English

应用科学学报 ›› 2018, Vol. 36 ›› Issue (3): 411-419.doi: 10.3969/j.issn.0255-8297.2018.03.001

• 通信工程 • 上一篇    下一篇

一种基于自编码器的无线传感网数据收集方案

李国瑞, 田丽, 崔浩, 陈浩波   

  1. 东北大学 计算机科学与工程学院, 沈阳 110819
  • 收稿日期:2017-08-25 修回日期:2017-10-05 出版日期:2018-05-31 发布日期:2018-05-31
  • 作者简介:李国瑞,副教授,研究方向:无线传感器网络,E-mail:lgr@neuq.edu.cn
  • 基金资助:

    国家自然科学基金（No.61402094）；辽宁省自然科学基金（No.201602254）；河北省自然科学基金（No.F2016501076）；教育部中央高校基本科研业务费资助项目基金（No.N172304022）资助

An Autoencoder-Based Data Collection Scheme for Wireless Sensor Networks

LI Guo-rui, TIAN Li, CUI Hao, CHEN Hao-bo   

  1. College of Computer Science and Technology, Northeastern University, Shenyang 110819, China
  • Received:2017-08-25 Revised:2017-10-05 Online:2018-05-31 Published:2018-05-31

PDF

223

摘要：

利用自编码器设计了一种高效的数据收集方案.该方案包括模型训练和数据收集两个阶段，在模型训练阶段利用历史监测数据进行模型训练从而获得测量矩阵和重构矩阵，在数据收集阶段首先利用测量矩阵实现分布式数据压缩，然后利用重构矩阵重构网络中的所有监测数据.实验结果表明，该方案不但具有较高的数据压缩率，而且具有较高的数据重构精度和较快的数据重构速度.

关键词: 无线传感器网络, 数据重构, 自编码器, 数据收集

Abstract:

Data collection is one of the key operations in wireless sensor networks. In this paper, we propose an energy efcient data collection scheme for wireless sensor networks by using an autoencoder. It includes the model training process and the data collection process. In the model training process, historical dataset is utilized to train the autoencoder with the goal of obtaining a measurement matrix and a reconstruction matrix. In the data collection process, the measurement matrix is utilized to compress the sensed data in a distributed manner and the reconstruction matrix is utilized to reconstruct the surveillant data of the whole sensor network. The experiment results show that the proposed scheme presents higher data compression ratio and higher data reconstruction accuracy as well as faster data reconstruction speed than existed data collection schemes.

Key words: data collection, data reconstruction, wireless sensor networks, autoencoder

中图分类号: