Back to Search
Start Over
A TrAdaBoost Method for Detecting Multiple Subjects' N200 and P300 Potentials Based on Cross-Validation and an Adaptive Threshold.
- Source :
-
International Journal of Neural Systems . Mar2020, Vol. 30 Issue 3, pN.PAG-N.PAG. 18p. - Publication Year :
- 2020
-
Abstract
- Traditional training methods need to collect a large amount of data for every subject to train a subject-specific classifier, which causes subjects fatigue and training burden. This study proposes a novel training method, TrAdaBoost based on cross-validation and an adaptive threshold (CV-T-TAB), to reduce the amount of data required for training by selecting and combining multiple subjects' classifiers that perform well on a new subject to train a classifier. This method adopts cross-validation to extend the amount of the new subject's training data and sets an adaptive threshold to select the optimal combination of the classifiers. Twenty-five subjects participated in the N200- and P300-based brain–computer interface. The study compares CV-T-TAB to five traditional training methods by testing them on the training of a support vector machine. The accuracy, information transfer rate, area under the curve, recall and precision are used to evaluate the performances under nine conditions with different amounts of data. CV-T-TAB outperforms the other methods and retains a high accuracy even when the amount of data is reduced to one-third of the original amount. The results imply that CV-T-TAB is effective in improving the performance of a subject-specific classifier with a small amount of data by adopting multiple subjects' classifiers, which reduces the training cost. [ABSTRACT FROM AUTHOR]
- Subjects :
- *BRAIN-computer interfaces
*SUPPORT vector machines
*KNOWLEDGE transfer
Subjects
Details
- Language :
- English
- ISSN :
- 01290657
- Volume :
- 30
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- International Journal of Neural Systems
- Publication Type :
- Academic Journal
- Accession number :
- 142000985
- Full Text :
- https://doi.org/10.1142/S0129065720500094