Motion intention prediction method based on brain network dynamic connection characteristics

Abstract

The invention discloses a motion intention prediction method based on brain network dynamic connection characteristics. The motion intention prediction method comprises the following steps of constructing a time-varying dynamic Bayesian network model, and converting an EEG signal matrix of a time domain into a directed weighted connection matrix between electrodes of the time domain; carrying outpairing t test on each electrode pair by the obtained directed weighted connection matrix according to a defined motion intention state and a rest state, screening to obtain electrode pairs with significant difference in two states, and reconstructing a feature matrix according to the electrode pairs obtained by screening and time; and reconstructing the obtained feature matrix into a feature vector, inputting the feature vector into the trained classifier, and outputting a prediction result of the motion intention. The defect that a traditional electroencephalogram motion intention predictionmethod ignores the dynamic relation between different areas of the cerebral cortex is overcome.

Description

technical field [0001] The invention belongs to the field of EEG signal analysis, and in particular relates to a method for predicting motion intention. Background technique [0002] Generally speaking, human body activities are controlled by the brain's will, so in order to assist and restore the motor communication ability of patients with impaired motor abilities such as disability and paralysis, it is crucial to predict the patient's motor intentions through the brain-computer interface. For the prediction of motor intentions, most of the published studies are based on the time-domain or frequency-domain features of movement-related cortical potentials. Although time-domain or frequency-domain features of motor-related cortical potentials have been proven to successfully predict motor intentions, these methods ignore the dynamic connections of EEG in different brain regions over time. In order to take into account the dynamic connections between different regions of the...

AI Technical Summary

Problems solved by technology

Although time-domain or frequency-domain features of motor-related cortical potentials have been proven to be successful in predicting motor intentions, these methods have ignored the dynamic connections of EEG in different brain regions over time.

Images