Improved seizure detection using optimized time sequence based deep learning framework

Abstract

Epilepsy disease originates due to the presence of disordered neurons, and epilepsy detection stands as a challenging task for neurologists. With recent advances, electroencephalography (EEG)-based analysis is increasingly supported by deep learning and metaheuristic optimization approaches in order to improve the test results. This experiment uses a convolutional neural network (CNN) model hybridized with bidirectional long short-term memory (BiLSTM). CNN leverages the work with improved feature extraction cum classification supports, and BiLSTM keeps the time sequence of data in both the forward and backward direction for improving signal mapping purposes. To reduce the computational overhead and improve execution accuracy, a hybrid optimization algorithm called secretary bird optimization algorithm (SBOA) is used to fine-tune the execution. Key classification parameters such as accuracy, sensitivity, and specificity reflect the model’s strong predictive capability, with accuracy reaching up to 98.49%. The proposed method demonstrates the potential for high-performance EEG-based seizure detection, paving the way for future integration with edge computing devices to support remote clinical diagnostics and continuous monitoring in real-world healthcare applications.