Pulse condition classification method based on salient signal sub-segment extraction

Abstract

The invention discloses a pulse condition classification method based on salient signal sub-segment extraction, and the method comprises the steps: S1, collecting pulse signals, carrying out the preprocessing, and obtaining c pulse signal training samples; s2, positioning a significant pulse signal sub-segment position indication vector; s3, constructing a multi-modal distance feature vector; andS4, classifying the pulse signals by adopting a nearest neighbor classifier to finish pulse condition classification based on significant signal sub-segment extraction. According to the pulse condition classification method, periodic segmentation does not need to be conducted on the pulse signals, the sub-segments with distinguishing force are extracted from the pulse signals, information redundancy is avoided, and the subsequent calculation process can be accelerated. Characteristic information complementation can be achieved by constructing the multi-modal distance characteristic vectors ofthe signal subsections, pulse signal classification accuracy can be improved, automatic pulse condition recognition is achieved, auxiliary decisions are provided for pulse diagnosis of doctors, and the extracted pulse signal subsections can provide interpretable results for further clinical analysis.

Description

technical field [0001] The invention belongs to the technical field of medical diagnosis, and in particular relates to a pulse condition classification method based on significant signal sub-segment extraction. Background technique [0002] In the clinical diagnosis of traditional Chinese medicine, doctors of traditional Chinese medicine feel the pulse at the radial artery of the wrist with their fingers, and judge the patient's health status according to the speed, strength and depth of the pulse. However, the description of the concept of pulse condition in traditional Chinese medicine is relatively vague, so the identification standard of pulse condition is not clear, and the accuracy of syndrome differentiation depends to a large extent on the experience of doctors. has a difference. This traditional method of pulse diagnosis, which relies entirely on the subjective experience of doctors, will limit the promotion and inheritance of TCM pulse diagnosis technology. There...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is in order to solve the problem of pulse condition classification, has proposed a kind of pulse condition classification method based on significant signal subsection extraction

Images