期刊
JOURNAL OF COMPUTATIONAL SCIENCE
卷 68, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.jocs.2023.102000
关键词
Manifold learning; Brain-computer interface; Steady-state visual evoked potential; Principal component analysis; Feature reduction
We propose a manifold learning framework to classify SSVEP data by reducing the number of features and comparing lower dimensional matrices with well-known machine learning algorithms. Among five manifold learning methods and nine machine learning algorithms, Principal Component Analysis shows the best classifier performance and achieves the highest accuracy when combined with the Naive Bayes classifier for a 7-class classification problem.
Steady-state visually evoked potentials (SSVEP) are stochastic and nonstationary bioelectric signals. Because of these properties, it is difficult to achieve high classification accuracy, especially when many considered features lead to a complex structure. We therefore propose a manifold learning framework to decrease the number of features and to classify SSVEP data by comparing lower dimensional matrices with well-known machine learning algorithms. We use the AVI-SSVEP Dataset, which includes stimuli at seven different frequencies and 15360 samples per person. The SSVEP features are extracted from relevant and distinctive frequency -domain, time-domain, and time-frequency domain properties, creating a total of 55 feature vectors. We then analyze and compare five divergent manifold learning methods with respect to their performance on nine different machine-learning algorithms. Among all considered manifold learning methods, we show that the Principal Component Analysis has the best classifier performance with an average of 22 components. Moreover, the Naive Bayes classifier with the Principal Component Analysis achieves the maximum accuracy of 50.0%-80.95% for a 7-class classification problem. Our research thus shows that the proposed analytical framework can significantly improve the decoding accuracy of 7-class SSVEP problems, and that it exhibits notable robustness and efficiency for small group datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据