Eeg-based Epileptic Seizure Detection Using Binary Dragonfly Algorithm And Deep Neural Network

EEG signals are an important source of information for medical practitioners to analyze the activity of the brain while diagnosing neurological disorders. Different frequency components from EEG signals are useful for medical analysis and are associated with different physical and mental activities. Time-frequency methods such as discrete wavelet transform, wavelet packet decomposition, dual-tree complex wavelet transform, and empirical mode decomposition are used to extract features from EEG signals. A wavelet-based method is proposed to capture the rhythmic nature of seizure discharges and a normalized wavelet-based index, named the Combined Seizure Index (CSI) is used for epileptic seizure detection.