Sleep Monitoring With Hidden Markov Model for Physical Conditions Tracking

Sleep monitoring is an important health monitoring approach. Generally, one's physical conditions fall into several qualities such as normal, weak, etc. And the clues of physical conditions are buried in the mass monitoring data. In this paper, a physical condition tracking method is proposed based on sleep monitoring with Hidden Markov Model (HMM). Firstly, physical features are acquired during sleep over a fixed time period using a micro movement sensitive mattress sleep monitoring system (MSMSMS). A feature matrix is created and used to derive an HMM that represents the condition of the subject. The connection between the variation of physical conditions and the Markov process is established. Bayesian information criterion is utilized to determine the number of hidden states in an HMM. Once a reference HMM is established, long-term physical conditions variation tracking can be realized by evaluating the fitnesses between upcoming monitoring data and the reference HMM. The proposed method is verified on a sleep monitoring experiment using the MSMSMS.