The invention belongs to the technical field of
signal identification, particularly relates to a Parkinson's
disease patient
dyskinesia quantification and identification method based on a
support vector machine, and aims to solve the problem that Parkinson's
disease patient
dyskinesia quantification and identification cannot be accurately realized in the prior art. The method comprises the following steps: acquiring
wrist motion signals and
ankle motion signals of a tested object and a healthy person; carrying out
resampling and
signal synthesis on the signals; extracting a walking interval through a sliding window; extracting the
gait features of the measured object and the healthy person respectively; normalizing the
gait features and classifying the
gait features through a trained
support vector machine; calculating Pr values, wherein the intervals Pr is greater than 0.9, Pr is less than 0.9 and greater than or equal to 0.6, Pr is less than 0.6 and greater than or equal to 0.5 and Pr is less than 0.5, which corresponds to a severe Parkinson's
disease patient, a moderate Parkinson's
disease patient, a mild Parkinson's
disease patient and a non-Parkinson's
disease patient respectively. The Parkinson's disease patient
dyskinesia quantification and identification method is high in accuracy, high in precision, small in occupied resource, suitable for remote
medical treatment, lowin cost and high in efficiency.