Gesture recognition method based on motion type brain-computer interface

Abstract

The invention discloses a gesture recognition method based on a motion type brain-computer interface, and the method comprises the steps of building an electroencephalogram signal collection platformbased on the motion type brain-computer interface, carrying out the collection and preprocessing of electroencephalogram signals through the electroencephalogram signal collection platform, and obtaining an electroencephalogram signal sample set; constructing a gesture recognition model based on a penalty long short-term memory network RLSTM, and training the gesture recognition model by using theelectroencephalogram signal sample set, wherein the RLSTM comprises control of a state C, and a loss function of the RLSTM comprises a penalty term; and performing gesture recognition on the electroencephalogram data acquired based on the motion type brain-computer interface through the trained gesture recognition model, and controlling the mechanical palm to execute a corresponding gesture according to a gesture recognition result. The invention can effectively solve the problem of overfitting in the training process of a traditional gesture recognition model and the problems of BCI blindness and one-person-one-model existing in a brain-computer interface, and is high in recognition accuracy and high in practicability.

Description

technical field [0001] The invention relates to the technical field of EEG signal collection and recognition, in particular to a gesture recognition method based on a motion brain-computer interface. Background technique [0002] Gesture recognition with the help of brain-computer interface is different from wearable accelerometer devices, vision with images and videos, and biosignals. It has lower cost, wider application scenarios and is applicable to more subject. The substantive purpose of brain-computer interface technology is to build an interactive bridge between the central nervous system of the brain and the outside world, through which the direct path of human nerve transmission can be avoided, which is of great significance to some subjects with physiological disabilities, so , more and more experts are attracted to conduct research and exploration related to brain-computer interface. [0003] Active brain-computer interface, that is, does not require external en...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a gesture recognition method based on a sports-type brain-computer interface to solve the technical problems existing in the prior art, and can effectively solve the over-fitting problem existing in the training process of the traditional gesture recognition model, and the brain-computer interface The problems of "BCI blindness" and "one person, one model" in the interface have high recognition accuracy and strong practicability

Images