Phonocardiography (PCG) Signal Optimization and Compression for Low Line Transmission in Telemedicine

Abstract

In telemedicine and tele-consultation, physiological signals such as ECG, EEG, and PCG play a vital role on eHealth. On low line transmission channels, achieving higher Quality of Service (QoS) of signals is a major research challenge. In this paper, a compression technique is proposed using machine learning algorithm for most alike pattern extraction from signal segments called motifs. These motifs are clustered using K-nearest neighbor (KNN) technique, and resultant dataset is compressed by a native discrete wavelet transformers (DWT). The sample signals considered under experiment is phonocardiograhic (PCG) signal as majority of population cover under smartphones and thus acquiring heart signals via microphones to process in telemedicine environment becomes easier. The experiments retrieves lower SNR ratio with higher order of compression ratio and QoS.