Signal processing and feature extraction for sleep evaluation in wearable devices

Abstract

In this paper we discuss the possibility of performing a sleep evaluation form the heart rate variability (HRV) and respiratory signals. This is particularly useful for wearable devices. The HRV and the respiration were analyzed in the frequency domain and the statistics on the spectral and cross-spectral parameters put into evidence the possibility of a sleep evaluation on their basis. Additional information can be achieved from the number of microarousals recognized in correspondence of typical modifications in the HRV signal.