AI/DL/ML for electroencephalogram (EEG) signals
Abstract:
Electroencephalography (EEG) is a well-known modality in the neuroscience and widely used in identifying and classifying neurological disorders. This project investigates on how EEG data can be used for various applications:
Knowledge distillation-based deep learning models in order to detect mental disorders like epilepsy and sleep disorders [1]
Interpretable machine learning models for emotion recognition [2]
Reviewing the use machine learning and deep learning in Parkinson disease detection [3]
Knowledge distilled transfer learning (KDTL) framework [1] for analysing the EEG-based spectrogramsÂ
References:
[1] S. Singh, H. Jadli, R. P. Priya, V. B. S. Prasath. KDTL: Knowledge distilled transfer learning framework for diagnosing mental disorders using EEG spectrograms. Neural Computing and Applications, 2024. doi:TBA
[2] P. Y. Preema, J. Chandra, V. A. Immanuel, B. Iyer, V. B. S. Prasath. Interpretable machine learning models for EEG signals for identification of emotional intelligence. Submitted, 2024.
[3] A. Shukla, G. Chettiar, B. Iyer, V. Vijayarajan, V. B. S. Prasath. Computational techniques for EEG-based Parkinson disease detection and classification - A review. Submitted, 2024.
