Sparse decomposition of pressure pulse wave signal based on time frequency analysis

In traditional Chinese medicine (TCM), wrist pulse is of great significance to help doctors in diagnosis. With the development of sensing technology, the computerized wrist pulse analysis has been attracting more attention in modern medicine for its non-invasive and convenient. Considering the TCM pulse diagnosis theory, it is necessary to develop effective feature extraction methods for computerized diagnosis. In this paper, we decompose the pressure pulse waveform of the radial artery to several components by sparse decomposition with Gabor function. In order to better represent the pulse waveform signal, we use an Gabor function based on the characteristics of the pulse waveform to generate a time-frequency dictionary. Compared with the conventional representation methods, the shape of the Gabor function is more variable, which can better represent both the contour and specific peaks. In addition, due to the limitation of the windowing, the Gabor function can reduce the influence on other positions when representing specific position. The feature vector composed of the decomposed components can be used for the computerized pulse signal analysis and disease diagnosis. The experimental results show that the proposed method can exhibit superior performance in distinguishing between the signals collected from patients and healthy individuals.