Analysis and classification of physiological signals using wavelet transforms

Physiological signals, such as the electrocardiogram (ECG), arterial blood pressure (ABP), and heart rate variability (HRV), have been shown to contain diagnostic information on the condition of the patient cardiac and circulatory systems. Changes in the physiological signal spectrum in response to various stimuli have been shown to be good indicators of the presence of disease, such as coronary heart disease (CHD) and diabetes mellitus (DM). In order to highlight these changes over time, time-frequency analysis is preformed before diagnostic classification. This brief paper focuses on the HRV signal and introduces the wavelet transform decomposition as a means of signal characterization for enhanced classification.