Research on Feature Extraction and Classification of P300 EEG Signals
- 10.2991/eame-17.2017.7How to use a DOI?
- P300 EEG signal; feature extraction; independent component analysis; support vector machines
For the feature of P300's low signal-to-noise ratio (SNR) and difficult classificion, in this paper, we use an EEG signal processing method based on independent component analysis(ICA) and support vector machine. First, make the P300 EEG singal to the superposition averaging, according to the requirements of the ICA algorithm, the superimposed average signal is de-averaged and whitened. Then, the fast fixed-point algorithm which called FastICA is used to extract the feature vector of P300 EEG signal, in the end, put the feature vector into the support vector machine for classification. Using the DataSet II datasets in the International BCI Contest III to verify, the highest classification accuracy of the algorithm is 90.12%. The principle of this algorithm is simple, can successfully extract the feature of P300 EEG signal, and provide reference method for P300 EEG feature extraction and classification.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Ye Ma AU - Guangping Jiang AU - Tanqing Chang AU - Libin Guo PY - 2017/04 DA - 2017/04 TI - Research on Feature Extraction and Classification of P300 EEG Signals BT - Proceedings of the 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017) PB - Atlantis Press SP - 26 EP - 30 SN - 2352-5401 UR - https://doi.org/10.2991/eame-17.2017.7 DO - 10.2991/eame-17.2017.7 ID - Ma2017/04 ER -