Support vector machine based surface electromyogram signal multi-hand action identification method

Abstract

The invention discloses a support vector machine based surface electromyogram signal multi-hand action identification method. The method comprises the following main steps: 1) obtaining electromyogram data, performing smooth filtering on a signal, and generating data samples through sampling windows of different scales; 2) by taking the data samples as units, extracting a novel multi-feature set containing 19 time domain, frequency domain and time-frequency domain features from each data sample, and performing normalization and minimum redundancy maximum correlation criterion based feature selection on eigenvectors; 3) designing a Pearson VII generalized kernel based support vector machine classifier and optimizing parameters of a support vector machine by using a cross validation based coarse grid search optimization algorithm; and 4) training a classification model by using data samples in a training set and optical classifier parameters obtained in the parameter optimization process of the step 3) and inputting data samples in a test set into the classification model to perform classification testing.

Description

technical field [0001] The invention relates to a method for recognizing multiple types of hand movements based on surface electromyography signals based on a support vector machine, and belongs to the technical field of pattern recognition. Background technique [0002] Feature extraction has a crucial impact on the final recognition rate of EMG signal pattern recognition. EMG signal features can be divided into three types: time domain, frequency domain, and time-frequency domain. Time domain features include some features based on signal amplitude, frequency domain features include some features based on signal power spectrum, and time-frequency domain features include Some features extracted by wavelet analysis technique. Time-domain features are not robust to non-stationary signals and are sensitive to signal amplitude changes. Frequency-domain features are not robust to signals after some preprocessing steps (such as full-wave correction). In addition, some literature...

AI Technical Summary

Problems solved by technology

[0003] The multi-feature set extracted from multi-channel EMG signals will have high-dimensional characteristics. Excessively high dimensions will lead to a decline in the model's generalization ability and greatly increase the computational load.

Images