Performance evaluation method, device, terminal and storage medium of prosthetic action classifier

Abstract

The invention discloses a performance evaluation method, device, terminal and storage medium of a prosthesis action classifier. The method includes: determining a test item among a plurality of preset test items as the current test item; displaying the starting point and test target in the current test item on the coordinate axis, and continuously acquiring the electromyography signal of the subject , identify the myoelectric signal through the prosthetic action classifier to obtain the result action, draw the action track corresponding to the result action from the starting point, and record the test time; according to the action track of the current test item and the test time , determining the test value of the current test item for the test evaluation index; combining the test values ​​of the multiple test items for the test evaluation index to obtain the evaluation value of the prosthetic movement classifier for the overall evaluation index. The invention realizes the real-time evaluation of the performance of the prosthesis action classifier, and obtains quantified evaluation results, which are relatively accurate.

Description

technical field [0001] Embodiments of the present invention relate to prosthetic limb control technology, and in particular to a performance evaluation method, device, terminal and storage medium of a prosthetic limb motion classifier. Background technique [0002] According to the 2006 sample survey data of my country's disabled population by the National Bureau of Statistics, among all kinds of disabled people in the country, the physically disabled population is the largest, accounting for 24.12 million people, accounting for 29.07% of the total disabled population. Due to accidents, birth defects, diseases, natural disasters and other reasons, the number of people with physical disabilities is still increasing. In the Sichuan Wenchuan Earthquake in May 2008 alone, more than 20,000 people lost limbs. These amputees need to wear artificial limbs to assist their daily life and work. According to the control method of the prosthesis, at present, the commercialized artifici...

AI Technical Summary

Problems solved by technology

However, the current myoelectric prosthetics on the market can only use offline data analysis to evaluate the classification method and training effect, and lack quantifiable real-time evaluation methods. Therefore, amputees can only use data prediction and subjective observation of the trained myoelectric prosthesis control effect, judging the control situation

Although offline data analysis can provide objective data, it cannot fully reflect the specific situation in real-time myoelectric prosthetic control

In the actual use of myoelectric prostheses, there may be situations where the movements made by the myoelectric prosthesis do not match the intended movements of the amputee, or even completely fail to complete the movements that the amputee wants to complete.

This creates certain surprises and risks for amputees

Images