Deep Learning for Cognitive Task and Seizure Classification with Hilbert–Huang Transform and Variational Mode Decomposition

Abstract

Electroencephalography (EEG) signals are often utilized to study cognitive processes and brain diseases. The non-stationary and non-linear nature of EEG signals makes their analysis difficult. A deep learning framework that suggested classifying seizures based on scalp EEG signals and automating cognitive tasks. We use a pre-processing module based on the Hilbert–Huang Transform (HHT) and Variational Mode Decomposition (VMD) to extract features from raw EEG data. We present an approach that combines deep learning with HHT and VMD for rapid and precise seizure detection. Our method detects seizures with an astounding 98.40% accuracy. Our suggested techniques have great potential for quantifying brain wave patterns and advancing neuroscience research, even outside of classification applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.