Epileptic seizure detection in EEG signals using deep learning: LSTM and bidirectional LSTM

This paper established a new automatic method to detect epileptic seizures in EEG signals based on discret wavelet transform (DWT) and Deep Learning (DL). DWT is used to decompose EEG into different sub-bands. Moreover, the proposed model combines Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM) networks with one layer of each network consecutive. The experimental results yield higher accuracies of 100% which it is demonstrated that the obtained results achieve better performance by using the new hybrid LSTM-BiLSTM network than other works. Finally, this hybrid LSTM-BiLSTM model confirmed their effectiveness for the classification of epileptic EEG signals.