An automated deep learning enabled brain signal classification for epileptic seizure detection on complex measurement systems

Recent advancements in machine learning and deep models find them helpful designing effective complex measurement systems. At the same time, examining brain’s activities using Electroencephalography (EEG) is essential to determine mental state or thought of a person. It several application areas, such as Brain-Computer Interface (BCI), emotion recognition, disease diagnosis. The proper brain signal classification EEG finds diagnose epileptic seizures. Since traditional seizure detection process lengthy challenging task, automated identification epilepsy significant problem. In order resolve issues that exist models, this study designs Automated Deep Learning-Enabled Brain Signal Classification for Epileptic Seizure Detection (ADLBSC-ESD). proposed ADLBSC-ESD technique aims classify signals existence seizures not. addition, presented model involves design Improved Teaching Optimization (ITLBO) selecting features from signals. Moreover, Belief Network (DBN) used an effectual signals, hyperparameters DBN are optimally tuned Swallow Swarm Algorithm (SSA). ensure improved performance technique, series simulations take place, outcomes investigated concerning different measures. experimental values highlighted better over current art techniques with maximum accuracy 0.8316 0.8609 under binary multiple classes, respectively.