External limb finger control method based on electroencephalogram and myoelectricity cooperation

Abstract

The invention provides an external limb finger control method based on electroencephalogram and myoelectricity cooperation, which comprises the following steps: taking a frontal myoelectricity signal and an electroencephalogram signal as a trigger instruction for action state conversion, and judging whether to output the trigger instruction or not according to a calculation result, so as to complete switching of different actions in upper limb rehabilitation training. An external limb robot can be controlled under the condition that the inherent limb freedom degree of human is not occupied, the human body movement function is enhanced or compensated in real time, and the potential of helping the stroke hemiplegia patient to achieve active movement rehabilitation is shown. Besides, the motor imagery electroencephalogram signals are identified and classified by using the convolutional neural network, the classification performance superior to that of a traditional classifier is shown, and various parameters of a convolutional neural network model are optimized by using a genetic algorithm, so that construction and use of a deep learning model under the condition of small samples are efficiently realized.

Description

technical field [0001] The invention belongs to the technical field of extremity finger control for rehabilitation, in particular to a method for controlling an extremity finger based on brain-myography coordination. Background technique [0002] The extremity robot is a new type of mechatronics robot proposed at ICRA, the top robotics conference in 2012. In the field of its control, most of the current research controls the external limb robot by tracking the user's hand posture and identifying the user's movement intention through electromyographic signals, and then converting it into control commands. For example, the right hand wears external limb fingers in rehabilitation training, Then the left hand makes specific movements to control the rehabilitation actions of the right hand. In this way, during rehabilitation training, the left hand cannot perform other tasks, which not only occupies the inherent freedom of human limbs while controlling the external limbs, but can...

AI Technical Summary

Problems solved by technology

In the field of its control, most of the current research controls the external limb robot by tracking the user's hand posture and identifying the user's movement intention through electromyographic signals, and then converting it into control instructions. For example, the right hand wears external limb fingers in rehabilitation training, Then the left hand makes specific movements to control the rehabilitation actions of the right hand. In this way, during the rehabilitation training, the left hand cannot perform other tasks, which not only occupies the inherent freedom of human limbs while controlling the external limbs, but cannot fully utilize the external limb robot as an emerging human body. Enhance the outstanding potential of equipment

Images