Continuous Object Monitoring Based on Wireless Sensor Network and RBF

DOI

10.2991/icmeit-17.2017.44How to use a DOI?

Keywords

Gaussian smoke model, wireless sensor network, continuous object, RBF neural network, monitoring.

Abstract

Monitoring of continuous object distribution in large-scale environmental monitoring depends on the problem of high-density sensor networks. The RBF neural network is used to fit the distributed data of continuous objects at low sensor network density. Firstly, based on the distribution characteristics of continuous objects, a continuous evolution model of continuous objects based on Gaussian smoke model [1] is established. Secondly, the RBF neural network is trained based on the known distributed node data. Thirdly, RBF neural network is used to fit the distribution data of continuous objects. Finally, the fitting error of different number of training nodes is calculated. Through the experiment of matlab simulation, the practicability of RBF neural network for continuous object distribution has been validated.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Chengping Peng
AU  - Guangcong Liu
PY  - 2017/05
DA  - 2017/05
TI  - Continuous Object Monitoring Based on Wireless Sensor Network and RBF
BT  - Proceedings of the 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)
PB  - Atlantis Press
SP  - 236
EP  - 239
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-17.2017.44
DO  - 10.2991/icmeit-17.2017.44
ID  - Peng2017/05
ER  -