Rashid Mamunur, Bari Bifta Sama, Hasan Md Jahid, Razman Mohd Azraai Mohd, Musa Rabiu Muazu, Ab Nasir Ahmad Fakhri, P P Abdul Majeed Anwar
Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, Malaysia.
Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronic Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, Malaysia.
PeerJ Comput Sci. 2021 Mar 2;7:e374. doi: 10.7717/peerj-cs.374. eCollection 2021.
Brain-computer interface (BCI) is a viable alternative communication strategy for patients of neurological disorders as it facilitates the translation of human intent into device commands. The performance of BCIs primarily depends on the efficacy of the feature extraction and feature selection techniques, as well as the classification algorithms employed. More often than not, high dimensional feature set contains redundant features that may degrade a given classifier's performance. In the present investigation, an ensemble learning-based classification algorithm, namely random subspace -nearest neighbour (-NN) has been proposed to classify the motor imagery (MI) data. The common spatial pattern (CSP) has been applied to extract the features from the MI response, and the effectiveness of random forest (RF)-based feature selection algorithm has also been investigated. In order to evaluate the efficacy of the proposed method, an experimental study has been implemented using four publicly available MI dataset (BCI Competition III dataset 1 (data-1), dataset IIIA (data-2), dataset IVA (data-3) and BCI Competition IV dataset II (data-4)). It was shown that the ensemble-based random subspace -NN approach achieved the superior classification accuracy (CA) of 99.21%, 93.19%, 93.57% and 90.32% for data-1, data-2, data-3 and data-4, respectively against other models evaluated, namely linear discriminant analysis, support vector machine, random forest, Naïve Bayes and the conventional -NN. In comparison with other classification approaches reported in the recent studies, the proposed method enhanced the accuracy by 2.09% for data-1, 1.29% for data-2, 4.95% for data-3 and 5.71% for data-4, respectively. Moreover, it is worth highlighting that the RF feature selection technique employed in the present study was able to significantly reduce the feature dimension without compromising the overall CA. The outcome from the present study implies that the proposed method may significantly enhance the accuracy of MI data classification.
脑机接口（BCI）对于神经疾病患者而言是一种可行的替代性交流策略，因为它有助于将人类意图转化为设备指令。BCI的性能主要取决于特征提取和特征选择技术的有效性，以及所采用的分类算法。通常，高维特征集包含可能会降低给定分类器性能的冗余特征。在本研究中，提出了一种基于集成学习的分类算法，即随机子空间-最近邻（-NN），用于对运动想象（MI）数据进行分类。已应用共同空间模式（CSP）从MI响应中提取特征，并且还研究了基于随机森林（RF）的特征选择算法的有效性。为了评估所提出方法的有效性，使用四个公开可用的MI数据集（BCI竞赛III数据集1（数据-1）、数据集IIIA（数据-2）、数据集IVA（数据-3）和BCI竞赛IV数据集II（数据-4））进行了一项实验研究。结果表明，与所评估的其他模型（即线性判别分析、支持向量机、随机森林、朴素贝叶斯和传统的-NN）相比，基于集成的随机子空间-NN方法对于数据-1、数据-2、数据-3和数据-4分别实现了99.21%、93.19%、93.57%和90.32%的卓越分类准确率（CA）。与近期研究中报道的其他分类方法相比，所提出的方法对于数据-1、数据-2、数据-3和数据-4的准确率分别提高了2.09%、1.29%、4.95%和5.71%。此外，值得强调的是，本研究中采用的RF特征选择技术能够在不影响整体CA的情况下显著降低特征维度。本研究的结果表明，所提出的方法可能会显著提高MI数据分类的准确率。
