检索结果-内蒙古大学图书馆

Optimal Deep Reinforcement Learning for Intrusion Detection in UAVs

computers, Materials & Continua 2022年第2期70卷 2639-2653页

作者： V.Praveena A.Vijayaraj P.Chinnasamy Ihsan Ali Roobaea Alroobaea Saleh Yahya Alyahyan Muhammad Ahsan Raza Department of Computer Science and Engineering Dr.N.G.P Institute of TechnologyCoimbatore641048India Department of Information Technology Vignan’s Foundation for ScienceTechnology&ResearchGuntur522213India Department of Information Technology Sri Shakthi Institute of Engineering and TechnologyCoimbatore641062India Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science Community College in DwadmiShaqra University11961Saudi Arabia Department of Information Technology Bahauddin Zakariya UniversityMultan60000Pakistan

In recent years,progressive developments have been observed in recent technologies and the production cost has been continuously *** such scenario,Internet of Things(IoT)network which is comprised of a set of Unmanned Aerial Vehicles(UAV),has received more attention from civilian tomilitary *** network security poses a serious challenge to UAV networks whereas the intrusion detection system(IDS)is found to be an effective process to secure the UAV *** IDSs are not adequate to handle the latest computer networks that possess maximumbandwidth and data *** order to improve the detection performance and reduce the false alarms generated by IDS,several researchers have employed Machine Learning(ML)and Deep Learning(DL)algorithms to address the intrusion detection *** this view,the current research article presents a deep reinforcement learning technique,optimized by BlackWidow Optimization(DRL-BWO)algorithm,for UAV *** addition,DRL involves an improved reinforcement learning-based Deep Belief Network(DBN)for intrusion *** parameter optimization of DRL technique,BWO algorithm is *** helps in improving the intrusion detection performance of UAV *** extensive set of experimental analysis was performed to highlight the supremacy of the proposed *** the simulation values,it is evident that the proposed method is appropriate as it attained high precision,recall,F-measure,and accuracy values such as 0.985,0.993,0.988,and 0.989 respectively.

关键词： Intrusion detection UAV networks reinforcement learning deep learning parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Secured Load Balanced Task Scheduling Approach for Fitness Service

引用

computers, Materials & Continua 2022年第5期71卷 2599-2616页

作者： Muhammad Ibrahim Faisal Jamil YunJung Lee DoHyeun Kim Big Data Research Center Department of Computer Science and StatisticsJeju National UniversityKoreaJeju-si63243Korea Department of Computer Engineering(and Advanced Technology Research Institute) Jeju National UniversityJeju 63243Korea

In recent times,the evolution of blockchain technology has got huge attention from the research community due to its versatile applications and unique security *** IoT has shown wide adoption in various applications including smart cities,healthcare,trade,business,*** these applications,fitness applications have been widely considered for smart fitness *** users of the fitness system are increasing at a high rate thus the gym providers are constantly extending the fitness ***,scheduling such a huge number of requests for fitness exercise is a big ***,the user fitness data is critical thus securing the user fitness data from unauthorized access is also *** overcome these issues,this work proposed a blockchain-based load-balanced task scheduling approach.A thorough analysis has been performed to investigate the applications of IoT in the fitness industry and various scheduling *** proposed scheduling approach aims to schedule the requests of the fitness users in a load-balanced way that maximize the acceptance rate of the users’requests and improve resource *** performance of the proposed task scheduling approach is compared with the state-of-the-art approaches concerning the average resource utilization and task rejection *** obtained results confirm the efficiency of the proposed scheduling *** investigating the performance of the blockchain,various experiments are performed using the Hyperledger Caliper concerning latency,throughput,resource *** Solo approach has shown an improvement of 32%and 26%in throughput as compared to Raft and Solo-Raft approaches *** obtained results assert that the proposed architecture is applicable for resource-constrained IoT applications and is extensible for different IoT applications.

关键词： Load balancing resource scheduling task scheduling Internet of things blockchain fitness applications

来源：评论

学校读者我要写书评

暂无评论

Link Connectivity based Reliability with Security in Autonomous Mobile Network

Link Connectivity based Reliability with Security in Autonom...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Sivasankar, C. Kumanan, T. Sekhar, Ch Chandra Srinivasan, T.R. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Dr Mgr Educational and Research Institute Department of Computer Science and Engineering Tamil Nadu Chennai India Ap Residential Degree College Department of Computer Science and Engineering Andhra Pradesh Guntur India Jimma Institute of Technology Jimma University Faculty of Electrical and Computer Engineering Department of Computer Engineering Jimma Ethiopia

ISBN: (纸本)9798350333602

Autonomous Mobile Network (AMN) contains mobile nodes which can predict the surrounding and forward the data to the receiver in undesirable conditions. AMN can observe, activate, calculate, and interconnect with others by applying point-to-point multi-hop transactions. Achieving such a fundamental agreement in a resource-constrained environment is a challenging problem since security methods always need additional energy and computational storage burdens. This paper proposes Link Connectivity based Reliability with Security (LCRS) in AMN to overcome this problem. This paper aims to detect abnormal nodes and improve link connectivity. The Link Connectivity Threshold (LCT) parameter estimates the link availability among the present sender and the subsequent forwarder node on the route to the destination. It selects the forwarder node by energy, link connectivity, and distance parameters. Furthermore, it isolates abnormal nodes using the lightweight Extended Kalman Filter (EKF) algorithm. This technique isolates the abnormal nodes and provides an effective route. The experimental outcomes demonstrate that the LCRS scheme diminishes the packet loss rate and delay. Furthermore, it raises the abnormal node detection ratio. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

MedFS: Pursuing Low Update Overhead via Metadata-Enabled Delta Compression for Log-structured File System on Mobile Device 23

MedFS: Pursuing Low Update Overhead via Metadata-Enabled Del...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Wu, Chao Ji, Cheng Chang, Li-Pin Zhu, Zongwei Gao, Congming Guo, Weichao Yu, Chao Wang, Yanzhi Department of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science National Yang Ming Chiao Tung University Taiwan Suzhou Institute for Advanced Research University of Science and Technology of China China School of Information Science Xiamen University China Guangdong Oppo Mobile Telecommunications Corp. Ltd. China College of Engineering Northeastern University United States

ISBN: (纸本)9781939133458

The increasing deployment of data-intensive applications on mobile devices poses a formidable challenge in designing flash-based file systems tailored to these needs. Studies have shown that adopting delta compression in log-structured file systems is promising for such an environment as it can effectively reduce the write stress and improve flash longevity. Unfortunately, delta compression suffers from large maintenance overhead. While prior works have introduced nonvolatile memory buffer or battery-backed DRAM to mitigate this, they are less appealing for cost-sensitive mobile devices. This paper introduces MedFS, a Metadata-enabled delta compression on log-structured File System for mobile devices, to achieve a good design trade-off in log-structured file systems employing delta compression. Through a comprehensive analysis of mobile applications and file update patterns, we develop delta-inlining technique, which consolidates delta updates within the inline area of the file's inode block. By leveraging the inherent inode structure and automatically flushing dirty inodes to storage, we effectively address the maintenance overhead associated with delta compression. Additionally, we propose a complementary delta maintenance strategy that selectively manages delta chunks in the data area, overcoming the space constraints of the inline area. Experimental results show that MedFS significantly reduces the write traffic by 55.1% on average, leading to the prolonged storage endurance by 122.7% and improved I/O performance by up to 37.3% over existing work. © 2025 FAST. All Rights Reserved.

关键词： Nonvolatile storage

来源：评论

学校读者我要写书评

暂无评论

The ForEx++ based decision tree ensemble approach for robust detection of Parkinson’s disease

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 11429-11453页

作者： Pramanik, Moumita Pradhan, Ratika Nandy, Parvati Bhoi, Akash Kumar Barsocchi, Paolo Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim Majitar737136 India Department of Computer Engineering Sikkim Institute of Science and Technology South Sikkim Jorethang India Department of Medicine Sikkim Manipal Institute of Medical Sciences Sikkim Manipal University Sikkim Gangtok737102 India Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim Majitar737136 India Institute of Information Science and Technologies National Research Council Pisa56124 Italy KIET Group of Institutions Delhi-NCR Ghaziabad201206 India Burla Sambalpur768018 India

The progressive reduction of dopaminergic neurons in the human brain, especially at the substantia nigra is one of the principal causes of Parkinson’s Disease (PD). Voice alteration is one of the earliest symptoms found in PD patients. Therefore, the impaired PD subjects’ acoustic voice signal plays a crucial role in detecting the presence of Parkinson's. This manuscript presents four distinct decision tree ensemble methods of PD detection on a trailblazing ForEx++ rule-based framework. The Systematically Developed Forest (SysFor) and a Penalizing Attributes Decision Forest (ForestPA) ensemble approaches has been used for PD detection. The proposed detection schemes efficiently identify positive subjects using primary voice signal features, viz., baseline, vocal fold, and time–frequency. A novel feature selection scheme termed Feature Ranking to Feature Selection (FRFS) has also been proposed to combine filter and wrapper strategies. The proposed FRFS scheme encompasses Gel’s normality test to rank and selects outstanding features from baseline, time–frequency, and vocal fold feature groups. The SysFor and ForestPA decision forests underneath the ForEx++ rule-based framework on both FRFS feature ranking and subset selection represents Parkinson’s detection approaches, which expedite a better overall impact on segregating PD from control subjects. It has been observed that the ForestPA decision forest in the ForEx++ framework on FRFS ranked features proved to be a robust Parkinson’s detection scheme. The proposed models deliver the highest accuracy of 94.12% and a lowest mean absolute error of 0.25, resulting in an Area Under Curve (AUC) value of 0.97. © 2022, The Author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Distributed Machine Learning System for Intrusion Detection 2

Distributed Machine Learning System for Intrusion Detection

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Patil, Harshal Lohumi, Yogesh Tejaswini, K.M. Sudheendramouli, H.C. Parikh, Swapnil Maranan, Ramya Sri Balaji University Pune India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Sri Siddhartha Institute of Technology Department of Mathematics Tumakuru India Gsss Simha SubbaMahalakshmi First Grade College Department of Computer Science and Application Mysuru India Parul University Department of Computer Science and Engineering Parul Institute of Engineering and Technology Post Limda India Saveetha School of Engineering Simats Department of Research and Innovation Chennai India

ISBN: (纸本)9798350373110

As network systems expand in complexity, the necessity for effective intrusion detection grows. This study compares two distributed machine learning systems utilizing different communication topologies: Parameter Server and Point-to-Point. The former employs centralized parameter management for efficient communication, while the latter facilitates direct node-to-node communication without a central server. Using extensive network traffic data, the models are assessed on performance metrics like accuracy, scalability, and false positive rates. Both systems show promising results, with median accuracy and F1 scores around 93%. However, limitations include potential data homogeneity issues, scalability challenges particularly with the Parameter Server becoming a bottleneck, concerns over model overfitting, and high computational overhead in maintaining models across numerous nodes. Addressing these drawbacks is crucial for improving the reliability of intrusion detection systems in complex network environments. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Advanced Recursive Spherical Quantization for Image Retrieval 20

Advanced Recursive Spherical Quantization for Image Retrieva...

引用

20th International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2023

作者： Fuchun, Wang Lei, Zhao Chaofeng, Yang Yu, Zhao Sichuan Artificial Intelligence Research Institute Yibin644000 China School of Computer Science and Technology Xinjiang University Urumqi830017 China The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798350318982

In recent years, quantization technology has proven to be very effective in the field of supervised image retrieval, owing to its capacity to provide both high accuracy and swift retrieval speeds. However, the challenge of balancing retrieval accuracy and speeds, as denoted by variable code lengths, persists as a fundamental consideration across different applications. Recently, there are a few methods that employ recursive strategies for quantization encoding, and there remains substantial room for improvement in their effectiveness. In this paper, we introduce the concept of a Recursive Spherical Quantization (RSQ) architecture, capable of generating sequential binary codes. It can reuse unit vector codebook to recursively quantize real vectors. Empirical findings from benchmark datasets demonstrate that our model is competitive or even superior performance in image retrieval, while simultaneously demanding a significantly reduced number of parameters. © 2023 IEEE.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

HERA: A Novel Heuristic Resource Allocator for Multi-SDM Multi-User Settings

HERA: A Novel Heuristic Resource Allocator for Multi-SDM Mul...

引用

2024 IEEE Conference on Standards for Communications and Networking, CSCN 2024

作者： Antoniadis, Christos Katsalis, Kostas Tyrovolas, Dimitrios Tegos, Sotiris A. Ioannidis, Sotiris Diamantoulakis, Panagiotis D. Karagiannidis, George K. Liaskos, Christos DOCOMO Euro-Labs Munich Germany Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki54124 Greece Technical University of Crete Dept. of Electrical and Computer Engineering Chania Greece Artificial Intelligence & Cyber Systems Research Center Lebanon University of Ioannina Computer Science Engineering Department Ioannina Greece Institute of Computer Science Foundation for Research and Technology Hellas Greece

ISBN: (纸本)9798331507428

The advent of Programmable Wireless Environments (PWEs) has transformed the wireless propagation phenomenon into a software-defined resource, leveraging Software-defined metasurfaces (SDMs). These new technologies have shown that wireless waves can be routed within a space, contrary to the regular, chaotic wireless propagation, yielding considerable benefits to communication efficiency, and even completely new applications. A new topic has risen, in the context of modeling these capabilities as network resources, and allocating them to users. In this context, the present paper contributes HERA, a heuristic resource allocator that receives a setup with users and SDMs as input, and produces the necessary configuration of the latter, for efficient shared performance. Simulation results demonstrate considerable efficiency in this task, while the heuristic nature of HERA sets the basis for a flexible definition of complex user objectives in the future. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

The PSG challenge: towards comprehensive scene understanding

引用

National science Review 2023年第6期10卷 41-44页

作者： Jingkang Yang Zheng Ma Qixun Wang Xiaofeng Guo Haofan Wang Ziwei Liu Wayne Zhang Xing Xu Hai Zhang Sense Time Research S-Lab Nanyang Technological University Xiaohongshu Inc Institute of Optics and Electronics Chinese Academy of Sciences School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION Most computer vision tasks currently focus on recognizing objects in *** instance,image classification only needs to identify the main object in an image [1],while object detection and image segmentation only require models to locate objects in images [2].However,these tasks are insufficient to achieve a comprehensive and in-depth understanding of a *** example,in ***(i),a model that only detects people,elephants,fences and trees would not have an understanding of the scene, making it unable to provide safety reminders such asnot to feed the *** many realworld AI applications like smart cities,autonomous driving and smart manufacturing,it is crucial to not only localize targets in the scene but also reason and predict their *** example,in autonomous driving,it is important to analyze whether pedestrians on the side of the road are pushing or riding *** smart factories,it is necessary to judge whether operators are working *** these relations is vital for decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Assessment of the Security Benefits of Secure Shell (SSH) in Wireless Networks 3

An Assessment of the Security Benefits of Secure Shell (SSH)...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Preetha, M. Dhabliya, Dharmesh Lone, Zeeshan Ahmad Pandey, Sakshi Acharjya, Kalyan Gowrishankar, J. Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science Engineering Faculty of Engineering and Technology Karnataka Ramnagar India

ISBN: (纸本)9798350319125

Comfortable Shell (SSH) is a community protocol that provides relaxed communique over an unsecured community, such as the internet. This protocol is generally used for far flung login, file switch, and remote command execution, making it a vital device for managing and securing networks. Wi-Fi networks, which rely upon radio frequency indicators for verbal exchange, are prone to various safety threats such as eavesdropping, spoofing, and man-in-themiddle assaults. This makes using relaxed protocols like SSH critical for protective sensitive statistics and keeping the integrity of Wi-Fi networks. This technical assessment evaluates the safety advantages of utilizing SSH in wireless networks. First of all, SSH makes use of strong encryption algorithms consisting of AES and RSA to encrypt the whole communique session, ensuring that records is transmitted securely between devices. This prevents attackers from intercepting and reading touchy records exchanged among gadgets. Secondly, SSH makes use of a public-key infrastructure for authentication, that's more at ease than conventional password-based totally authentication. This is because the private key, which is used for authentication, is not transmitted all through the login system, making it greater tough for attackers to advantage get entry to the network. © 2023 IEEE.

关键词： Authentication

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：