Division of Cyber-Human Interaction Technologies, University of Guadalajara (UdG), Guadalajara 44100, Jalisco, Mexico.
Sensors (Basel). 2022 Apr 16;22(8):3066. doi: 10.3390/s22083066.
Epilepsy is a disease that decreases the quality of life of patients; it is also among the most common neurological diseases. Several studies have approached the classification and prediction of seizures by using electroencephalographic data and machine learning techniques. A large diversity of features has been extracted from electroencephalograms to perform classification tasks; therefore, it is important to use feature selection methods to select those that leverage pattern recognition. In this study, the performance of a set of feature selection methods was compared across different classification models; the classification task consisted of the detection of ictal activity from the CHB-MIT and Siena Scalp EEG databases. The comparison was implemented for different feature sets and the number of features. Furthermore, the similarity between selected feature subsets across classification models was evaluated. The best F1-score (0.90) was reported by the K-nearest neighbor along with the CHB-MIT dataset. Results showed that none of the feature selection methods clearly outperformed the rest of the methods, as the performance was notably affected by the classifier, dataset, and feature set. Two of the combinations (classifier/feature selection method) reporting the best results were K-nearest neighbor/support vector machine and random forest/embedded random forest.
癫痫是一种降低患者生活质量的疾病；它也是最常见的神经疾病之一。多项研究已经通过使用脑电图数据和机器学习技术来研究癫痫发作的分类和预测。从脑电图中提取了大量的特征来进行分类任务；因此，使用特征选择方法来选择那些有利于模式识别的特征是很重要的。在这项研究中，比较了一组特征选择方法在不同分类模型中的性能；分类任务包括从 CHB-MIT 和 Siena Scalp EEG 数据库中检测癫痫发作活动。在不同的特征集和特征数量上进行了比较。此外，还评估了跨分类模型的选定特征子集之间的相似性。基于 CHB-MIT 数据集，K-最近邻方法报告了最佳 F1 分数（0.90）。结果表明，没有一种特征选择方法明显优于其他方法，因为性能明显受到分类器、数据集和特征集的影响。报告最佳结果的两种组合（分类器/特征选择方法）是 K-最近邻/支持向量机和随机森林/嵌入式随机森林。
