Degirmenci Murside, Yuce Yilmaz Kemal, Perc Matjaž, Isler Yalcin
Kutahya Vocational School, Kutahya Health Sciences University, Kutahya, Türkiye.
Department of Computer Engineering, Alanya Alaaddin Keykubat University, Antalya, Türkiye.
Front Hum Neurosci. 2024 Dec 17;18:1525139. doi: 10.3389/fnhum.2024.1525139. eCollection 2024.
Motor Imagery (MI) Electroencephalography (EEG) signals are non-stationary and dynamic physiological signals which have low signal-to-noise ratio. Hence, it is difficult to achieve high classification accuracy. Although various machine learning methods have already proven useful to that effect, the use of many features and ineffective EEG channels often leads to a complex structure of classifier algorithms. State-of-the-art studies were interested in improving classification performance with complex feature extraction and classification methods by neglecting detailed EEG channel and feature investigation in predicting MI tasks from EEGs. Here, we investigate the effects of the statistically significant feature selection method on four different feature domains (time-domain, frequency-domain, time-frequency domain, and non-linear domain) and their two different combinations to reduce the number of features and classify MI-EEG features by comparing low-dimensional matrices with well-known machine learning algorithms.
Our main goal is not to find the best classifier performance but to perform feature and channel investigation in MI task classification. Therefore, the detailed investigation of the effect of EEG channels and features is implemented using a statistically significant feature distribution on 22 EEG channels for each feature set separately. We used the BCI Competition IV Dataset IIa and 288 samples per person. A total of 1,364 MI-EEG features were analyzed in this study. We tested nine distinct classifiers: Decision tree, Discriminant analysis, Logistic regression, Naive Bayes, Support vector machine, k-Nearest neighbor, Ensemble learning, Neural networks, and Kernel approximation.
Among all feature sets considered, classifications performed with non-linear and combined feature sets resulted in a maximum accuracy of 63.04% and 47.36% for binary and multiple MI task predictions, respectively. The ensemble learning classifier achieved the maximum accuracy in almost all feature sets for binary and multiple MI task classifications.
Our research thus shows that the statistically significant feature-based feature selection method significantly improves the classification performance with fewer features in almost all feature sets, enabling detailed and effective EEG channel and feature investigation.
运动想象（MI）脑电图（EEG）信号是非平稳且动态的生理信号，其信噪比很低。因此，难以实现高分类准确率。尽管各种机器学习方法已被证明对此有效，但使用众多特征和无效的EEG通道往往会导致分类器算法结构复杂。当前的前沿研究致力于通过复杂的特征提取和分类方法来提高分类性能，却忽略了在从EEG预测MI任务时对EEG通道和特征的详细研究。在此，我们通过比较低维矩阵与知名机器学习算法，研究具有统计学意义的特征选择方法对四个不同特征域（时域、频域、时频域和非线性域）及其两种不同组合的影响，以减少特征数量并对MI-EEG特征进行分类。
我们的主要目标不是找到最佳分类器性能，而是在MI任务分类中进行特征和通道研究。因此，使用具有统计学意义的特征分布，分别对每个特征集在22个EEG通道上详细研究EEG通道和特征的影响。我们使用了脑机接口竞赛IV数据集IIa，每人有288个样本。本研究共分析了1364个MI-EEG特征。我们测试了九种不同的分类器：决策树、判别分析、逻辑回归、朴素贝叶斯、支持向量机、k近邻、集成学习、神经网络和核近似。
在所有考虑的特征集中，对于二分类和多分类MI任务预测，使用非线性和组合特征集进行的分类分别达到了63.04%和47.36%的最高准确率。集成学习分类器在几乎所有特征集的二分类和多分类MI任务分类中都取得了最高准确率。
我们的研究表明，基于具有统计学意义的特征的特征选择方法在几乎所有特征集中用更少的特征显著提高了分类性能，从而能够对EEG通道和特征进行详细且有效的研究。
