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%.

中文翻译：

---

基于力学的头部运动模式识别及其应用

本研究的第一部分研究了基于机械肌谱 (MMG) 信号的头部运动模式识别。当受试者低头、抬起头、侧弯向左、侧弯向右、转向左转右转。然后使用不等长分割算法对 MMG 信号进行过滤、归一化和划分为单个动作帧。在提取了小波包系数的能量特征和双谱主对角切片的特征后，通过Fisher线性判别分析（FLDA）对能量特征进行降维。最后，通过支持向量机（SVM）分类器对所有特征进行分类。识别率高达95.92%。在此基础上，本研究的第二部分利用头部运动控制汽车模型来模拟对轮椅的控制，成功率为85.74%。