Pulse Feature Extraction Based on Improved Gaussian Model

Wrist pulse contains important information about the health status of a person. The pathological changes of organ could be perceived by pulse-feeling which has been popular for thousands of years in China. However, the traditional Chinese medicine usually portrays the pulse types in a vague and general language, and the diagnoses from physicians often diverge greatly due to their subjective experience. Thus, the objectification of pulse diagnosis is imperative under the modern computer technology circumstance. This paper proposes a novel pulse feature extraction method based on improved Gaussian model, the experiments has been done on a dataset which is collected from 148 healthy persons and 288 patients by using the self-designed pulse collecting system, the results show that the method is efficient for diagnosis.