Motor imagery electroencephalogram signal classification method of optimal region common space mode

Abstract

The invention discloses a motor imagery electroencephalogram signal classification method of an optimal region common space mode. The method comprises the following steps: firstly, collecting and preprocessing multichannel electroencephalogram signals; secondly, selecting n channels near a channel according to the Euclidean distance of the channel to form local areas, conducting CSP filtering onthe multiple areas to acquire the variance ratio of multiple areas and then, according to the separability criterion of the CSP, selecting the areas with the maximum variance ratio and the minimum variance ratio as the selected areas; performing cross validation on the number n of channels in the region to obtain an optimal area; finally, performing CSP filtering on the optimal area, forming a feature space by taking the three filtered maximum and minimum feature vectors, inputting the training set features into an SVM classifier to train a classification model, and classifying the test set features to obtain a test result. According to the invention, the performance of BCI is improved by removing irrelevant noisy channels; meanwhile, the number of channels and the verification operation time are reduced.

Description

Technical field [0001] The invention belongs to the field of pattern recognition, and is a method for extracting the characteristics and classification of the channel signals in the region by using the separability of the variance ratio of the two types of signals to extract the characteristics and classification of the channel signals in the region by using the separability of the variance ratio of the two types of signals. Background technique [0002] Brain-computer interface technology (BCI) is a human-computer interaction system that does not rely on the normal transmission pathways of human nerves and muscle tissues, but directly communicates information between the human brain and the outside world. It is true for the patient's ability to restore and function Training is of great significance and can provide great help for the rehabilitation of patients with disturbances of consciousness and stroke. Patients can use this technology to control mechanical equipment and comple...

AI Technical Summary

Problems solved by technology

However, LRCSP defines several local regions, and for EEG signals with large individual differences, the range and channel selection of fixed regions cannot be determined.

Images