Brain state classification of Electroencephalogram (EEG) data acquired by Brain Computer Interface (BCI) is a new dimension in an immersive human-computer interaction. However, labeled EEG data is limited due to long time of data acquisition and expensive data post-processing. For this reason, a preliminary study on brain state classification with limited EEG labeled data is proposed. A small amount of labeled data and a large amount of unlabeled data are learned together via a graph-based semi-supervised learning approach for classifying brain states. Our method produces promising results on EEG signal classification and shows the effective use of unlabeled brain state data.
Semi-Supervised Learning, Graph, Electroencephalogram (EEG), Brain State Classification, Data Augmentation
1. Singer, E., “Brain games,” Technology Review, 2008, 111(4), pp. 82–84.
2. Zaremba W., Kumar, M. P., Gramfort, A., and Blaschko, M. B., “Learning from m/eeg data with variable brain activation delays,” in Information Processing in Medical Imaging, Springer, 2013, pp. 414–425.
3. Holzel, B. K., Ott, U., Hempel, H., Hackl, A., Wolf, K., Stark, R., and Vaitl, D., “Differential engagement of anterior cingulate and adjacent medial frontal cortex in adept meditators and nonmeditators,” Neuroscience Letters, 2007, 421(1), pp. 16–21.
4. Fox M. D., and Raichle, M. E., “Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging,” Nature Reviews Neuroscience, 2007, 8(9), pp. 700–711.
5. “Electroencephalography (EEG) and event-related potentials (ERP’s) with human participants”, Current Protocols in Neuroscience, 2010, 6(6), pp.1-24.
6. Szummer, M.O., “Learning from partially labeled data,” Thesis, Massachusetts Institute of Technology, 2002.
7. Cheng, J., Tegge, A.N., Baldi, P., “Machine learning methods for protein structure prediction,” IEEE Reviews in Biomedical Engineering, 2008, 1, pp. 41 – 49.
8. Zien A., Schölkopf B., and Chapelle O.: “Semi-supervised learning,” The MIT Press, 2006.
9. Liu, W., Wang J., and Chang, S.F., “Robust and scalable graph-based semisupervised learning,” Proceedings of the IEEE, 2012, 100(9), pp. 2624 – 2638.
10. Zhou D., Bousquet, O., Thomas N. L., Weston J., Schölkopf, B., “Learning with local and global consistency”, Advances in Neural Information Processing Systems (NIPS), 2003.
11. P300, URL: https://en.wikipedia.org/wiki/P300_(neuroscience)
12. Wang J., Jebara T., and Chang S.F., “Semi-supervised learning using greedy max-cut”, Journal of Machine Learning Research, 2013, 14, pp. 771-800.
13. Zhu, X., Ghahramani Z., and Lafferty J., “Semi-supervised learning using gaussian fields and harmonic functions”, In Proceedings of International Conference on Machine Learning, 2003, pp. 912–919.
14. Zhou , Bousquet O., Lal T. N., Weston J., and Scholkopf B., “Learning with local and global consistency”, Advances in Neural Information Processing Systems, 2004, 16, pp. 321–328
Computer Science and Engineering Technology Department, University of Houston – Downtown, Houston, Texas, United States 77002