Indonesian Journal of Electrical Engineering and Computer Science Vol. 32, No. 2, November 2023, pp. 1123~1133 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v32.i2.pp1123-1133  1123 Journal homepage: http://ijeecs.iaescore.com Prediction of the epileptic seizure through deep learning techniques using electroencephalography Mounika Sunkara, Reeja Sundaran Rajakumari School of Computer Science and Engineering, VIT-AP University, Amaravati, India Article Info ABSTRACT Article history: Received Jul 4, 2023 Revised Aug 3, 2023 Accepted Aug 17, 2023 Electroencephalography (EEG) is a widely used and significant technique for aiding in epilepsy diagnosis and investigating the electrical patterns of the human brain. Due to the non-stationary nature of EEG signals, seizure patterns will vary across different recording sessions for individual patients. In this study, a new deep learning long short-term memory (LSTM) model is implemented for the detection of brain tumors and seizures. The process consists of four key steps: EEG signal pre-processing, preictal feature extraction, hyper optimization using grey wolf optimization (GWO), and LSTM-based classification. The evaluation makes use of long-term EEG recordings from the EEG and ABIDE fMRI datasets. By experimenting with various modules and layers of memory units, a pre-analysis is first conducted to determine the best LSTM network architecture. The LSTM model makes use of numerous retrieved features, including temporal and frequency domain information between EEG channels that were extracted before classification. The discovery of the implemented methodology revealed significant advantages in accurately predicting seizures while minimizing false alarms. The implemented LSTM method achieves a 99% accuracy rate, 98% precision, 99% recall, and 98% f1-measure which is better when compared with cross sub-pattern correlation-based principal component analysis (SUBXPCA) and gradient-boosting decision tree (GBDT) methods. Keywords: Deep learning Epilepsy Electroencephalogram LSTM model Seizure prediction This is an open access article under the CC BY-SA license. Corresponding Author: Mounika Sunkara School of Computer Science and Engineering, VIT-AP University Amaravati, Andhra Pradesh, India Email: mounikasunkara9179@gmail.com 1. INTRODUCTION Epilepsy is a chronic brain disease caused by the sudden abnormal discharge of neurons in the brain resulting in temporary impairment of brain function [1], [2]. One of the most prevalent neurological non- communicable illnesses is epilepsy. An abnormality in the brain’s electrical activity, which can be classed as focal, generalized, or undetermined, is what causes epileptic seizures [3], [4]. Electroencephalography (EEG) signals are electrical impulses generated by biological brain activity in humans. Disabled or elderly people can utilize a particular wearable EEG device to collect EEG data and generate control signals for motor imaging, allowing for remote control [5]. With the aid of an EEG device, electrodes can be placed on the scalp in a non- invasive way to detect brain activity [6]. To analyze variations in brain activity and to distinguish between normal and abnormal processes occurring in the human brain, EEG is frequently utilized. EEG is also quite inexpensive, which makes it the best test for epilepsy sufferers [7]. When used on EEG recordings, common spatial pattern filters, and optimized spatial pattern filters also offer a higher signal-to-noise ratio [8]. Accurate prediction is made possible by spatial attention, which also realizes adaptive learning of feature characteristics [9]. The convolutional neural network (CNN) deep learning model’s main input type is a single domain input,