一种基于HHT和AR模型的手部运动模式识别方法  

Pattern Recognition of Hand Motions Based on HHT and AR-Model

作　　者：罗志增[1] 马文杰[1] 孟明[1] 

机构地区：[1]杭州电子科技大学机器人研究所,杭州310018

出　　处：《模式识别与人工智能》2008年第2期227-232,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60705010);浙江省科技计划支持项目(No.2007C23088)资助

摘　　要：为了实现基于表面肌电信号(SEMG)的手部动作运动模式识别,提出一种 Hilbert-Huang 变换(HHT)和自回归(AR)模型相结合的特征提取算法.该方法依据 HHT 后各层固有模态函数(IMF)的瞬时频率定义每层 IMF的频率有效度,由频率有效度选取6层平稳的 IMF,同时考察具有最大频率有效度的 IMF,并以该 IMF 的瞬时幅值确定动作信号的起止点.对6层 IMF 中的动作信号建立 AR 模型提取手部运动模式的特征向量.提取主成分后,将降维的动作特征向量输入 SVM 分类器,实现基于 SEMG 信号的手部多运动模式的识别.对伸腕、屈腕、握拳、展拳4种手部动作的识别实验表明,该方法的识别正确率可达91%.In order to recognize the hand motions based on the surface electromyogram （SEMG）, a feature extraction algorithm is presented which is built by the combination of Hilbert-Huang transform （HHT） and AR-model. According to the frequency-credit of each intrinsic mode function （IMF） after HHT, six intrinsic mode functions （IMFs） are selected. In the meantime, the rectangle window is built to cut motion signals of the six IMFs based on the motion-start and the motion-end points. The motion-start and motion-end points are decided by the instantaneous amplitude of the IMF with the largest frequency-credit. AR-model of each IMF is built to extract the hand-motion features. Finally, the motion-feature vector processed by principal component analysis （PCA） is input into the SVM classifier to recognize the hand motions. The experimental results indicate that the proposed method can discriminate the four hand-motion patterns （namely, palmar dorsiflexion and flexion, hand opening and closing） with the correct rate up to 91%.

关 键 词：Hilbert—Huang变换(HHT) 自回归(AR)模型 支持向量机(SVM) 模式识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]