Evolving Training Sets for Improved Transfer Learning in Brain Computer Interfaces
- 2.5k Downloads
A new proof-of-concept method for optimising the performance of Brain Computer Interfaces (BCI) while minimising the quantity of required training data is introduced. This is achieved by using an evolutionary approach to rearrange the distribution of training instances, prior to the construction of an Ensemble Learning Generic Information (ELGI) model. The training data from a population was optimised to emphasise generality of the models derived from it, prior to a re-combination with participant-specific data via the ELGI approach, and training of classifiers. Evidence is given to support the adoption of this approach in the more difficult BCI conditions: smaller training sets, and those suffering from temporal drift. This paper serves as a case study to lay the groundwork for further exploration of this approach.
KeywordsOptimisation Machine learning Ensemble Brain-computer interface P300 Evolutionary computation Transfer learning
This research was funded by the ESPRC through the DAASE project [grant number EP/J017515/1]. The authors are grateful for the assistance of Kate Howie in preparating the statistical analyses.
Data Access Statement. The dataset and source code used in this paper are available on request from the lead author.
- 1.Waytowich, N.R., Lawhern, V.J., Bohannon, A.W., Ball, K.R., Lance, B.J.: Spectral transfer learning using information geometry for a user-independent brain-computer interface. Front. Neurosci. 10 (2016)Google Scholar
- 4.Khatwani, P., Tiwari, A.: A survey on different noise removal techniques of EEG signal. Int. J. Adv. Res. Comput. Commun. Eng. 2(2), 1091–1095 (2013)Google Scholar
- 8.Cantillo-Negrete, J., Gutierrez-Martinez, J., Carino-Escobar, R., Carrillo-Mora, P., Elias-Vinas, D.: An approach to improve the performance of subject-independent BCIs-based motor imagery allocating subjects by gender. Biomed. Eng. 13(1), 158 (2014)Google Scholar
- 12.Xu, M., Liu, J., Chen, L., Qi, H., He, F., Zhou, P., Cheng, X., Wan, B., Ming, D.: Inter-subject information contributes to the ERP classification in the P300 speller. In: International IEEE/EMBS Conference on Neural Engineering 2015 July, pp. 206–209 (2015)Google Scholar