A multi-task motor imagination EEG feature extraction and pattern recognition method for vehicle control

Abstract

The invention relates to a multi-task motor imagination EEG feature extraction and pattern recognition method for vehicle control. The multi-task imagination EEG signals were collected by EEG amplifier and transmitted to PC. The frequency domain and spatial feature combinations of imaginary EEG were extracted by Welch power spectrum and one-to-one common spatial pattern algorithm. A plurality of GMM classifiers are constructed according to the categories to which the training set data belongs. The original EEG signal is passed through the GMM classifier, and the probability density is comparedwith the set credible threshold. The samples below the credible threshold are classified twice by artificial neural network, and the final classification result is transmitted to the vehicle throughwireless serial port to realize the real-time movement of the vehicle. The invention utilizes welch power spectrum and CSP to extract frequency domain and spatial domain features related to motion imagination, utilizes GMM and artificial neural network two-level classifier, effectively improves real-time performance of vehicle control and safety of vehicle driving, and lays a foundation for practical application of brain-controlled vehicle.

Description

technical field [0001] The invention relates to a vehicle control-oriented multi-task motor imagery EEG feature extraction and pattern recognition method, and the fields of signal processing and pattern recognition. Background technique [0002] Brain-computer interface (BCI) can directly control peripheral devices through the interaction of neurons in the human brain. This control method that does not rely on limbs and peripheral nerves brings hope for the disabled to realize autonomous activities. Motor imagery EEG signals have the advantage of being evoked autonomously, so they are widely used in brain-computer interfaces. [0003] Motor imagery EEG signals have low amplitude and are easily affected by other physiological electrical signals, so their effective components are often submerged in noise. In order to improve the signal-to-noise ratio of EEG signals and extract the features that can best represent the subjects' imaginary actions, many frequency domain and spat...

AI Technical Summary

Problems solved by technology

However, its classification accuracy is still difficult to meet the high safety requirements in the actual driving process.

The artificial neural network contains a large number of weights and bias parameters. A large number of fitting parameters not only improves the nonlinear classification ability of the algorithm, but also increases its computational complexity.

Images