Motion imagery electroencephalograph classification method based on multilayer extreme learning machine

Abstract

The invention relates to a motion imagery electroencephalograph (EEG) classification method based on a multilayer extreme learning machine (ML-ELM), and the motion imagery EEG classification method belongs to the field of pattern identification and brain-computer interfaces (BCI). The classification and identification of EEG mainly comprise feature extraction and feature classification of the EEG. The motion imagery EEG classification method comprises the steps of: firstly, subjecting an original signal of each sample to windowing and segmentation to obtain S segments of sub-signals; secondly, performing principal component analysis and linear discriminant analysis on the S segments of sub-signals obtained through segmentation in the step 1 separately, and combining final S (K-1)-dimensional feature vectors to obtain features of S*(K-1) dimension; and finally, transmitting the features of the S* (K-1) dimension into an ML-ELM classifier, so as to obtain a final classification. Compared with the prior art, the motion imagery EEG classification method has the advantages that a traditional ELM algorithm is of a single-hidden layer structure and has great limitations in extracting features of complex signals, thus the motion imagery EEG classification method increases the number of hidden layers for extracting deep-layer information, thereby improving classification accuracy and maintaining the low time-consuming advantage of the ELM.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and Brain-Computer Interface (Brain-Computer Interface, BCI), and relates to a method for classifying motor imagery EEG signals in a Brain-Computer Interface system device by using a multi-layer extreme learning machine. Background technique [0002] The human brain is a high-speed computing system that dominates and controls all human behaviors, thoughts, emotions and other high-level neural activities. How to effectively acquire and use brain information has always been a hot topic for researchers. Electroencephalogram (Electroencephalograph, EEG) is the discharge activity of brain neuron cells, which contains a large amount of information representing the physiological and psychological state of the human body, and is one of the important means to effectively obtain brain information. Brain-computer interface technology establishes a brand-new channel for transmitting information between th...

AI Technical Summary

Problems solved by technology

However, due to the limitation of its shallow structure, ELM has certain limitations in processing complex signals.

Images