An Improved HMM Model for Sensing Data Predicting in WSN

Wireless sensor networks (WSN) have been employed in numerous fields of real world applications. Data failure and noise reduction still remain tough unsolved problems for WSN. Predicting methods for data recovery by empirical treatment, mostly based on statistics has been studied exclusively. Machine learning models can greatly enhance the predicting performance. In this paper, an improved HMM is proposed for multi-step predicting of wireless sensing data given historical data. The proposed model is based on clustering of wireless sensing data and multi-step predicting is accordingly accomplished for different varying patterns using HMM whose parameters are optimized by Particle Swarm Optimization (PSO). We evaluate our model on two real wireless sensing datasets, and comparison between Naive Bayesian, Grey System, BP Neural Networks and traditional HMMs are conducted. The experimental results show that our proposed model can provide higher accuracy in sensing data predicting. This proposed model is promising in the fields of agriculture, industry and other domains, in which the sensing data usually contains various varying patterns.