Natural action electroencephalography recognition method based on source positioning and brain network
A recognition method and source location technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as inability to distinguish effects of natural actions, and achieve the effect of ensuring robustness, improving accuracy and speed
Active Publication Date: 2021-02-26
SOUTHEAST UNIV
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the complexity of natural actions and the use of many joints, such as hand holding, finger pinching, rotation, plugging, etc., and many times these actions activate the same motor brain area, traditional EEG recognition methods cannot be used for natural Action achieves a good distinguishing effect
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.
[0048] The present invention designs a natural action EEG recognition method based on source location and brain network, such as figure 1 As shown, the steps are as follows:
[0049] (1) Multi-channel EEG measurement of natural movements;
[0050] (2) Preprocess the collected EEG signal, remove artifacts, and extract action-related cortical potential (MRCP), θ wave, α wave, β wave and γ wave;
[0051] (3) Determine the lead field matrix of the signal, use the L1 regularization constraint to find the initial value solution of the source, and then use the successive hyper-relaxation method to iterate the initial value solution, and use the latest solution vector as the...
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
Login to View More Abstract
The invention discloses a natural action electroencephalography recognition method based on source positioning and a brain network. The method comprises the steps that (1) multichannel electroencephalography measurement is conducted on natural actions; (2) acquired EEG signals are preprocessed, and MRCP, theta waves, alpha waves, beta waves and gamma waves are extracted; (3) a lead field matrix ofthe signals is determined, initial value solutions of sources are solved by utilizing L1 regularization constraint, and iterative solving is conducted through a successive over relaxation method to obtain a source positioning result; (4) the sources are taken as nodes, the PLV between each pair of sources is calculated one by one point in time by adopting a short-time sliding window, and the brain network is constructed; and (5) a network adjacency matrix and five brain network indexes are calculated one by one point in time, the characteristics are sent into a classifier for training and testing, and statistical test is conducted on the brain network indexes. According to the method, a traditional source positioning method is improved by combining a T-wMNE algorithm and the successive over relaxation method, and the brain network is constructed by taking the sources as the nodes, so that the decoding precision of natural action electroencephalography is improved, and a neural operation mechanism of a human body is revealed.
Description
technical field [0001] The invention belongs to the field of biological signal processing, and relates to an EEG signal identification method, in particular to an EEG identification method for natural actions based on source location and brain network, which provides technical means for EEG decoding of natural actions. Background technique [0002] Brain-computer interface (BCI) is a means of communicating and controlling directly with the outside world through EEG signals, and it is also a research hotspot in the fields of rehabilitation medicine engineering and neural engineering technology in recent years. In recent years, BCI-based rehabilitation training has mainly relied on repetitive imagery of basic motor tasks, such as performing the operation of holding a glass through repeated foot motor imagery as a control signal, which brings unnatural and uncoordinated operations to the user experience. In order to allow users to obtain a better operating experience, the imag...
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
Login to View More IPC IPC(8): A61B5/369A61B5/374A61B5/372
CPCA61B5/7225A61B5/7203A61B5/7264A61B5/7235A61B5/372A61B5/725A61B5/7267A61B5/7278G06F3/015
Inventor 徐宝国邓乐莹汪逸飞王欣宋爱国
Owner SOUTHEAST UNIV