Selective Subject Pooling Strategy to Improve Model Generalization for a Motor Imagery BCI
Open Access
Abstract
Brain–computer interfaces (BCIs) facilitate communication for people who cannot move their own body. A BCI system requires a lengthy calibration phase to produce a reasonable classifier. To reduce the duration of the calibration phase, it is natural to attempt to create a subject-independent classifier with all subject datasets that are available; however, electroencephalogram (EEG) data have notable inter-subject variability. Thus, it is very challenging to achieve subject-independent BCI performance comparable to subject-specific BCI performance. In this study, we investigate the potential for achieving better subject-independent motor imagery BCI performance by conducting comparative performance tests with several selective subject pooling strategies (i.e., choosing subjects who yield reasonable performance selectively and using them for training) rather than using all subjects available. We observed that the selective subject pooling strategy worked reasonably well with public MI BCI datasets. Finally, based upon the findings, criteria to select subjects for subject-independent BCIs are proposed here.Keywords
Funding Information
- Institute of Information & Communications Technology (IITP) (2017-0-00451, 2019-0-01842, 2021-0-01537)
This publication has 36 references indexed in Scilit:
- High Theta and Low Alpha Powers May Be Indicative of BCI-Illiteracy in Motor ImageryPLOS ONE, 2013
- Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2bFrontiers in Neuroscience, 2012
- The role of orienting in vibrissal touch sensingFrontiers in Behavioral Neuroscience, 2012
- Single-trial analysis and classification of ERP components — A tutorialNeuroImage, 2011
- Applying a brain-computer interface to support motor imagery practice in people with stroke for upper limb recovery: a feasibility studyJournal of NeuroEngineering and Rehabilitation, 2010
- Neurophysiological predictor of SMR-based BCI performanceNeuroImage, 2010
- Subject-independent mental state classification in single trialsNeural Networks, 2009
- Towards Zero Training for Brain-Computer InterfacingPLOS ONE, 2008
- Brain–computer interfaces for communication and controlClinical Neurophysiology, 2002
- Involvement of Primary Motor Cortex in Motor Imagery: A Neuromagnetic StudyNeuroImage, 1997