An electromyographic signal feature fusion method based on genetic algorithm generalized canonical correlation analysis
A technology of typical correlation analysis and electromyography, applied in computing, computer components, instruments, etc., can solve problems such as increasing memory requirements, reducing speed, accuracy, and increasing classifier learning parameters, so as to reduce complexity and achieve good results. Monotonicity and robustness, the effect of feature space dimensionality reduction
Inactive Publication Date: 2019-04-02
HANGZHOU DIANZI UNIV
View PDF6 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In this case, traditional data integration techniques cannot provide high-performance solutions
In addition, the expansion of the dimension increases the learning parameters of the classifier, thereby reducing the speed and accuracy, and increasing the demand for memory
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
[0038] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following the described embodiment.
[0039] Such as figure 1 As shown, this embodiment includes the following steps:
[0040] Step 1. When the human body is doing daily behaviors, collect four channels of EMG signals from the human gastrocnemius, tibialis anterior, vastus medialis, and vastus externus, and obtain the average amplitude (MA) and Wilson amplitude (WAMP) of the four EMG signals. ), fuzzy entropy (FE), wavelet energy coefficient (EWT), and a 16-dimensional feature vector composed of 4 features of each of the 4 EMG signals. The 16-dimensional standard sample feature vector X is extracted dur...
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 provides an electromyographic signal feature fusion method based on genetic algorithm generalized canonical correlation analysis. The method includes obtaining average amplitude values,Wilson amplitudes, fuzzy entropies and wavelet energy coefficients of four paths of electromyographic signals when the human body performs daily behavior actions, and forming 16-dimensional eigenvectors by four features of each of the four paths of electromyographic signals; extracting a 16-dimensional standard sample feature vector X and a training sample feature vector Y; calculating an intra-class dispersion matrix and an inter-class dispersion matrix of X and Y respectively, and finally obtaining a generalized regular projection vector which maximizes a generalized canonical correlation discrimination criterion. Preferentially selecting the GCPV to obtain a new GCPV, and projecting the original characteristics to a new space to form a GCCA (GA-GCCA) combined with a genetic algorithm; and projecting the original features to a new plane through the newly obtained GCPV to obtain a finally fused electromyographic signal feature vector S. According to the method, the dimension is effectively reduced, and the optimal feature vector is dynamically selected while the monotonicity is improved.
Description
technical field [0001] The invention belongs to the field of feature fusion and relates to a method for fusion of myoelectric signal feature layers based on generalized canonical correlation analysis of genetic algorithms. Background technique [0002] As the concept of healthcare shifts from disease diagnosis and treatment to disease prevention, the importance of technological developments in systematic and continuous exercise management is increasingly emphasized. Due to the growing aging population, the number of elderly or infirm people who need assistance with daily activities is rapidly increasing, and this change has led to awareness of the importance of activity monitoring. Electromyography (EMG) sensors are widely used in medical diagnosis, rehabilitation and human-computer interaction. Compared with other wearable sensors, EMG sensors can directly show the myoelectric response of the human body to various activities. However, there are still considerable challeng...
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): G06K9/62
CPCG06F18/21322G06F18/2193G06F18/253
Inventor 席旭刚汤敏彦姜文俊石鹏袁长敏章燕杨晨佘青山罗志增
Owner HANGZHOU DIANZI UNIV