Epileptic Seizure Mining via Novel Empirical Wavelet Feature with J48 and KNN Classifier
In this paper, we are providing the application of options using empirical wavelet transform (EWT) and J48 decision tree model for electroencephalogram (EEG) signal classification. The features were extracted from EEG signal based on the empirical wavelet transform. Empirical wavelet transform (EWT) decomposes the EEG signal in the form of the intrinsic mode functions (IMFs) which is an AM–FM signal. The statistical values were extracted from the decomposed signals resulting in the EWT features. The extracted features were classified using classifiers J48 and KNN classifier. The proposed J48 model achieved higher accuracy rates than that of the KNN algorithm.
KeywordsEpilepsy Wavelet features KNN classifier J48 classifier
- 4.Cunningham, P., Delany, S.J.: K-Nearest neighbor classifiers. Technical Report. D UCD-CSI-2007-4, Artificial Intelligence Group, DublinGoogle Scholar
- 7.Andrzejak, R.G., Lehnertz, K., Mormann, F., et al.: Indications of nonlinear deterministic and finite dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys. Rev. E 64(6), 061907 (2001)Google Scholar
- 8.Lekshmi, S.S., Selvam, V., Pallikonda Rajasekaran, M.: EEG signal classification using principal component analysis and wavelet transform with neural network. In: Proceedings of International Conference on Communication and Signal Processing, India, 3–5 April 2014Google Scholar
- 10.Hazarika, N., Chen, J.Z., Tsoi, A.C., Sergejew, A.: Classification of EEG signals using the wavelet transform. In: Proceedings of 13th International Conference on Digital Signal Processing, India, vol. 59(1), pp. 89–92 (1997)Google Scholar