基于车联网的数据动态压缩采集策略

doi:10.11896／j.issn.1002-137X.2018.11.049

摘要/Abstract

摘要： 车联网能高效地实现感知区域的覆盖,因此被应用于大规模城市感知。同时,为了解决车联网难以传输大量数据的问题,一些研究者使用压缩感知对具有时空相关性的数据进行压缩。但是,目前在车联网中应用压缩感知的研究并没有考虑数据和车辆分布变化的特性,很可能导致不可接受的误差。为了保证数据的重构精度,提出面向车联网的动态压缩感知方法。该方法能自动分析感知对象的数据特征、车辆分布和观测数量之间的关系。在压缩感知的基础上加入观测数量调整功能,通过对当前感知对象的数据特征和车辆分布的分析,实时调整压缩感知中观测矩阵的参数,从而控制观测数据的数量,提升重构精度,实现更高质量的数据传输。实验表明与现有车联网中的压缩感知方法相比,面向车联网的动态压缩感知方法在重构精度上提升了15.3%。

关键词: 车联网, 城市感知, 动态压缩, 压缩感知, 重构精度

Abstract: Internet of Vehicle (IoV) can effectively cover the sensing area,so it is applied to large-scale urban sensing.Meanwhile,in order to solve the problem that it is difficult for the IoV to transfer a large amount of data,the compressive sensing (CS) is used to compress the data with spatio-temporal correlation by some researchers.However,the current researches on the applications of CS in the IoV do not consider dynamic changes in data characteristic and vehicle distribution,which may lead to unacceptable errors.In order to ensure the accuracy of data reconstruction,this paper proposed a dynamic CS approach in the IoV.The approach can automatically analyze the relationship among data chara-cteristic,vehicle distribution and the number of measurements.Then,based on the CS,a function of adjusting the number of measurements is added.Through the analysis of data characteristic and vehicle distribution,theparameters of the observation matrixin CS is adjusted in real time so as to improve the accuracy of reconstruction to achieve higher quality data transmission.The experiment shows that the proposed dynamic CS method improves the reconstruction accuracy by 15.3% compared with the existing CS method in the IoV.

Key words: Compressive sensing, Dynamic compression, Internet of vehicle, Reconstruction accuracy, Urban sensing

中图分类号:

TP393

黄志清, 李梦佳, 田锐, 张严心, 王伟东. 基于车联网的数据动态压缩采集策略[J]. 计算机科学, 2018, 45(11): 304-311. https://doi.org/10.11896／j.issn.1002-137X.2018.11.049

HUANG Zhi-qing, LI Meng-jia, TIAN Rui, ZHANG Yan-xin, WANG Wei-dong. Dynamic Data Compression Strategy Based on Internet of Vehicle[J]. Computer Science, 2018, 45(11): 304-311. https://doi.org/10.11896／j.issn.1002-137X.2018.11.049

参考文献

[1]NEIROTTIP,MARCOA D,CAGLIANOA C,et al.Current trends in Smart City initiatives:Some stylised facts[J].Cities,2014,38(5):25-36.
[2]LIU J,LI Y,CHEN M,et al.Software-defined internet of things for smart urban sensing[J].Communications Magazine IEEE,2015,53(9):55-63.
[3]JALALVANDIS,RAFEHR.A cluster-based routing algorithm for VANET[C]∥IEEE International Conference on Computer and Communications.IEEE,2016:2068-2072.
[4]LIU K,NG J K Y,LEE V C S,et al.Cooperative data scheduling in hybrid vehicular ad hoc networks:VANET as a software defined network[J].IEEE/ACM Transactions on Networking,2016,24(3):1759-1773.
[5]HE J,CAI L,CHENG P,et al.Delay Minimization for Data Dissemination in Large-scale VANETs with Buses and Taxis[J].IEEE Transactions on Mobile Computing,2016,15(8):1939-1950.
[6]LEE U,MAGISTRETTI E,GERLA M,et al.Dissemination and Harvesting of Urban Data using Vehicular Sensor Platforms[J].IEEE Transactions on Vehicular Technology,2009,58(2):882-901.
[7]SALHI I,CHERIF M O,SENOUCI S M.A New Architecture for Data Collection in Vehicular Networks[C]∥IEEE International Conference on Communications.IEEE Press,2009:2705-2710.
[8]JANG J,YANG Y,SMYTH A W,et al.Framework of Data Acquisition and Integration for the Detection of Pavement Distress via Multiple Vehicles[J].Journal of Computing in Civil Engineering,2016,31(2):04016052.
[9]MALIK A,PANDEY B.An Intelligent Authentication Based Vehicle Initiated Broadcast-Dynamic Path Data Collection Scheme in VANET[J].Indian Journal of Science & Technology,2016,9(16):1-9.
[10]ANASTASI G,ANTONELLI M,BECHINI A,et al.Urban and social sensing for sustainable mobility in smart cities[C]∥Sustainable Internet and ICT for Sustainability.IEEE,2013:1-4.
[11]ZHU Y,LIU X,WANG Y.Pervasive Urban Sensing with Large-Scale Mobile Probe Vehicles[J].International Journal of Distributed Sensor Networks,2013,2013:177-182.
[12]HULL B,BYCHKOVSKY V,ZHANG Y,et al.CarTel:a distributed mobile sensor computing system[C]∥International Conferece on Embedded Networked Sensor Systems.2006:125-138.
[13]HU S C,WANG Y C,HUANG C Y,et al.A vehicular wireless sensor network for CO2 monitoring[C]∥Sensors,2009 IEEE.2009:1498-1501.
[14]DONOHO D L.Compressive sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[15]YU X,ZHAO H,ZHANG L,et al.Cooperative Sensing and Compression in Vehicular Sensor Networks for data gathering[C]∥IEEE International Conference on Communications.IEEE Xplore,2010:1-5.
[16]WANG H,ZHU Y,ZHANG Q.Compressive sensing based monitoring with vehicular networks[C]∥IEEE INFOCOM.IEEE,2013:2823-2831.
[17]LIU C,CHIGAN C,GAO C.Compressive sensing based data collection in VANETs[C]∥Wireless Communications and NETWORKING Conference.IEEE,2013:1756-1761.
[18]ZHU Y,LI Z,ZHU H,et al.A Compressive Sensing Approach to Urban Traffic Estimation with Probe Vehicles[J].IEEE Transactions on Mobile Computing,2013,12(11):2289-2302.
[19]WANG G Y,JIANG Y J,MO L F,et al.Dynamic measurement policy for soil respiraten monitoring sensor networks based on compressive sensing[J].Scientia Sinica,2013,43(10):1326-1341.(in Chinese)
王国英,江雨佳,莫路锋,等.基于压缩感知的土壤呼吸监测传感网动态采样调度策略[J].中国科学:信息科学,2013,43(10):1326-1341.
[20]QUER G,ZORDAN D,MASIERO R,et al.WSN-Control:Signal reconstruction through Compressive Sensing in Wireless Sensor Networks[C]∥The IEEE Conference on Local ComputerNetworks.2010:921-928.
[21]HAO J,ZHANG B,JIAO Z,et al.Adaptive compressive sensing based sample scheduling mechanism for wireless sensor networks[J].Pervasive & Mobile Computing,2015,22(C):113-125.
[22]RADOVIC＇ M,DUKNIC＇ M,TASESKI J.Sensing,Compression,and reconstruction for WSNs:Sparse Signal Modeling and Monitoring Framework [J].IEEE Transactions on Wireless Communications,2012,11(10):3447-3461.
[23]WANG J,TANG S,YIN B,et al.Data gathering in wireless sensor networks through intelligent compressive sensing[J].IEEE INFOCOM,2012,131(5):603-611.
[24]CHEN W,WASSELL I J.Energy efficient signal acquisition via compressive sensing in wireless sensor networks[C]∥2011 6th International Symposium on Wireless and Pervasive Computing (ISWPC).IEEE,2011:1-6.
[25]FRAGKIADAKIS A,CHARALAMPIDIS P,TRAGOS E. Adaptive compressive sensing for energy efficient smart objects in IoT applications[C]∥International Conference on Wireless Communications.2014:1-5.
[26]CANES E,ROMBERG J.Sparsity and incoherence in compressive sampling[J].Inverse Problems,2006,23(3):969-985.
[27]HECHT-NIELSEN R.Theory of backpropagation neural net- works[C]∥International Joint Conference on Neural Networks.IEEE Xplore,1989:593-605.
[28]LI B,LIU C.Parallel BP Neural Network on Single-chip Cloud Computer[C]∥IEEE International Conference on High Performance Computing and Communications.IEEE,2015:1871-1875.
[29]TROPPJ A,GILBEFTA C.Signal reconstruction From Random Measurements Via Orthogonal Matching Pursuit[J].IEEE Transactions on Information Theory,2008,53(12):4655-4666.
[30]GRIGGSW M,ORDÓÑEZ-HURTADO R H,CRISOSTOMI E,et al.A Large-Scale SUMO-Based Emulation Platform[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(6):3050-3059.

相关文章 15

[1]	陈晶, 吴玲玲. 多源异构环境下的车联网大数据混合属性特征检测方法 Mixed Attribute Feature Detection Method of Internet of Vehicles Big Datain Multi-source Heterogeneous Environment 计算机科学, 2022, 49(8): 108-112. https://doi.org/10.11896/jsjkx.220300273
[2]	宋涛, 李秀华, 李辉, 文俊浩, 熊庆宇, 陈杰. 大数据时代下车联网安全加密认证技术研究综述 Overview of Research on Security Encryption Authentication Technology of IoV in Big Data Era 计算机科学, 2022, 49(4): 340-353. https://doi.org/10.11896/jsjkx.210400112
[3]	张海波, 张益峰, 刘开健. 基于NOMA-MEC的车联网任务卸载、迁移与缓存策略 Task Offloading,Migration and Caching Strategy in Internet of Vehicles Based on NOMA-MEC 计算机科学, 2022, 49(2): 304-311. https://doi.org/10.11896/jsjkx.210100157
[4]	唐亮, 李飞. 基于决策树的车联网安全态势预测模型研究 Research on Forecasting Model of Internet of Vehicles Security Situation Based on Decision Tree 计算机科学, 2021, 48(6A): 514-517. https://doi.org/10.11896/jsjkx.200700158
[5]	俞建业, 戚湧, 王宝茁. 基于Spark的车联网分布式组合深度学习入侵检测方法 Distributed Combination Deep Learning Intrusion Detection Method for Internet of Vehicles Based on Spark 计算机科学, 2021, 48(6A): 518-523. https://doi.org/10.11896/jsjkx.200700129
[6]	于天琪, 胡剑凌, 金炯, 羊箭锋. 基于移动边缘计算的车载CAN网络入侵检测方法 Mobile Edge Computing Based In-vehicle CAN Network Intrusion Detection Method 计算机科学, 2021, 48(1): 34-39. https://doi.org/10.11896/jsjkx.200900181
[7]	葛雨明, 韩庆文, 王妙琼, 曾令秋, 李璐. 汽车大数据应用模式与挑战分析 Application Mode and Challenges of Vehicular Big Data 计算机科学, 2020, 47(6): 59-65. https://doi.org/10.11896/jsjkx.191200165
[8]	刘玉红,刘树英,付福祥. 基于卷积神经网络的压缩感知重构算法优化 Optimization of Compressed Sensing Reconstruction Algorithms Based on Convolutional Neural Network 计算机科学, 2020, 47(3): 143-148. https://doi.org/10.11896/jsjkx.190100199
[9]	田伟, 刘浩, 陈根龙, 宫晓蕙. 面向分块压缩感知的交叉子集导引自适应观测 Cross Subset-guided Adaptive Measurement for Block Compressive Sensing 计算机科学, 2020, 47(12): 190-196. https://doi.org/10.11896/jsjkx.200800197
[10]	吴学林, 朱荣, 郭迎. 基于块稀疏贝叶斯模型的鬼成像重构算法 Ghost Imaging Reconstruction Algorithm Based on Block Sparse Bayesian Model 计算机科学, 2020, 47(11A): 188-191. https://doi.org/10.11896/jsjkx.200200058
[11]	王春东, 罗婉薇, 莫秀良, 杨文军. 车联网互信认证与安全通信综述 Survey on Mutual Trust Authentication and Secure Communication of Internet of Vehicles 计算机科学, 2020, 47(11): 1-9. https://doi.org/10.11896/jsjkx.200800024
[12]	熊玲, 李发根, 刘志才. 车联网环境下基于区块链技术的条件隐私消息认证方案 Conditional Privacy-preserving Authentication Scheme Based on Blockchain for Vehicular Ad Hoc Networks 计算机科学, 2020, 47(11): 55-59. https://doi.org/10.11896/jsjkx.200500116
[13]	许锋, 孙洁, 刘世杰. 基于遗传算法的声场重构测量优化方法 Sampling Optimization Method for Acoustic Field Reconstruction Based on Genetic Algorithm 计算机科学, 2020, 47(11): 304-309. https://doi.org/10.11896/jsjkx.200600167
[14]	刘丹. 基于雾计算和自评估的VANET聚类与协作感知 Fog Computing and Self-assessment Based Clustering and Cooperative Perception for VANET 计算机科学, 2020, 47(10): 55-62. https://doi.org/10.11896/jsjkx.200500154
[15]	侯明星,亓慧,黄斌科. 基于分布式压缩感知的无线传感器网络异常数据处理 Data Abnormality Processing in Wireless Sensor Networks Based on Distributed Compressed Sensing 计算机科学, 2020, 47(1): 276-280. https://doi.org/10.11896/jsjkx.180901667

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed