检索结果-内蒙古大学图书馆

6th international symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2022

作者： Khudhayer, Yasameen Marhoon, Haydar Abdulameer University of Karbala Dept. of Computer Science College of Computer Science and Information Technology Karbala Iraq Al-Ayen University Information and Communication Technology Research Group Scientific Research Center Thi-Qar Iraq

ISBN: (数字)9781665470131

ISBN: (纸本)9781665470131

In the last few years, numerous applications of wireless sensor networks that make use of a variety of data transfer protocols have been created in the commercial and industrial sectors. Because the sensor nodes have a finite amount of energy, it is necessary for wireless sensor networks to implement large data transmission delays to prolong the lifetime of the network. With a WSN, many sensor nodes can be set up in a sensor field, where they can collect data, process it, and then send it on to a designated sink node. Battery power is what keeps sensor nodes going, which is why WSNs rely heavily on routing algorithms. WSNs can be categorized into three distinct types of routing strategies: flat, clustering, and geographic. Clustering routing, of which chain-based routing is a subset, has a wide range of practical applications, including volcanology (area planning), seismology (earthquake measurement), and more. The Deterministic Chain-Based Routing Protocol (DCBRP), the Energy-Efficient Two-Stage Chain Routing Protocol (TSCP), and the Deterministic Power-Efficient Gathering in Sensor Information systems (PEGASIS) are just a few of the algorithms discussed in this article, along with a new method of data transmission for chain-based routing in WSN. These statistics are transmitted based on the nodes' remaining energy and their distance from the sink node. Efficient Time-Sensitive Routing Protocol (ETSRP) is a newly proposed technology that reduces end-To-end delay while simultaneously reducing energy consumption and extending the lifetime of a network. When compared to other proposed solutions, ETSRP can reduce the network's energy usage and extend the network's lifetime. © 2022 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Adaptive Devices for AIoT systems

Adaptive Devices for AIoT Systems

引用

2021 international symposium on Intelligent Signal Processing and Communication systems, ISPACS 2021

作者： Hung, Li-Ling Computer Science and Information Engineering Aletheia University New Taipei Taiwan

ISBN: (纸本)9781665419512

Internet of Things (IoT) systems and Artificial Intelligence of Things (AIoT) systems are applied in wide range nowadays. This paper proposes developing adaptive devices for AIoT systems. The adaptive devices include adaptive sensing devices for IoT systems and adaptive gateway in the systems. These adaptive devices have good use to balance the traffic in heterogeneous AIoT systems. In our preliminary evaluations, the transmission efficiency of AIoT systems is improved using proposed devices. Because balancing the transmissions in the networks, the cost efficiency is much better than original AIoT systems. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

international Conference on Parallel and distributed systems (ICPADS)

作者： Ronghuan Zhang Jing Zhao Ming Li Qingzhi Zou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity.

关键词： Accuracy Computational modeling Memory management Neural networks Feature extraction Transformers Sensors Data mining Computational complexity Remote sensing

来源：评论

学校读者我要写书评

暂无评论

DONS: Dynamic Optimized Neighbor Selection for smart blockchain networks

引用

FUTURE GENERATION computer systems-THE international JOURNAL OF ESCIENCE 2022年 130卷 75-90页

作者： Baniata, Hamza Anaqreh, Ahmad Kertesz, Attila Univ Szeged Dept Software Engn H-6720 Szeged Hungary Univ Szeged Dept Computat Optimizat H-6720 Szeged Hungary

Blockchain (BC) systems mainly depend on the consistent state of the distributed Ledger (DL) at different logical and physical places of the network. The majority of network nodes need to be enforced to use one or both of the following approaches to remain consistent: (i) to wait for certain delays (i.e. by requesting a hard puzzle solution as in PoW and PoUW, or to wait for random delays as in PoET, etc.) (ii) to propagate shared data through shortest possible paths within the network. The first approach may cause higher energy consumption and/or lower throughput rates if not optimized, and in many cases these features are conventionally fixed. Therefore, it is preferred to enhance the second approach with some optimization. Previous works for this approach have the following drawbacks: they may violate the identity privacy of miners, only locally optimize the Neighbor Selection method (NS), do not consider the dynamicity of the network, or require the nodes to know the precise size of the network at all times. In this paper, we address these issues by proposing a Dynamic and Optimized NS protocol called DONS, using a novel privacy-aware leader election within the public BC called AnoLE, where the leader anonymously solves the The Minimum Spanning Tree problem (MST) of the network in polynomial time. Consequently, miners are informed about the optimum NS according to the current state of network topology. We analytically evaluate the complexity, the security and the privacy of the proposed protocols against state-of-the-art MST solutions for DLs and well known attacks. Additionally, we experimentally show that the proposed protocols outperform state-of-the-art NS solutions for public BCs. Our evaluation shows that the proposed DONS and AnoLE protocols are secure, private, and they acutely outperform all current NS solutions in terms of block finality and fidelity. (C) 2021 The Author(s). Published by Elsevier B.V.

关键词： Smart networking Blockchain Optimized neighbor selection Minimum Spanning Tree Anonymized Leader Election

来源：评论

学校读者我要写书评

暂无评论

DDPG-Based UAV Path Planning for Data Collection in Emergency IoT networks

DDPG-Based UAV Path Planning for Data Collection in Emergenc...

引用

computer Engineering and Intelligent Communications (ISCEIC), international symposium on

作者： Jiageng Han Chunhui Liu Yu Deng Institute of Unmanned Systems Beihang University School of Electronics and Information Engineering Beihang University Beijing China

ISBN: (数字)9798331518677

ISBN: (纸本)9798331518684

With the rapid development of VAV technology and the Internet of Things (IoT), the application of VAVs in emergency scenarios has become a research hotspot. In emergency situations, how to efficiently plan UAV flight paths to assist in collecting data from ground sensors has become a key issue to ensure a swift re-sponse to emergency actions. Traditional path planning methods often fail to adapt to complex and dynamic emergency environments. Therefore, based on the Deep Deterministic Policy Gradient (DDPG) algorithm, we introduce a Prioritized Experience Re-play (PER) network to improve learning efficiency, and propose a novel end-to-end reinforcement learning (RL) UAV path planning algorithm for data collection from IoT devices in emergency sce-narios.

关键词： Training Heuristic algorithms Reinforcement learning Data collection Autonomous aerial vehicles Path planning Sensors Planning Internet of Things Trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

Light-Weight Permutation Generator for Efficient Convolutional Neural Network Data Augmentation 1

引用

18th international symposium on Applied Reconfigurable Computing

作者： Kwan, Bowen P. Y. Guo, Ce Luk, Wayne Jiang, Peiyong Imperial Coll London Dept Comp London England Ctr Novost Hong Kong Sci Pk Hong Kong Peoples R China Chinese Univ Hong Kong Li Ka Shing Inst Hlth Sci Hong Kong Peoples R China

ISBN: (数字)9783031199837

ISBN: (纸本)9783031199820;9783031199837

Permutation is a fundamental way of data augmentation. However, it is not commonly used in image based systems with hardware acceleration due to distortion of spatial correlation and generation complexity. This paper proposes Restricted Permutation Network (RPN), a scalable architecture to automatically generate a restricted subset of local permutation, preserving the features of the dataset while simplifying the generation to improve scalability. RPN reduces the spatial complexity from O(Nlog(N)) to O(N), making it easily scalable to 64 inputs and beyond, with 21 times speed up in generation and significantly reducing data storage and transfer, while maintaining the same level of accuracy as the original dataset for deep learning training. Experiments show Convolutional Neural networks (CNNs) trained by the augmented dataset can be as accurate as the original one. Combining three to five networks in general improves the network accuracy by 5%. Network training can be accelerated by training multiple sub-networks in parallel with a reduced training data set and epochs, resulting in up to 5 times speed up with a negligible loss in accuracy. This opens up the opportunity to easily split long iterative training process into independent parallelizable processes, facilitating the trade off between resources and run time.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Distribution Key Scheme for Secure Group Management in VANET Using Polynomial Interpolation

Distribution Key Scheme for Secure Group Management in VANET...

引用

7th international symposium on Security and Privacy in Social networks and Big Data, SocialSec 2021

作者： Kumar, Ankit Singh, Kamred Udham Hsieh, Sun-Yuan Kumar, V. D. Ambeth Kumar, Abhishek Department of Computer Science and Engineering Swami Keshvanand Institute of Technology Management and Gramothan Jaipur India Department of Computer Science and Information Engineering National Cheng Kung University Tainan701 Taiwan Department of Computer Science and Information Engineering Institute of Medical Information Institute of Manufacturing Information and Systems Center for Innovative FinTech Business Models and International Center for the Scientific Development of Shrimp Aquaculture National Cheng Kung University No. 1 University Road Tainan70101 Taiwan Department of Computer Science and Engineering Panimalar Engineering College Anna University Chennai India Bengaluru India

ISBN: (纸本)9789811679124

Security is a major concern for vehicular ad hoc networks (VANETs). Group-based communications in VANETs is a commonly investigated topic. Creating a group and distributing a key to numerous fast-moving vehicles for secure communication is a major security challenge for VANETs. distributed keys in VANETs allow for the secure participation of vehicles that may not have been present when the group was formed. This paper presents a new distributed key scheme for secure group management in VANET by using polynomial interpolation. The proposed scheme not only provides a distributed key for vehicles to be created, to join, and to communicate in the group but also provides and manages the distribution of keys to maintain the security of VANETs. The experimental results reveal that the proposed scheme is a secure solution for group communication in VANETs. © 2021, Springer Nature Singapore Pte Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Evaluation Framework for Assessing IPFS Performance within a Blockchain-Based Healthcare System

An Evaluation Framework for Assessing IPFS Performance withi...

引用

IEEE international Conference on Blockchain (Blockchain)

作者： Ghassan Al-Sumaidaee Rami Alkhudary Zeljko Zilic Andraws Swidan ECE. McGill University Montreal Canada Université Paris-Panthéon-Assas LARGEPA Paris France Department of Computer Engineering University of Jordan Amman Jordan

Blockchain applications require metadata to be associated with the blockchain ledger. Metadata is often stored in centralized cloud servers, which limits the decentralization of the blockchain. Alternatively, metadata can be integrated into distributed storage systems to achieve full decentralization of blockchain networks. However, evaluating the performance of distributed storage systems is often neglected. To address this gap, we present a framework that includes a set of technical indicators. We specifically focus on the InterPlanetary File System (IPFS) as an illustrative distributed storage system and provide a practical use case to demonstrate the application of our framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection Model for RISC-V in Automotive Applications: A Domain-Specific Accelerator Perspective

An Anomaly Detection Model for RISC-V in Automotive Applicat...

引用

Euromicro Conference on Parallel, distributed and Network-Based Processing

作者： Elio Vinciguerra Enrico Russo Maurizio Palesi Giuseppe Ascia Department of Electrical Electronic and Computer Engineering University of Catania Catania Italy

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

Early anomaly detection in automotive systems is crucial for enhancing user safety and enabling timely corrective actions, thereby minimizing the risks associated with system malfunctions. This paper presents an approach for implementing Artificial Intelligence (AI)-based algorithms for anomaly detection in the automotive domain, leveraging the RISC-V architecture in conjunction with Domain-Specific Accelerators (DSAs). By exploiting the efficiency of DSAs, the proposed system aims to achieve faster anomaly detection compared to traditional processing methods. A detailed comparison is conducted between the performance of executing the AI-based anomaly detection algorithm on the RISC-V core versus offloading it to an optimized hardware accelerator tailored to the specific AI model. The goal of this work is to provide valuable insights into the potential of RISCV and DSAs to enhance AI-driven safety mechanisms, contributing to the development of more reliable automotive systems.

关键词： Program processors Neural networks Real-time systems Safety Reliability Artificial intelligence Anomaly detection Hardware acceleration Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of YOLOv9 and YOLOv10 Algorithms for Urban Safety Improvement

Comparative Analysis of YOLOv9 and YOLOv10 Algorithms for Ur...

引用

international symposium on Intelligent systems and Informatics (SISY)

作者： Matko Glučina Nikola Žigulic Domagoj Frank Ivan Lorencin Dario Matika Department of Engineering Istrian University of Applied Sciences Pula Croatia Faculty of Engineering University of Rijeka Rijeka Croatia Department of Computer Science and Informatics University North Koprivnica Croatia Faculty of Informatics Juraj Dobrila University of Pula Pula Croatia Department of Electrical engineering University North Varazdin Croatia

ISBN: (数字)9798350385601

ISBN: (纸本)9798350385618

Individual safety in urban and city centers is one of the fundamental rights of every person. Today's innovations open up various possibilities for improving the quality of life and safety, but if they are not applied, they carry the danger of an additional increase in crime or greater insecurity in urban centers. This investigation aims to apply insights into the anticipation of illegal actions by various criminal groups that use illegal means, such as weapons, to get property that does not belong to them. In this research, computer vision and advanced strategies such as YOLOv10 and YOLOv9 are used to compare their properties and performance for improving security in urban and populated areas. The best results were achieved by YOLOv9m with a high percentage of mean average precision in the amount of 0.923, while the worst performance was shown by YOLOv10n with a mean average precision of 0.902. Precision and recall for the YOLOv9 and YOLOv10 models were also taken into account and the results are as follows: 0.984.. 0.993.. 0.979.. and 0.996.

关键词： Technological innovation computer vision Weapons Urban areas Artificial neural networks Safety Security Intelligent systems Informatics

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：