Recognition of aging effect from cardiomechanical signals using novel SF-ART neural network

In this study we applied Haar wavelets to extract essential features of cardiac mechanical signals classified them using a novel neural network so called, Supervised Fuzzy Adaptive Resonance Theory (SF-ART). Initial tests with sternal signals of cardiac vibration from six young, middle-aged and old subjects indicate that SF-ART can classify the subjects into three classes with a high accuracy, fast learning speed, and low computational load. The method is insensitive to latency and non-linear disturbance. Moreover, the applied wavelet transform requires no prior knowledge of the statistical distribution of data samples. This can offer a novel method for the analysis of the effects of aging on the heart and assessment of the physiological age of the heart.