Brain-computer interface decoding method based on intracranial electroencephalogram and scalp electroencephalogram fusion

Abstract

The invention discloses a brain-computer interface decoding method based on intracranial electroencephalogram and scalp electroencephalogram fusion. The brain-computer interface decoding method comprises the steps of synchronously collecting intracranial electroencephalogram signals and scalp electroencephalogram signals, preprocessing the electroencephalogram signals, extracting electroencephalogram signal features and jointly decoding the electroencephalogram signals. The motor imagery intention of a user is decoded by fusing the characteristics of an intracranial local field potential signal LFP and a scalp electroencephalogram EEG signal, the classification accuracy is high, the robustness is good, and accurate real-time feedback can be provided in rehabilitation training based on a brain-computer interface, so that a good rehabilitation effect is achieved, and a thought and a method are provided for combined application of the intracranial electroencephalogram signals and the scalp electroencephalogram signals.

Description

technical field [0001] The invention belongs to the field of biomedical engineering, and in particular relates to a brain-computer interface decoding method based on fusion of intracranial brain electricity and scalp brain electricity. Background technique [0002] At present, the number of disabled people with impaired motor function is on the rise, and rehabilitation training is the most common method to assist patients in recovering their motor ability. Compared with the traditional passive rehabilitation training, the active rehabilitation training based on the brain-computer interface (BCI) uses the patient to spontaneously generate the movement intention of the rehabilitation training, and converts the intention into instructions to control external equipment to assist the patient to complete the training action. . BCI techniques can increase patient engagement and are believed to be more effective at inducing neuroplasticity and achieving better recovery. Therefore,...

AI Technical Summary

Problems solved by technology

However, the acquisition electrodes of intracranial signals can only detect brain activity in a small area, and may only have a good performance in decoding part of the motion intention.

In addition, the position of the collection electrode cannot be changed after implantation, and the scalability is poor

Images