An enhanced classification scheme with AdaBoost concept in BCI

Issue title: Special Section: Recent Advances in Machine Learning and Soft Computing

Guest editors: Srikanta Patnaik

Article type: Research Article

Authors: Kim, June-Hyoung^a | Yang, Yeon-Mo^{b; *}

Correspondence: [*] Corresponding author. Yeon-Mo Yang, School of Electronic Eng., Kumoh National Inst. of Tech.1 Yanghodong, Gumi, Gyeongbuk 39177, Korea. E-mail: yangym@ vivaldi.kumoh.ac.kr.

Abstract: EEG (Electroencephalography)-based motor imagery signal classification is very important in brain-computer interface (BCI) technology. In this paper, we improve a classification method by utilizing AdaBoost, an extension of artificial intelligence (AI), instead of linear discriminant analysis (LDA). In order to confirm the classification improvement, the classification accuracy of LDA and AdaBoost has been analyzed. The data set used in the simulation was Data set III of BCI Competition II, and the Matlab tool has been used for the simulation. The results of the proposed scheme with Adaboost show a dramatic improvement in classification compared to that than LDA.

Keywords: Soft Computing, brain computer interface (BCI), motor imagery, neuro signal classification, linear discriminant analysis (LDA), AdaBoost, artificial intelligence (AI)

DOI: 10.3233/JIFS-169567

Journal: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 1, pp. 63-68, 2018