Design and Implementation of Pulse Diagnosis Instrument Based on Wavelet Transform

Abstract

Aiming at the subjective factors in the process of TCM diagnosis, this paper designed a portable TCM pulse-diagnosis instrument. And the body state and pulse information of the user was collected by simulating the diagnosis mode of “looking, listening, questioning, and feeling the impulse”, and finally, the disease was diagnosed, and the corresponding treatment plan was proposed. STM32 is used as the main control chip, while the thin-film varistor is used as the pressure sensor to collect the pulse information of the human body. After filtering the EMG and power frequency interference by the wavelet transform algorithm, the convolution neural network algorithm is used for real-time classification and diagnosis of pulse signals to achieve the purpose of disease diagnosis. Through the experiment, it can be seen that the similarity between the pulse signal collected by the pulse detector and the ideal pulse signal is above 83%, which meets the design requirements and can realize the basic functions.