Abstract
Background Spatial characteristics of sEMG signals are obtained by high-density matrix sEMG electrodes for further complex upper arm movement classification. Multiple electrode channels of the high-density sEMG acquisition device aggravate the burden of the microprocessor and deteriorate control system's real-time performance at the same time. A shoulder motion recognition optimization method based on the maximizing mutual information from multiclass CSP selected spatial feature channels and wavelet packet features extraction is proposed in this study. Results The relationship between the number of channels and recognition rate is obtained by the recognition optimization method. The original 64 electrodes channels are reduced to only 4-5 active signal channels with the accuracy over 92%. Conclusion The shoulder motion recognition optimization method is combined with the spatial-domain and time-frequency-domain features. In addition, the spatial feature channel selection is independent of feature extraction and classification algorithm. Therefore, it is more convenient to use less channels to achieve the desired classification accuracy.
Highlights
Analysis of user’s intention through noninvasive surface electromyography acquisition methods has the advantages of shorter experimental preparation time and more convenient acquisition
Three healthy experimental subjects were selected. sEMG signals were recorded by a 64-channel highdensity matrix electrode, which is made by OT Bioelectronics in Italy, as shown in Figure 1(a). 64-channel high-density matrix-type electrode arrangement is 5 rows × 13 columns, the spacing between adjacent electrodes is 8 mm, the diameter of each electrode is 3 mm, and the number and position of 64 channels are arranged in a certain order, which is convenient to determine the electrode position by the channel number
12 12 10 10 11 11 dimensional representation by linear transformation without discarding the original sEMG information features. e subject eight different motion high-density sEMG signal spatial filter preprocessing results by principle component analysis (PCA) are shown in Figure 3; the linear dimensionality reduction process of the original sEMG data is visualized by PCA and the contribution rate is calculated to be 95%; the separation matrix is determined to retain the least number of spatial filters, which achieves the purpose of reducing the number of dimensions
Summary
Spatial characteristics of sEMG signals are obtained by high-density matrix sEMG electrodes for further complex upper arm movement classification. Multiple electrode channels of the high-density sEMG acquisition device aggravate the burden of the microprocessor and deteriorate control system’s real-time performance at the same time. A shoulder motion recognition optimization method based on the maximizing mutual information from multiclass CSP selected spatial feature channels and wavelet packet features extraction is proposed in this study. E relationship between the number of channels and recognition rate is obtained by the recognition optimization method. E original 64 electrodes channels are reduced to only 4-5 active signal channels with the accuracy over 92%. E shoulder motion recognition optimization method is combined with the spatial-domain and time-frequency-domain features. The spatial feature channel selection is independent of feature extraction and classification algorithm. The spatial feature channel selection is independent of feature extraction and classification algorithm. erefore, it is more convenient to use less channels to achieve the desired classification accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
