Title: An energy-saving wireless sensor network based model for monitoring of ammonia concentration
Authors: Chong Chen; Xingqiao Liu; Chengyun Zhu; Caihong Huo
Addresses: School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China; School of Electrical Engineering, Yancheng Institute of Technology, Yancheng, 224051, China ' School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China; National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, China ' School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China; National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, China ' School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China; National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, China
Abstract: The ammonia concentration in the piggery plays a key role in the growth of fattening pigs. An intelligent environmental monitoring system is proposed based on a wireless sensor network. Specifically, a model has been developed to predict environmental parameters in the server. To optimise its prediction accuracy, this model was designed based on least squares support vector regression (LSSVR) with chaotic mutation to improve the estimation of distribution algorithm (CMEDA) for searching of the optimised parameters, which are γ and σ. Three optimisation methods were involved and compared with it. The experimental results indicated that it exhibits advantages in the prediction accuracy over the other three algorithms. Furthermore, the prediction accuracy of the server was 95%, resulting in reduction of internet of things (IoT) card flow and battery power of LoRa module per day by 50%. The proposed monitoring system is an effective strategy for piggery environmental control.
Keywords: energy-saving; prediction model; LSSVR; least squares support vector regression; chaotic mutation; EDA; estimation of distribution algorithm; WSN; wireless sensor network.
DOI: 10.1504/IJSNET.2019.099226
International Journal of Sensor Networks, 2019 Vol.30 No.1, pp.24 - 34
Received: 27 Oct 2018
Accepted: 21 Nov 2018
Published online: 23 Apr 2019 *