Heart Rate Variability Analysis Using Threshold of Wavelet Package Coefficients
share
In this paper, a new efficient feature extraction method based on the adaptive threshold of wavelet package coefficients is presented. This paper especially deals with the assessment of autonomic nervous system using the background variation of the signal Heart Rate Variability HRV extracted from the wavelet package coefficients. The application of a wavelet package transform allows us to obtain a time-frequency representation of the signal, which provides better insight in the frequency distribution of the signal with time. A 6 level decomposition of HRV was achieved with db4 as mother wavelet, and the above two bands LF and HF were combined in 12 specialized frequencies sub-bands obtained in wavelet package transform. Features extracted from these coefficients can efficiently represent the characteristics of the original signal. ANOVA statistical test is used for the evaluation of proposed algorithm.
READ FULL TEXT