摘要
传统检测方法处理肌电信号时,个体差异比较大,针对这一不足,首先应用小波消噪理论对肌电信号进行预处理,将信号进行小波分解与重构,消除了肌电信号实际测量中不可测噪声的干扰,然后分析重构得到的信号的功率谱比值和对应肢体动作变化之间的关系。这种方法很适合处理非特定人的肌电信号。实验表明这种方法与单一使用功率谱比值法的方法相比,动作模式识别率得到了提高。同时,采用虚拟仪器技术提高仪器的测量精度,降低成本。
While surface electromyography(SEMG) using traditional disposal, the individual difference is obvious. To reduce these disadvanteages, the EMG signal is pre-disposed by wavelet de-noising theory. After the signal is decomposed and reconstructed by wavelet functions, the unmeasurabled noise jamming is eliminated, then use power spectrum coefficient method to analyse it. By calculated the parameters of power spectrum,we got the numerical value of power spectrum and knew the relations between hand movement and power spectrum coefficient. This method is suitable to the feature extraction of non-specified-person. The result of experimentation shows that its recognition of movement is much better than the method only using power spectrum coefficient.
出处
《杭州电子科技大学学报（自然科学版）》
2005年第1期14-17,共4页
Journal of Hangzhou Dianzi University：Natural Sciences
基金
国家自然科学基金资助项目(60474054)
浙江省自然科学基金资助项目(RC02070)
