Multi-channel surface electromyography action intention recognition method without feature description
A multi-channel, featureless technology, applied in the fields of medical science, diagnosis, diagnostic recording/measurement, etc., can solve problems such as the inability to fully express the intention of movement, and achieve the effect of improving accuracy and reliability
Active Publication Date: 2022-03-25
深圳沃立康生物医疗有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
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
[0070] In the present embodiment, a multi-channel surface myocymp is integrated with a multi-channel surface, and the overall process works. figure 1 As shown, 1. Calculate the multi-dimensional vector of surface electromyrower carrying P known actions and determines the domain value of each action, and this is used as a standard for moving the surface electromyrower data. 2. A matrix H made compared to multiplication of multi-dimensional multi-dimensional multi-dimensional composed of surface electromyrics that require action intent recognition to obtain a matrix V compared to multiplication j . 3. For the screening matrix F and the comparative value matrix to perform a matrix subtraction method, the maximum value element in the deviation value matrix is extracted, and the standard operation intent for the maximum value corresponds to the action intent for the surface electromardinal data.
[0071] In response to step 1 is made as follows.
[0072] Step 1.1, the effective surfa...
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 multi-channel surface electromyography action intention recognition method without feature description, the steps of which include: 1. Calculate the multi-dimensional vector of surface electromyography data carrying P known action intentions and determine the division of each action Value, which is used as the standard for screening the action intention of the surface electromyography data. 2. Comparing and multiplying the obtained surface electromyographic data that needs action intention recognition with the matrix H composed of P multidimensional vectors of known actions to obtain the comparison value matrix V j . 3. Perform matrix subtraction for the screening matrix F and the comparison value matrix to obtain the deviation value matrix, extract the maximum value element in the deviation value matrix and determine that the standard action intention corresponding to the maximum value is the action intention represented by the surface electromyography data. The present invention recognizes action intentions by using multi-channel surface electromyography without feature description, which can effectively avoid the problem that the identification result is affected by inaccurate surface electromyographic feature descriptions, thereby improving the accuracy and reliability of action intention identification.
Description
Technical field [0001] The present invention relates to the technical field of multi-channel surface mymp electromycmon signal operation intent, and in particular, a recognition technique that does not require a surface electromymp electromyrower of the limb movement. Background technique [0002] The body's limb action is achieved by single joint movement or multi-joint motion, while the joint movement has sliding, flexion, horizontal flexion, exhibition, cyclone and annulus; these complex exercises are often involved in the completion of multiple muscles . Therefore, accurately identify multi-channel electromyrographic signals common meanings, which will undoubtedly express the intention of human body limbs more completely. [0003] The current electromyophoresis action recognition technique requires an accurate description of the surface electromechanical characteristics obtained by the specific position of a known exercise intended. The foregoing statement of the human body i...
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 Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/00A61B5/389
CPCA61B5/00A61B5/72
Inventor 杨建伟李正茂苏权超
Owner 深圳沃立康生物医疗有限公司