基于表面肌电信号的人体运动意图识别方法研究

提出了基于表面肌电信号进行人体运动意图识别的新方法。该方法将智能发育思想结合其中,分为离线知识库建立和在线知识库检索两个过程。首先,进行离线训练,建立IHDR(Incremental Hierarchical Discriminant Regression)知识库。采集人体表面肌电信号,对肌电信号进行小波分解,将各层小波系数的方差作为每个通道信号的特征;然后,将每个通道的特征作为输入,人体运动行为作为输出,离线建立基于智能发育思想的IHDR知识库。人体运动意图识别的过程即知识库的检索运用过程,通过每个通道的特征来在线检索IHDR知识库,搜索到合适的节点即为运动意图。实验表明,基于智能发育思想的人体运动意图识别方法可以达到满意的识别率。

A new mental development based identification method of human body movement intention using sEMG signal is proposed.The method is consist of two steps,i.e.knowledge-base establishing off-line and searching of knowledge-base on-line.Firstly,establish IHDR(Incremental Hierarchical Discriminant Regression) based knowledge-base by off-line training.Primary characteristics of each channel of sEMG signal are extracted using wavelet method.Then,the primary characteristics are as the input data of knowledge-base,at...

国家自然科学基金(No.60705028)