Pattern recognition of head movement based on mechanomyography and its application

• Published in: Biomedizinische Technik Vol. 65; no. 1; pp. 51 - 60
• Main Authors: Gu, Xiaolin, Wu, Qing, Zhang, Yue, Zhong, Hao, Zhang, Shengli, Xia, Chunming, Yu, Jing
• Format: Journal Article
• Language: English
• Published: Germany Walter de Gruyter GmbH 01.02.2020
• Subjects: Algorithms; Bowing; Computer simulation; Discriminant Analysis; Feature extraction; Head; Head movement; Head Movements - physiology; Humans; Muscle, Skeletal - physiology; Muscles; Pattern recognition; Segmentation; Support Vector Machine; Support vector machines; Wavelet analysis; Wheelchairs; wheelchair; car model control; mechanomyography; feature extraction; head movement
• ISSN: 0013-5585; 1862-278X; 1862-278X
• DOI: 10.1515/bmt-2018-0007

The first part of this study investigated pattern recognition of head movements based on mechanomyography (MMG) signals. Four channel MMG signals were collected from the sternocleidomastoid (SCM) muscles and the splenius capitis (SPL) muscles in the subjects’ neck when they bowed the head, raised the head, side-bent to left, side-bent to right, turned to left and turned to right. The MMG signals were then filtered, normalized and divided using an unequal length segmentation algorithm into a single action frame. After extracting the energy features of the wavelet packet coefficients and the feature of the principal diagonal slices of the bispectrum, the dimension of the energy features were reduced by the Fisher linear discriminant analysis (FLDA). Finally, all the features were classified through the support vector machine (SVM) classifier. The recognition rate was up to 95.92%. On this basis, the second part of this study used the head movements to control a car model for simulating the control of a wheelchair, and the success rate was 85.74%.