检索结果-内蒙古大学图书馆

coverage hole detection in WSN with force-directed algorithm and transfer learning

APPLIED INTELLIGENCE 2022年第5期52卷 5435-5456页

作者： Lai, Yue-Hui Cheong, Se-Hang Zhang, Hui Si, Yain-Whar Univ Macau Macau Peoples R China BNU HKBU United Int Coll Zhuhai Peoples R China

coverage hole detection is an important research problem in wireless sensor network research community. However, distributed approaches proposed in recent years for coverage hole detection problem have high computational complexity. In this paper, we propose a novel approach for coverage hole detection in wireless sensor networks called FD-TL (Force-directed and Transfer-learning) which is based on layout generation capability of Force-directed Algorithms and image recognition power of Convolutional Neural Network with transfer learning. In contrast to existing approaches, the proposed approach is a pure topology-based approach since FD-TL can detect both triangular and non-triangular coverage holes from a wireless sensor network based on the input network topology without relying on the physical locations of the anchor nodes. In FD-TL, a Force-directed Algorithm is used to generate a series of possible layouts from a given input topology. Next, a Convolutional Neural Network is used to recognize potential coverage holes from the generated layouts. During the training phase, a transfer learning method is used to aid the recognition process. Experimental results show that FD-TL method can achieve 90% sensitivity and 96% specificity for coverage hole detection in wireless sensor networks.

关键词： Wireless sensor networks coverage hole detection Force-directed algorithm Convolutional neural network Transfer learning

来源：评论

学校读者我要写书评

暂无评论

coverage hole detection using social spider optimized Gaussian Mixture Model

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第10期34卷 9814-9821页

作者： Gupta, Abhishek Kumar, Somesh Pattanaik, Manisha ABV Indian Inst Informat Technol Management Gwalior India

Wireless sensors are backed by their battery life. The battery depletion creates a communication hole in the network. The replacement of certain energy-depleted sensor nodes necessitates their detection. The work in this article presents a novel solution for the detection of coverage hole in the WSN. An undirected graph was employed in this study to divide the WSN region into two parts: the outer and inner nodes. The Gaussian Mixture Model (GMM) clustering detects the outer/edge nodes at the coverage hole area. Node degree, closeness, betweenness, and page rank are the four graph metrics that GMM uses for clustering in this work. GMM's clustering performance is governed by the static mean and covariance. A novel combination of social spider optimization and GMM is then leveraged to fine-tune the cluster to decrease false detection rates of holes. Distinct holes, such as round, E-shape, and rectangular, are used to conduct the analysis. Using the SSO-EM GMM approach, the comparison shows that it outperforms the current methods of coverage hole identification. (c) 2021 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： coverage hole detection Social spider optimization Gaussian Mixture Model WSN Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

coverage hole detection Algorithm without Location Information in Wireless Sensor Networks 3

Coverage Hole Detection Algorithm without Location Informati...

引用

3rd IEEE International Conference on Computer and Communications (ICCC)

作者： Ma, Wenyu Yan, Feng Zuo, Xuzhou Ren, Liwei Xia, Weiwei Shen, Lianfeng Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Jiangsu Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Sichuan Peoples R China CSIC Res Inst 724 Nanjing 211106 Jiangsu Peoples R China

ISBN: (纸本)9781509063529

In this paper, we propose a simple and accurate coverage hole detection algorithm without location information for wireless sensor networks. The coverage hole detection algorithm consists of two components, named boundary edge detection and boundary cycle detection. In the first component, we use a graph to model the wireless sensor network, and each edge in the graph is checked to determine whether it is a boundary edge or not. In the second component, the boundary cycles of all coverage holes are discovered to localize each coverage hole. By comparing with a location based algorithm, it is shown that our proposed algorithm can accurately detect over 99% coverage holes.

关键词： coverage hole detection coverage wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Greedy Approach for coverage hole detection and Restoration in Wireless Sensor Networks

引用

WIRELESS PERSONAL COMMUNICATIONS 2018年第1期101卷 75-86页

作者： Verma, Manoj Sharma, Sanjay Maulana Azad Natl Inst Technol Dept Math & Comp Applicat Bhopal India

Wireless sensor network contains several small sensor nodes that are designed to work autonomously. coverage preservation is an underlying requirement to efficiently deliver certain services in WSNs. During network operation, some sensor nodes die because of several reasons like energy exhaustion, link failure, node failure etc. We refer it as coverage hole problem of WSNs. In this paper, a new decentralized, node based, localized algorithm called coverage hole detection and Restoration is proposed for detection as well as restoration of coverage holes. Our proposed algorithm is expected to outperform existing algorithms on the parameters of energy and time consumption for convex and non-convex holes.

关键词： Wireless sensor networks coverage hole problem coverage hole detection coverage hole restoration

来源：评论

学校读者我要写书评

暂无评论

Confident information coverage hole detection in sensor networks for uranium tailing monitoring

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2018年第Part1期118卷 57-66页

作者： Yi, Lingzhi Deng, Xianjun Zou, Zenghui Ding, Dexin Yang, Laurence T. Univ South China Sch Civil Engn Hengyang Hunan Peoples R China Univ South China Dept Commun Engn Hengyang Hunan Peoples R China Univ South China Sch Environm Protect & Safety Engn Hengyang Hunan Peoples R China St Francis Xavier Univ Antigonish NS Canada St Francis Xavier Univ Dept Comp Sci Antigonish NS Canada

The wireless sensor networks recently abstract great attention and are used for a wide range of cyberenabled applications each of which with rigid accuracy requirements. The emergence and existence of coverage holes in WSNs will dramatically degrade the network coverage performance and quality of service. To diminish the negative effects of coverage holes, this paper addresses and studies the confident information coverage hole detection problem (CICHD) based on the proposed novel confident information coverage model (CIC). For solving the CICHD problem, we design two effective heuristic CIC holes detection algorithms including the CHD without considering the nodes residual energy and the other CHDRE taking the nodes' residual energy into account. In the both proposed algorithms, the sensing field is firstly partitioned into a series of reconstruction grids based on the spatial correlation and correlation range. Then each reconstruction grid will be scanned and detected based on the CIC model to be judged whether it is a hole. Once obtaining the coverage status of every reconstruction grid, the boundary of the coverage hole will be exacted by image processing method. The results of the simulations show that both the proposed schemes can efficiently detect the emerged coverage holes including the locations and the number, and the CHDRE algorithm is more practical and efficient compared to the CHD without considering the energy problem. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Confident information coverage coverage hole detection Sensor networks Cyber-enabled applications

来源：评论

学校读者我要写书评

暂无评论

Connectivity Based k-coverage hole detection in Wireless Sensor Networks

引用

MOBILE NETWORKS & APPLICATIONS 2020年第2期25卷 783-793页

作者： Yan, Feng Ma, Wenyu Shen, Fei Xia, Weiwei Shen, Lianfeng Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai Peoples R China

A connectivity based k-coverage hole detection algorithm is proposed in this paper. We adopt Rips complex in homology theory to model a wireless sensor network (WSN). We firstly present a simplicial complex reduction algorithm to simplify the network topology by vertex and edge deletion, while keeping the homology intact. Then a connectivity-based algorithm is proposed for discovering boundary cycles of non-triangular k-coverage holes. The algorithm consists of two parts, one part is 1-coverage hole detection and the other part is coverage degree reduction. In the 1-coverage hole detection part, boundary cycles of 1-coverage holes are found. In the coverage degree reduction part, an independent covering subset of nodes for the covered region is found and these nodes are set to dormant state to decrease the coverage degree of the target region by one. The k-coverage hole detection algorithm is an iterative process of the two parts. Computation complexity of the algorithm is analyzed and simulation results show that more than 95% of non-triangular k-coverage holes can be accurately detected by our algorithm.

关键词： Wireless sensor network coverage hole detection k-coverage Homology theory

来源：评论

学校读者我要写书评

暂无评论

Tree-based coverage hole detection and healing method in wireless sensor networks

引用

COMPUTER NETWORKS 2016年 103卷 33-43页

作者： Li, Wei Wu, Yuwei Sichuan Univ Sch Aeronaut & Astronaut 24South Sect 1Yihuan Rd Chengdu 610065 Peoples R China Huawei Technol Co Ltd 1899 Xiyuan Rd Chengdu 611731 Peoples R China

In wireless sensor networks, coverage is a fundamental issue affecting the quality of service. A coverage hole may appear anywhere in the area being monitored at any time because of many reasons. Thus, hole detection and healing have become major challenges towards achieving perfect coverage. This study provides a novel algorithm using trees and graph theory to detect and describe the existing holes in the region of interest. Simulation results show that the tree-based method can indicate the location, size, and shape of coverage holes accurately. Based on the results for hole detection, a tree-based healing method is also proposed. The method is divided into two phases, namely, hole dissection and optimal patch position determination. Results obtained from the experimental evaluation reveal that the proposed healing method can increase the coverage rate with only a few additional sensors compared to other related methods. (C) 2016 Elsevier B.V. All rights reserved.

关键词： coverage hole detection hole healing Tree Sensor network

来源：评论

学校读者我要写书评

暂无评论

coverage hole detection method of wireless sensor network based on clustering algorithm

引用

MEASUREMENT 2021年 179卷 109449-109449页

作者： Wang, Feifei Hu, Haifeng Pingdingshan Univ Informat Engn Coll Pingdingshan 467000 Peoples R China

The traditional method does not calculate the moving distance parameter when detecting coverage vulnerabilities, so its coverage performance is poor. The clustering algorithm can effectively calculate the moving distance parameter. Therefore, a method to detect the coverage hole in wireless sensor network based on clustering algorithm was proposed. Firstly, the parameter of coverage hole in wireless sensor network were calculated, including the moving distance parameters, circular intersection area parameters and redundancy parameters. Secondly, the algorithm of hole edge intersection was used to judge edge nodes of coverage holes in wireless sensor network. By judging whether there was a hole edge intersection on the sensing circle, the edge nodes of coverage holes in wireless sensor network could be determined. Thirdly, the mobile nodes were deployed in the way of airdrop, and then they were distributed evenly. The density of the initially deployed mobile nodes should meet the highest coverage requirement in wireless sensor network. After determining the edge nodes of coverage holes in wireless sensor network, the deployed mobile nodes were used to find the edge nodes of coverage holes in wireless sensor networks by random walk. Meanwhile, the coverage holes were approximated by the set of edge nodes. Finally, it was able to detect the coverage holes in wireless sensor network by clustering algorithm, including the detection of hole shape and the judgment of holes size. In order to verify the gap coverage performance of the coverage hole detection method based on clustering algorithm, the traditional method was compared with the proposed method. Experimental results show that the gap coverage performance of the proposed method is better than that of traditional method. The gap coverage performance of this method is 389 T, while the traditional method is only 351 T. so this method is more suitable for the detection of coverage hole in wireless sensor network.

关键词： Clustering algorithm Wireless sensor network coverage hole detection Sensing radius

来源：评论

学校读者我要写书评

暂无评论

Virtual Edge Based coverage hole detection Algorithm in Wireless Sensor Networks

Virtual Edge Based Coverage Hole Detection Algorithm in Wire...

引用

IEEE Wireless Communications and Networking Conference (WCNC)

作者： Zhang, Yunzhou Zhang, Xiaohua Wang, Zeyu Liu, Honglei Northeastern Univ Coll Informat Sci & Engn Shenyang Peoples R China

ISBN: (纸本)9781467359399;9781467359382

With the knowledge of locations of each node in randomly deployed wireless sensor networks, the detection of coverage holes is researched in this paper. An improved hole detection algorithm is proposed based on the Boolean sensing model. The algorithm screens out hole-boundary nodes by Voronoi Diagram. In order to achieve location information of coverage holes, we introduce a new method called Virtual Edge to calculate boundary nodes. The simulation shows that compared to such popular hole detection methods as Voronoi Diagram algorithm and Simplicial Complex algorithm, the algorithm proposed can get more accurate location, shape and area information of coverage holes.

关键词： Wireless sensor network coverage hole detection Voronoi diagram Virtual edge hole boundary

来源：评论

学校读者我要写书评

暂无评论

A Novel Confident Information coverage hole detection Algorithm in Sensor Networks

A Novel Confident Information Coverage Hole Detection Algori...

引用

9th IEEE Int Conf on Internet of Things / 12th IEEE Int Conf on Green Comp and Communicat / 9th IEEE Int Conf on Cyber, Phys, and Social Comp / IEEE Int Conf on Smart Data

作者： Zou, Zenghui Deng, Xianjun Yi, Lingzhi Tang, Zujun Wang, Minghua Gong, Xueyu Univ South China USC Dept Commun Engn Hengyang Peoples R China

ISBN: (纸本)9781509058808

The emergence and existence of coverage holes in WSNs will dramatically degrade the network coverage performance and quality of service. To diminish the negative effects of coverage holes, this paper studies the confident information coverage hole detection problem(CICHD) based on the proposed novel confident information coverage model(CIC). For solving the CICHD problem, we design an effective heuristic CIC hole detection algorithm. In the proposed algorithm, the sensing field is firstly partitioned into a series of reconstruction grids based on the spatial correlation and correlation range. Then each reconstruction grid will be scanned and detected based on the CIC model to be judged whether it is a coverage hole or not. After obtaining the coverage status of each reconstruction grid, the coverage hole boundary will be extracted by image processing method. Simulation results show that the proposed scheme can efficiently detect the emerged coverage holes including the locations and the number.

关键词： Confident Information coverage coverage hole detection Wireless Sensor Networks

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：