基于emg-kja神经肌骨动力学模型下肢动作模式识别及运动轨迹预测word格式论文.docx

优秀毕业论文 精品参考文献资料 contrasting the two modeling methods, the ideal prediction way is SVM whose error is much lower than that of ANN. In order to inprove the degree of real- time and on- line of prediction, a set of muscle-source channel optimization program was designed for each action by removing the unrelated channel one-by-one according to the correlation coefficient between RMS of sEMG signals and knee joint angle. Tthe prediction results were tested to find out the optimal prediction method. The research results in this thesis are not only conductive for the future design of EMG controlled lower limb prosthesis and the exploration on relevant neurological and kinematic mechanism, but also could be employed in motion sensing, human-machine interface, virtual reality, remote control and other related fields. Key Words: Surface Electromyogram (sEMG), Knee-Joint-Angle (KJA), Feature Parameters, Pattern Classification, Kinematic Trajectory Prediction, Muscle-Source Channle Optimization 6 目 录  HYPERLINK \l _bookmark0 第一章 绪 论 1  HYPERLINK \l _bookmark1 1.1 研究背景 1  HYPERLINK \l _bookmark2 1.2 假肢与神经肌骨动力学简介 2  HYPERLINK \l _bookmark3 1.2.1 假肢简介 2  HYPERLINK \l _bookmark4 1.2.2 神经肌骨动力学模型 4  HYPERLINK \l _bookmark5 1.2.3 肌电假肢 6  HYPERLINK \l _bookmark6 1.2.4 研究现状 8  HYPERLINK \l _bookmark7 1.3 本课题研究内容、目的及意义 9  HYPERLINK \l _bookmark8 第二章 EMG-KJA 信号采集平台与实验方案 12  HYPERLINK \l _bookmark9 2.1 下肢关键动作模态介绍 12  HYPERLINK \l _bookmark10 2.2 表面肌电检测的下肢肌群位置选择 13  HYPERLINK \l _bookmark11 2.3 EMG-KJA 信号采集平台 15  HYPERLINK \l _bookmark12 2.3.1 表面肌电采集系统 15  HYPERLINK \l _bookmark13 2.3.2 三维运动捕捉系统 18  HYPERLINK \l _bookmark14 2.4 实验准备 20  HYPERLINK \l _bookmark15 2.4.1 受试者选取 20  HYPERLINK \l _bookmark16 2.4.2 EMG 采集电极粘贴 20  HYPERLINK \l _bookmark17 2.4.3 KJA 采集体表 marker 点粘贴 22  HYPERLINK \l _bookmark18 2.5 实验设置 22  HYPERLINK \l _bookmark19 第三章 EMG 信号预处理及特征提取 24  HYPERLINK \l _bookmark20 3.1 EMG 信号预处理 24  H