Comparison of Classification Algorithms Towards Subject-Specific and Subject-Independent BCI

Motor imagery brain computer interface designs are considered difficult due to limitations in subject-specific data collection and calibration, as well as demanding system adaptation requirements. Recently, subject-independent (SI) designs received attention because of their possible applicability to multiple users without prior calibration and rigorous system adaptation. SI designs are challenging and have shown low accuracy in the literature. Two major factors in system performance are the classification algorithm and the quality of available data. This paper presents a comparative study of classification performance for both SS and SI paradigms. The present classification algorithms include two parametric (LDA and SVM) and two non-parametric (k-NN and CART) methods. Our results show that classification algorithms for SS models display large variance in performance. Therefore, distinct classification algorithms per subject may be required. SI models display lower variance in performance but should only be used if a relatively large sample size is available. For SI models, LDA and CART had the highest accuracy for small and moderate sample size, respectively. The source code of this paper is available at github.com/parisaghane/eegbciMI.