EEG Dataset Reduction and Classification Using Wave Atom Transform
Brain Computer Interface (BCI) systems perform intensive processing of the electroencephalogram (EEG) data in order to form control signals for external electronic devices or virtual objects. The main task of a BCI system is to correctly detect and classify mental states in the EEG data. The efficiency (accuracy and speed) of a BCI system depends upon the feature dimensionality of the EEG signal and the number of mental states required for control. Feature reduction can help improve system learning speed and, in some cases, classification accuracy. Here we consider Wave Atom Transform (WAT) of the EEG data as a feature reduction method. WAT takes input data and concentrates its energy in a few transform coefficients. WAT is used as a data preprocessing step for feature extraction. We use artificial neural networks (ANNs) for classification and perform research with varying number of neurons in a hidden layer and different network training functions (Levenberg-Marquardt, Conjugate Gradient Backpropagation, Bayesian Regularization). The novelty of the paper is the application of WAT in the EEG data processing. We conclude that the method can be successfully used for feature extraction and dataset feature reduction in the BCI domain.
KeywordsEEG Brain Computer Interface Wave Atom Transform dimensionality reduction classification
Unable to display preview. Download preview PDF.
- 2.Martisius, I., Sidlauskas, K., Damasevicius, R.: Real-Time Training of Voted Perceptron for Classification of EEG Data. International Journal of Artificial Intelligence 10(S13), 41–50 (2013)Google Scholar
- 3.Birvinskas, D., Jusas, V., Martisius, I., Damasevicius, R.: EEG dataset reduction and feature extraction using discrete cosine transform. In: Proc. of UKSim-AMSS EMS 2012: 6th European Modelling Symposium on Mathematical Modeling and Computer Simulation, Malta, November 14-16, pp. 186–191 (2012)Google Scholar
- 8.Aggarwal, V., Patterh, M.S.: ECG Compression using Wavelet Packet, Cosine Packet and Wave Atom Transforms. Int. Journal of Electronic Engineering Research 1(3), 259–268 (2009)Google Scholar
- 9.Rajeesh, J.: Rician noise removal on MRI using wave atom transform with histogram based noise variance estimation. In: IEEE Int. Conf. on Communication Control and Computing Technologies (ICCCCT), October 7-9, pp. 531–535 (2010)Google Scholar
- 10.Geetika, D., Varun, R.: MRI Denoising Using Waveatom Shrinkage. Global Journal of Researches in Engineering 12(4) (2012)Google Scholar
- 12.Birbaumer, N., Flor, H., Ghanayim, N., Hinterberger, T., Iverson, I., Taub, E., Kotchoubey, B., Kbler, A., Perelmouter, J.: A Brain-Controlled Spelling Device for the Completely Paralyzed. Nature 398, 297–298Google Scholar