采用核主成分分析和相关向量机的人体运动意图识别

发布时间：2018-06-30 08:15

本文选题：表面肌电信号 + 核主成分分析　；参考：《机器人》2017年05期

【摘要】：针对人体步态识别率低的问题,提出了一种将核主成分分析(KPCA)和相关向量机(RVM)相结合的步态识别方法.首先,选择表面肌电信号(s EMG)作为步态识别信息源,提取表面肌电信号的小波包能量特征.然后,采用核主成分分析方法降维特征值去除冗余的信息,得到能反映步态特征的特征值.最后,利用相关向量机对步态特征向量进行分类,识别平地行走、上楼、下楼、上坡、下坡5种步态.通过分析不同受试者步态识别结果,验证了该方法的可行性和实用性,并和BP(反向传播)神经网络、SVM(支持向量机)等方法比较,结果表明该方法分类时间为2.6609×10~(-4)s,识别正确率为96.67%,是一种有效的步态识别方法.
[Abstract]:To solve the problem of low gait recognition rate, a gait recognition method combining kernel principal component analysis (KPCA) and correlation vector machine (RVM) is proposed. Firstly, the surface EMG signal (s EMG) is selected as the gait recognition information source to extract the wavelet packet energy features of the surface EMG signal. Then the kernel principal component analysis (KPCA) method is used to reduce the dimensionality eigenvalues to remove redundant information and to obtain the eigenvalues which can reflect the gait features. Finally, the gait feature vectors are classified by correlation vector machine, and five gaits are identified, such as walking on flat ground, going upstairs, going downstairs, going up and down slope. The feasibility and practicability of this method are verified by analyzing the gait recognition results of different subjects, and compared with BP (back propagation) neural network and SVM (support vector machine). The results show that the classification time is 2.6609 脳 10 ~ (-4) s and the recognition accuracy is 96.67. This method is an effective gait recognition method.
【作者单位】：郑州轻工业学院建筑环境工程学院;河北工业大学控制科学与工程学院;智能康复装置与检测技术教育部工程研究中心;
【基金】：国家自然科学基金(61203323) 河南省高等学校重点科研项目(16B413006) 河北省自然科学基金(F2015202150,F2017202119) 河南省科技厅重点科研项目(162300410070)
【分类号】：TN911.7

【相似文献】