Montazeri Nasim, Shamsollahi Mohammad Bagher, Hajipour Sepideh
School of Electrical Engineering, Sharif University of Technology, Tehran, Iran.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:986-9. doi: 10.1109/IEMBS.2009.5334472.
Neural activity is very important source for data mining and can be used as a control signal for brain-computer interfaces (BCIs). Particularly, Magnetic signals of neurons are enriched with information about the movement of different part of the body such as wrist movement. In this paper, we use MEG (Magneto encephalography) signals of two subjects recorded during wrist movement task in four directions. Data were prepared for BCI competition 2008 for multiclass classification. Our approach for this classification problem consists of PCA as a noise reduction method, ULDA for feature reduction and various linear classifiers such as Bayesian, KNN and SVM. Final results (58%-62% for subject 1 and 36%-40% for subject 2) prove that the suggested method shows better performance compared with other methods.
神经活动是数据挖掘的非常重要的来源，并且可以用作脑机接口（BCI）的控制信号。特别是，神经元的磁信号富含有关身体不同部位运动的信息，例如手腕运动。在本文中，我们使用了在四个方向的手腕运动任务期间记录的两名受试者的脑磁图（MEG）信号。数据是为2008年BCI竞赛的多类分类准备的。我们针对此分类问题的方法包括作为降噪方法的主成分分析（PCA）、用于特征约简的统一局部判别分析（ULDA）以及各种线性分类器，如贝叶斯分类器、K近邻（KNN）和支持向量机（SVM）。最终结果（受试者1为58%-62%，受试者2为36%-40%）证明，与其他方法相比，所提出的方法表现出更好的性能。
