提取表面肌电信号的复杂性测度信息 ,利用原始数据的复杂度指标构造特征矢量对四种前臂动作进行分类 ,取得了较好的识别效果。通过比较 ,发现基于原始数据的复杂度指标在分类性能上要优于基于重构序列的复杂度。肌电信号的复杂度算法简单 ,适合短数据运算 ,能够满足实时处理的要求。作为一种新的肌电信号特征 ,复杂性测度也为生理与病理分析提供了新的思路 The complexity information of surface electromyography (EMG) signal is extracted, and the feature vector is constructed based on the complexity index of the original data to classify the four kinds of forearm motion, and a good recognition effect is achieved. By comparison, it is found that the complexity index based on the original data is better than the complexity based on the reconstruction sequence in classification performance. The complexity of EMG signal algorithm is simple, suitable for short data operations, to meet the requirements of real-time processing. As a new feature of EMG signal, the complexity measure also provides a new idea for physiological and pathological analysis