Freezing gait detection method and system based on staged feature extraction

Abstract

The invention discloses a freezing gait detection method and a system based on staged feature extraction, and belongs to the field of machine learning. The freezing gait detection method of the present invention comprises the steps, constructing a sample set with a label based on original acceleration data collected in the walking process of a user, wherein the sample is an acceleration data sequence after windowed processing, and the label represents whether the sample belongs to a normal gait or a freezing gait; carrying out staged feature extraction on each sample; performing feature transformation on a gait feature set by using PCA to obtain a low-dimensional new gait feature set, performing feature selection on the low-dimensional new gait feature set to obtain an optimal gait featuresubset; training a freezing gait detection model based on machine learning by using the optimal gait feature subset; extracting a staged feature of the sample to be detected, and inputting the stagedfeature into the trained freezing gait detection model to obtain a freezing gait detection result. According to the method, a motion component and a freezing zone in an acceleration signal are extracted, and a motion signal is synthesized and decomposed, so that the potential features of the original data are brought into full play.

Description

technical field [0001] The invention belongs to the field of machine learning, and more specifically relates to a method and system for detecting frozen gait based on staged feature extraction. Background technique [0002] Parkinson's disease (PD) is a common neurodegenerative disease. At present, the number of PD patients in my country has reached 2.9 million, and it continues to grow at a rate of about 100,000 new patients every year. With the increasing rate of population aging, it is estimated that by 2030, the number of PD patients in my country will reach 5 million. Freezing of Gait (FoG) is a common disabling symptom in middle and advanced PD, which seriously affects the patient's mobility. Early detection of FoG events, as the basis for the implementation of intervention measures, can help patients with the disease to reduce the risk of falls and resume walking and normal activities; as the basis for follow-up disease assessment, it can provide relevant symptom inf...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, most of the detection methods for frozen gait of Parkinson's patients are to directly extract features from the preprocessed signal, and then use the feature set to train the classifier, which has indistinct features, low robustness, Problems such as poor generalization ability

Images