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

TL;DR

This study compares classification algorithms for subject-specific and subject-independent brain-computer interfaces, highlighting performance variability and offering insights into optimal algorithm choices based on sample size and user needs.

Contribution

It provides a comprehensive comparison of classification algorithms for SS and SI BCI paradigms, emphasizing performance variability and practical considerations.

Findings

SS algorithms show high performance variance across subjects.

SI models have lower performance variance but need larger sample sizes.

LDA and CART perform best for small to moderate samples; SVM may excel with large data.

Abstract

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. 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, whereas we hypothesize that SVM would be superior to the other classifiers if large training sample-size was available. Additionally, one should choose the design approach considering the users. While the SS design sound more promising for a specific subject, an SI approach can be more convenient for mentally or physically challenged users.