The Survey of Low-Power Sleep Monitoring Algorithm Based on the Wrist Movement Signal

Diagnosis of sleep disorders in an expensive procedure that requires performing a sleep study, known as polysomnography(PSG), in a controlled environment. However, PSG still requires patients to use a cumbersome system with multiple recording channels that need to be precisely placed, which gives burden to testers greatly. This paper proposes a low-power sleep monitoring algorithm based on the wrist movement signal by studying several relatively mature algorithms of sleep. We combine with low-power hardware strategy, and enable power consumption of monitoring process to reduce by more than 50%. Besides, the monitoring results obtained in this paper are nearly superior to common sleep monitoring mechanism, such as proportional integral model, and accuracy also has risen greatly to a certain degree.