Unlock instant, AI-driven research and patent intelligence for your innovation.

Hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions

A technology of brain-computer interface and motion intention, applied in character and pattern recognition, computer components, medical science, etc., can solve problems such as difficult distinction, low spatial resolution, and few MI-BCI instruction sets

Active Publication Date: 2021-04-09
TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the volume conductor effect in the brain, the EEG signal collected from the scalp often has a low signal-to-noise ratio. Therefore, the spatial resolution of the EEG-based MI-BCI is poor, and it is difficult to identify fine imaginative action tasks and the movement intention of adjacent limbs. Currently, the MI-BCI There are fewer movement modes, and the single action mode is limited to large body movements such as the left hand, right hand, tongue, and feet, resulting in fewer MI-BCI output instruction sets
Especially for the lower limbs of the human body, due to the almost overlapping brain projection areas of the left and right feet, it is difficult to decode the movement intention of the lower limbs. Therefore, the feet can only be used as an instruction set at present, and cannot effectively identify finer lateral movement intentions.
[0006]The EEG signal collected from the brain scalp has a high time resolution due to the volume conductor effect, but the spatial resolution is relatively low, so it is similar to the sensorimotor cortex of the brain For the limb task of spatial position, it is extremely difficult to recognize the movement intention, especially for the lower limbs of the human body, such as the human feet. According to the projection relationship between the limb parts and the motor sensory cortex, the motor function areas of the left foot and the right foot overlap in the center It is a limited area in the back of the area, so it is extremely difficult to directly use the ERD features of motor imagery to distinguish the related movements of the human left / right foot. In the current relatively mature motor imagery body movement patterns, both feet are regarded as the same movement pattern , without lateral distinction
[0007] In the existing literature, there are few relevant reports on the classification of lower limbs, and the accuracy of motion intention recognition in some existing reports has not reached 70%. BCI Threshold Levels of
However, the current situation that it is difficult to recognize the movement intention of lower limbs will inevitably affect the rehabilitation effect of MI-BCI lower limb motor function.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions
  • Hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions
  • Hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions, comprising the following steps:

[0039] Step 1: Randomly perform the motor imagery task of the left foot / right foot, and the motor imagery task induces desynchronization features (ie, ERD features); a fixed frequency electrical stimulation is applied to the posterior tibial nerve of the medial malleolus of the right foot, and the electrical stimulation induces homeostasis Somatosensory evoked potential characteristics (i.e. SSSEP characteristics), collect the original EEG data of motor imagination tasks under electrical stimulation;

[0040] Step 2: Preprocessing the collected raw EEG data;

[0041] Step 3: Then use the co-space pattern algorithm based on multi-frequency spatial filtering to extract features from the preprocessed EEG data to obtain a fusion feature vector;

[0042] Step 4: Use the support vector machine method to perform binary classific...

Embodiment 2

[0054] This embodiment is based on the hybrid online brain-computer interface method in Embodiment 1, and introduces its experimental paradigm process, such as figure 1 shown.

[0055] During the performance of the motor imagery task, the subjects were required to perform the motor imagery task of hooking the left foot or the right foot under the condition of electrical stimulation of the right foot. The motor imagery task is performed from a first-person perspective, imagining the feeling of the hook movement rather than the picture. The duration of the motor imagery task was 5 seconds. One second before the execution of the motor imagery task, the electrical stimulator began to apply electrical stimulation to the right foot, and ">" and red "+", the direction of the arrow represents which foot will be performed the somatosensory stimulation motor imagery task next. During this period, the subjects were prepared to perform a motor imagery task of either the left or the right...

Embodiment 3

[0058] The placement of stimulating electrodes on the inner ankle of the right foot is as follows: image 3 As shown, before the start of the experiment, the specific stimulation position and current stimulation intensity of each subject need to be adjusted separately to achieve the effect of toe contraction and no pain. Different subjects have different lower limb electrical stimulation intensity, generally between 10- between 25mA. Electric stimulation uses a current pulse with a pulse width of 0.2ms. The stimulation position is about 2-3cm behind the inner ankle of both feet. A saddle-shaped electrode with a size of 3.5×2.3cm is used. During the experiment, the subjects sit quietly at the computer in a comfortable posture. About 60cm in front of the screen, keep the whole body relaxed, avoid body shaking and subtle body movements during the experiment, and minimize the number of blinks during the task execution.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions. According to the hybrid online brain-computer interface method, electrical stimulation with a certain frequency is applied to a right foot while left and right foot hooking imaginary actions are performed, and left / right foot movement intention decoding is performed by combining SSSEP features generated by electrical stimulation of lower limbs of a human body and ERD features generated by MI. A hybrid brain-computer interface can successfully decode the movement intentions of feet of the human body, distinguish limb tasks at the spatial positions close to a brain, improve the MI-BCI spatial resolution and expand an instruction set of a MI motion mode, and a new method is provided for promoting the application of MI-BCI in the field of lower limb rehabilitation to explore a new way.

Description

technical field [0001] The invention relates to the technical field of brain-computer interface, in particular to a hybrid online brain-computer interface method for lateral recognition of left and right foot movement intentions. Background technique [0002] Brain-computer interface (Brain-computer interface, BCI) refers to a system that detects central nervous system activity and converts it into artificial output. It can replace, repair, enhance, supplement or improve the normal output of the central nervous system, thereby changing the central nervous system. The interaction between the nervous system and the internal and external environment. The brain-computer interface establishes a new type of connection channel between the brain and the environment. This channel can make the brain independent of the conventional peripheral nervous system, and directly exchange information between the thinking activities of the human brain and the internal and external environment. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B5/383A61B5/00G06K9/62
CPCA61B5/7225A61B5/7203A61B5/725G06F18/24G06F18/253
Inventor 边琰赵丽李嘉莹刘昭君
Owner TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE