Rag‐bull rider optimisation with deep recurrent neural network for epileptic seizure detection using electroencephalogram

Electroencephalogram (EEG) signal is mostly utilised to monitor epilepsy revitalize the close loop brain. Several classical methods devised identify seizures rely on visual analysis of EEG signals which a costly and complex task if channel count increases. A novel method, namely, rag-Rider optimisation algorithm (rag-ROA) for training deep recurrent neural network (Deep RNN) discover epileptic seizures. Here input are splitted different channels wherein each undergoes feature extraction. The features like Holoentropy, relative energy, fluctuation index, tonal power ratio, spectral along with proposed Taylor-based delta amplitude modulation spectrogram (Taylor-based AMS) mined from channel. AMS designed by integrating Taylor series. probabilistic principal component (PPCA) employed reduce dimension. dimensionally reduced vector classified Deep RNN using rag-ROA, rag-bull rider four other riders available in Rider (ROA). Thus, resulted output rag-ROA-based seizure detection. showed improved results maximal accuracy 88.8%, sensitivity 91.9%, specificity 89.9% than existing methods, such as Wavelet + SVM, HWPT RVM, MVM-FzEN, EWT RF, TUEP dataset.