Faculty of Information Technology, Beijing University of Technology, Beijing, China.
Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China.
Technol Health Care. 2021;29(5):921-937. doi: 10.3233/THC-202619.
Motor imagery electroencephalogram (MI-EEG) play an important role in the field of neurorehabilitation, and a fuzzy support vector machine (FSVM) is one of the most used classifiers. Specifically, a fuzzy c-means (FCM) algorithm was used to membership calculation to deal with the classification problems with outliers or noises. However, FCM is sensitive to its initial value and easily falls into local optima.
The joint optimization of genetic algorithm (GA) and FCM is proposed to enhance robustness of fuzzy memberships to initial cluster centers, yielding an improved FSVM (GF-FSVM).
The features of each channel of MI-EEG are extracted by the improved refined composite multivariate multiscale fuzzy entropy and fused to form a feature vector for a trial. Then, GA is employed to optimize the initial cluster center of FCM, and the fuzzy membership degrees are calculated through an iterative process and further applied to classify two-class MI-EEGs.
Extensive experiments are conducted on two publicly available datasets, the average recognition accuracies achieve 99.89% and 98.81% and the corresponding kappa values are 0.9978 and 0.9762, respectively.
The optimized cluster centers of FCM via GA are almost overlapping, showing great stability, and GF-FSVM obtains higher classification accuracies and higher consistency as well.
运动想象脑电（MI-EEG）在神经康复领域发挥着重要作用，模糊支持向量机（FSVM）是最常用的分类器之一。具体来说，模糊 C 均值（FCM）算法用于隶属度计算，以处理具有异常值或噪声的分类问题。然而，FCM对初始值敏感，容易陷入局部最优。
提出遗传算法（GA）和 FCM 的联合优化，以增强模糊隶属度对初始聚类中心的鲁棒性，从而得到改进的 FSVM（GF-FSVM）。
通过改进的细化复合多变量多尺度模糊熵提取 MI-EEG 每个通道的特征，并融合形成一个试验的特征向量。然后，GA 用于优化 FCM 的初始聚类中心，通过迭代过程计算模糊隶属度，并进一步应用于分类两类 MI-EEG。
在两个公开可用的数据集上进行了广泛的实验，平均识别准确率分别达到 99.89%和 98.81%，相应的kappa 值分别为 0.9978 和 0.9762。
GA 优化的 FCM 聚类中心几乎重叠，显示出很强的稳定性，GF-FSVM 获得了更高的分类准确率和更高的一致性。
