摘要
针对肌电信号的非平稳特性 ,采用短时傅里叶变换方法对表面肌电信号进行分析 ,并通过奇异值分解有效地提取特征矢量进行模式识别 ,能够成功地从掌长肌和肱桡肌采集的两道表面肌电信号中识别展拳、握拳、腕内旋、腕外旋四种运动模式。实验表明 ,基于短时傅里叶变换的奇异值分解方法是一种稳定、有效的特征提取方法。
A Surface EMG signal identification method based on short time fourier transform is presented in this paper.To fully utilize the nonstationary character of the EMG signal,short time fourier transform is employed to get the signal's time frequency representation.Singular value decomposition is then used in the spectrogram to extract feature vector for pattern identification.Four types of movement of forearm,hand grasp,hand extension,wrist pronation and wrist supination can be identified from surface EMG signals.Experimental results show that it is a stable and efficient method for extracting features.
出处
《中国医疗器械杂志》
CAS
2000年第3期133-136,共4页
Chinese Journal of Medical Instrumentation
