A dynamical model for generating synthetic Ballistocardiogram signals

Abstract

Ballistocardiogram (BCG) signal reflects the status of cardiovascular system. Many researchers have done a lot of remarkable work on BCG research. Because of the environment noise and individual differences, acquired BCG signals often fluctuated greatly. In this paper, a dynamic BCG signal model based on Gaussian kernel function is proposed. The proposed model consists of five waveforms of BCG signals, such as H wave, I wave, J wave, K wave, L wave and M wave. By comparing the similarity and morphology from healthy individuals BCG signal, the dynamic of Gaussian model is able to close the BCG signal of real individuals. The BCG signal based on the dynamic Gaussian model can fully express the BCG signal characteristics of the healthy individual.