Feature Extraction and Simulation of EEG Signals During Exercise-Induced Fatigue
Feature Extraction and Simulation of EEG Signals During Exercise-Induced Fatigue
复制标题
运动疲劳时脑电信号的特征提取与模拟
作者：
Zhong Yang;Huijie Ren
准确提取运动性疲劳时的脑电信号特征，可以为运动性疲劳检测和运动性疲劳损伤治疗提供科学依据。基于多元经验模式分解(MEMD)和希尔伯特-黄(HHT)算法，对运动性疲劳时的脑电信号进行了特征提取。MEMD将标准经验模式扩展到多通道信号处理，解决了传统算法的不足。它不适用于自适应、模式混叠和比例对齐。适用于分析多时间序列、多通道、多尺度的脑电信号分解。原始脑电信号通过MEMD后，计算不同层次脑电频段的能量均值、中位数和标准差，形成特征集。然后利用支持向量机分类器对提取的特征进行分类。仿真结果表明，该方法能有效地提取运动疲劳时的脑电信号特征。
Accurate extraction of EEG signal characteristics during exercise fatigue can provide a scientific basis for sports fatigue detection and exercise fatigue injury treatment. In this paper, based on multivariate empirical mode decomposition (MEMD) and Hilbert-Huang (HHT) algorithm, feature extraction of EEG signals during exercise fatigue is performed. MEMD extends standard experience mode to multi-channel signal processing and solves traditional algorithms. It is not suitable for self-adaptability, modal aliasing, and scale alignment. It is suitable for analyzing multi-time sequence; multi-channel and multi-scale EEG signal decomposition. After the original EEG signal passes through the MEMD, the energy mean, median and standard deviation of the EEG bands in different levels are calculated and used to form the feature set. Then the support vector machine (SVM) classifier is used to classify the extract the extracted features. The simulation results show that the proposed method can effectively extract the features of EEG signals during exercise fatigue.