Abstract
Brain Computer Interface technology enables a pathway for analyzing EEG signals for seizure detection. EEG signal decomposition, features extraction and machine learning techniques are more familiar in seizure detection. However, selecting decomposition technique and concatenation of their features for seizure detection is still in the state-of-the-art phase. This work proposes DWT-EMD Feature level Fusion-based seizure detection approach over multi and single channel EEG signals and studied the usability of discrete wavelet transform (DWT) and empirical mode decomposition (EMD) feature fusion with respect to individual DWT and EMD features over classifiers SVM, SVM with RBF kernel, decision tree and bagging classifier for seizure detection. All classifiers achieved an improved performance over DWT-EMD feature level fusion for two benchmark seizure detection EEG datasets. Detailed quantification results have been mentioned in the Results section.
Highlights
Electroencephalogram (EEG) signals decomposition and features extraction from the decomposed segments are popular approaches in seizure detection
We studied and found that various decomposition approaches from the Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) family are used in seizure detection over EEG signals
A discrete cosine transform (DCT) based approach [2] has been suggested in the context of EEG signals compression, and this provides us with a basic understanding of discrete transform even if it is applied over motor imagery EEG data
Summary
Electroencephalogram (EEG) signals decomposition and features extraction from the decomposed segments are popular approaches in seizure detection. The authors of [3] claimed that their approach achieved a minimum accuracy of 98.50% and maximum accuracy of 100% over the University of Bonn single channel EEG dataset, but they have not tested their approach over a multichannel EEG dataset Another wavelet-based approach is named flexible analytic wavelet transform (FAWT) [4], which has been used for EEG signals decomposition to propose seizure detection approaches, where entropy-based features have extracted and been fed into SVM with an RBF kernel. The authors of [8] have considered the University of Bonn and CHB-MIT EEG datasets (i.e., single and multi channel EEG dataset) to test their approach and claimed that their approach with SVM achieved an accuracy of 89.03% over CHB-MIT and 97.67% over Bonn
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
