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

A motion image recognition method based on mutual information feature extraction and multi-person fusion

A technology of motor imagery and feature extraction, applied in the field of brain-computer interface and feature engineering research, which can solve problems such as single user mode, misjudgment stability, etc.

Active Publication Date: 2022-07-08
HANGZHOU DIANZI UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the research on motor imagery brain-computer interface is a single user mode, which has limitations such as misjudgment and stability.

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
  • A motion image recognition method based on mutual information feature extraction and multi-person fusion
  • A motion image recognition method based on mutual information feature extraction and multi-person fusion
  • A motion image recognition method based on mutual information feature extraction and multi-person fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below with reference to the accompanying drawings.

[0036] The system flow chart of the implementation of the present invention is as attached figure 1 As shown: firstly collect the required EEG signals and record the motor imagery at the same time, then preprocess the EEG data, then filter the preprocessed data to a specific frequency band to calculate mutual information feature extraction, and finally use KNN for classification.

[0037] The specific implementation steps of the present invention are as follows, taking two users as an example:

[0038] Step 1: Simultaneously collect the EEG signals of two users through a multi-channel EEG acquisition device, and collect multiple times. During the same acquisition, the two users have the same motor imagery task; the user's motor imagery task can be the same in each acquisition. Can also be different. like figure 2 As shown, this embodiment adopts 64-channel Neuroscan ...

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 motion image recognition method based on mutual information feature extraction and multi-person fusion. The present invention is as follows: 1. Simultaneously collect the EEG signals of P users performing motor imagery through a multi-channel EEG acquisition device. 2. Preprocess the collected EEG data of P users respectively. 3. Extracting one or more mutual information vectors from the EEG data collected each time. 4. Multi-person movement image recognition. The invention utilizes the extraction of multi-person EEG mutual information, and finally performs classification by the K-nearest neighbor algorithm through three different levels of fusion strategies, and can quickly and accurately realize the human brain movement image recognition based on multi-person EEG data.

Description

technical field [0001] The invention belongs to the field of feature engineering research in the field of brain-computer interface, in particular to a method for feature extraction based on mutual information and multi-person fusion feature classification. Background technique [0002] Motor imagery refers to the direct use of brain ideas to imagine body movements without actual body behaviors, and convert them into control instructions, which are then implemented by the controller for subsequent actual operations. The motor-imagination EEG is an endogenous spontaneous EEG. Unlike the induced EEG, it does not require external stimulation. As long as the person performs imaginative movements, the brainwaves show a specific waveform. With the advancement of brain neuroscience and information technology, motor imagery can serve general groups and special groups, and provide an important means for brain science research. [0003] At present, the research on the motor imagery br...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/01G06K9/00G06K9/62
CPCG06F3/015G06F2218/08G06F2218/12G06F18/253G06F18/214
Inventor 孔万增杨宇朱莉王鑫洋张建海
Owner HANGZHOU DIANZI UNIV