochhayat Sachin Shetty Virginia Modeling Analysis and Simulation Center Old Dominion University Norfolk VA USA Department of Electrical and Computer Engineering Villanova University Villanova PA USA

An end-to-end fiber-based network has the potential to offer multi-gigabit fixed access to end users. However, a fiber network’s biggest hurdle is delivering that fiber access to the end user. Especially in places where fiber is non-existent, it can be time-consuming and costly to deploy, resulting in Operators experiencing a long delay in realizing a return on their *** work investigates transmission data from fixed broadband wireless access in the mmWave band in 5G. With the increasing interest in this domain, it is worth investigating the transmission characteristic of the data and utilizing the same to build more sophisticated capabilities. Existing datasets for the mmWave band are detailed but generated from simulated environments. In this work, we introduce a dataset built from the collection of real-world transmission data from fixed broadband wireless access in mmWave band device(RWM6050). The goal of this data is to enable self-configuration capability based on transmission characteristics. Towards this goal, we present an online machine learning-based approach that can classify transmission characteristics with real-time training. We also present two more advanced temporal models for more accurate classifications. We demonstrate that it is possible to detect the transmission angle and distance directly from the analysis of transmission data with very high accuracy. We achieved up to 99% accuracy on the combined classification task. Finally, we outline some interesting future research scopes based on the collected data.

关键词： Wireless communication Training Solid modeling 5G mobile communication Machine learning Optical fiber networks Real-time systems

来源：评论

学校读者我要写书评

暂无评论

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Transmission Power Control for Interference Reduction in Cellular D2D Networks

Transmission Power Control for Interference Reduction in Cel...

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Mehrdad Sadehvand Neda Moghim Behrouz Shahgholi Ghahfarokhi Sachin Shetty Department of Computer Engineering University of Isfahan Isfahan I.R.Iran Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk USA

Interference is one of the most critical issues in the cellular Device-to-Device (D2D) networks. The sharing of radio resources in cellular and D2D communications offers spectrum efficiency advantages for the cellular network. However, resource sharing also introduces interference, leading to a reduction in the quality of service experienced by users. In this paper, we propose an adversarial Multi-Armed Bandit learning-based transmission Power Control method called MAB-PC for both cellular and D2D transmitters. The objective of this method is to ensure the minimum service quality for users, considering the minimum spectral efficiency and maximum block error rate. Additionally, to address the conflicting objectives of D2D and cellular communications, MAB-PC is modeled as a Pareto optimization problem for D2D transmitters. MAB-PC is a distributed method that minimizes signaling overhead and relies solely on local Channel State Information (CSI). The effectiveness of the proposed method is evaluated based on reliability, total data rate, spectral efficiency, block error rate, and outage probability, demonstrating superior performance compared to its counterpart.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Provably Secure and Lightweight Access Control Protocol for EI-Based Vehicle to Grid Environment

引用

IEEE Internet of Things Journal 2023年第18期10卷 16650-16657页

作者： Shamshad, Salman Mahmood, Khalid Shamshad, Usman Hussain, Ibrar Hussain, Shafiq Das, Ashok Kumar The University of Lahore Department of Software Engineering Lahore54590 Pakistan National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan Riphah International University Riphah School of Computing and Innovation Lahore54000 Pakistan University of Sahiwal Department of Computer Science Sahiwal57000 Pakistan International Institute of Information Technology Hyderabad Center for Security Theory and Algorithmic Research Hyderabad500032 India Old Dominion University Virginia Modeling Analysis and Simulation Center SuffolkVA23435 United States

The energy Internet (EI) presents a novel paradigm for renewable energy distribution that utilizes communication and computing technologies to revolutionize the conventional intelligent transportation systems (ITSs) and power grid into a structure that provides assistance to open innovation. The EI offers sustainable and bidirectional transmission for the improvement and analysis of energy convention among electric vehicles (EVs) and service providers. To ensure efficient, reliable, and secure operation, EI must be safe from security attacks. Therefore, efficient and secure key negotiation is a significant issue for the EI-based Vehicle-to-Grid (V2G) architecture. Thus, to ensure the system's security, we have devised a robust scheme to facilitate a secure key agreement between the entities involved for the secure and efficient renewable energy distribution for the EI-based energy vehicles in V2G. The devised scheme's robustness is solicited through the widely accepted formal random or real (RoR) model. In addition, the informal security analysis is conducted on the devised scheme, which is evident that the designed scheme achieves all the required security features of EI-based ITS. Moreover, the performance evaluation results endorse that the designed scheme achieves the desired security and minimizes the communication, computation, and energy overhead by 29.33%, 27.94%, and 28.08% in comparison to the existing competitive schemes. © 2014 IEEE.

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Xu, Mengchu Zeng, Yan Xue, Meiting Zhang, Ji-Lin Wan, Jian Zhou, Mingyao Wen, Yilin Shi, Yukun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China Hangzhou Dianzi University School of Cyberspace Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

ISBN: (纸本)9798350345384

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms. © 2023 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Fixed Broadband Wireless Access in mmWave Band in 5G

arXiv

引用

arXiv 2023年

作者： Banerjee, Soumya Gochhayat, Sarada Prasad Shetty, Sachin Virginia Modeling Analysis and Simulation Center Old Dominion University NorfolkVA United States Department of Electrical and Computer Engineering Villanova University VillanovaPA United States

An end-to-end fiber-based network has the potential to offer multi-gigabit fixed access to end-users. However, a fiber network’s biggest hurdle is delivering that fiber access to the end-user. Especially in places where fiber is non-existent, it can be time-consuming and costly to deploy, resulting in Operators experiencing a long delay in realizing a return on their investment. This work investigates transmission data from fixed broadband wireless Access in mmWave band in 5G. With the increasing interest in this domain, it is worth investigating the transmission characteristic of the data and utilizing the same to build more sophisticated capabilities. Existing datasets for mmWave band are detailed but generated from simulated environments. In this work, we introduce a dataset built from the collection of real-world transmission data from Fixed Broadband Wireless Access in mmWave Band device(RWM6050). The goal of this data is to enable self-configuration capability based on transmission characteristics. Towards this goal, we present an online machine learning-based approach that can classify transmission characteristics with real-time training. We also present two more advanced temporal models for more accurate classifications. We demonstrate that it is possible to detect the transmission angle and distance directly from the analysis of transmission data with very high accuracy. We achieved up to 99% accuracy on the combined classification task. Finally, we outline some interesting future research scopes based on the collected data. © 2023, CC BY-NC-ND.

关键词： Fibers

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Artificial Intelligence Framework for Proactive Detection and Risk Explanation of Cyber Attacks in Smart Grid

Trustworthy Artificial Intelligence Framework for Proactive ...

引用

simulation Winter Conference

作者： Md. Shirajum Munir Sachin Shetty Danda B. Rawat Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA Department of Electrical and Computer Science Howard University Washington D.C. USA

The rapid growth of distributed energy resources (DERs), such as renewable energy sources, generators, consumers, and prosumers in the smart grid infrastructure, poses significant cybersecurity and trust challenges to the grid controller. Consequently, it is crucial to identify adversarial tactics and measure the strength of the attacker’s DER. To enable a trustworthy smart grid controller, this work investigates a trustworthy artificial intelligence (AI) mechanism for proactive identification and explanation of the cyber risk caused by the control/status message of DERs. Thus, proposing and developing a trustworthy AI framework to facilitate the deployment of any AI algorithms for detecting potential cyber threats and analyzing root causes based on Shapley value interpretation while dynamically quantifying the risk of an attack based on Ward’s minimum variance formula. The experiment with a state-of-the-art dataset establishes the proposed framework as a trustworthy AI by fulfilling the capabilities of reliability, fairness, explainability, transparency, reproducibility, and accountability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EXPLORING XENOPHOBIC EVENTS THROUGH GDELT DATA ANALYSIS

arXiv

引用

arXiv 2023年

作者： Jayanetti, Himarsha R. Frydenlund, Erika Weigle, Michele C. Department of Computer Science Old Dominion University NorfolkVA United States Virginia Modeling Analysis and Simulation Center Old Dominion University SuffolkVA United States

This study explores xenophobic events related to refugees and migration using the GDELT 2.0 database and APIs through visualizations. We conducted two case studies – the first being an analysis of refugee-related news following the death of a two-year-old Syrian boy, Alan Kurdi, and the second a surge in news articles in March 2021 based on the data obtained from GDELT API. In addition to the two case studies, we present a discussion of our exploratory data analysis steps and the challenges encountered while working with GDELT data and its tools. © 2023, CC BY-NC-SA.

关键词： Big data

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：