An Algorithm Combining Spatial Filtering and Temporal Down-Sampling with Applications to ERP Feature Extraction
Event-related potentials (ERP) based brain-computer interfaces (BCI) is a promising technology for decoding mental states. Due to the high trail-to-trial variability and low signal-to-noise ratio caused by volume conduction, analyzing brain states corresponding to ERP on a single trial is a challenging task. In this paper, we propose a computationally efficient method for ERP feature extraction, termed spatial filtering and temporal down-sampling (SFTDS). The spatial filters and the temporal down-sampling weight vectors can be optimized under a single objective function by SFTDS. Experiments on real P300 data from 10 subjects show the superiority of SFTDS over other algorithms.
KeywordsERP Spatial filter Weighted down-sampling Regularization
This work was supported by 973 Program of China (No. 2015CB351703), the National Natural Science Foundation of China (No. 61403144, No. 61633010), the tip-top Scientific and Technical Innovative Youth Talents of Guangdong special support program (No. 2015TQ01X361).
- 6.Luck, S.J.: An Introduction to the Event-Related Potential Technique. The MIT Press, Massachusetts (2005)Google Scholar
- 8.Makeig, S., Bell, A.J., Jung, T.P., Sejnowski, T.J.: Independent component analysis of electroencephalographic data. Adv. Neural Inf. Process. Syst. 8, 145–151 (1996)Google Scholar
- 13.Wu, W., Gao, S.: Learning event-related potentials (ERPs) from multichannel EEG recordings: a spatio-temporal modeling framework with a fast estimation algorithm. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6959–6962. IEEE Press, Boston (2011)Google Scholar