https://doi.org/10.1140/epjs/s11734-025-01606-y
Review
EEG signal processing in neurological conditions using machine learning and deep learning methods: a comprehensive review
School of Computer Science and Engineering, VIT-AP University, Amaravati, Andhra Pradesh, India
Received:
9
January
2025
Accepted:
29
March
2025
Published online:
23
April
2025
This comprehensive study explores a wide range of applications of Machine Learning (ML) and Deep Learning (DL) methods in Electroencephalogram (EEG) signal processing for neurological disorders such as epilepsy and schizophrenia. The methodologies include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM) networks for managing time-series data, as well as advanced models like Deep Belief Retworks (DBNs) and Restricted Boltzmann Machines (RBMs). Hybrid models that integrate CNNs with Discrete wavelet Transforms (DWT) and dense networks (DenseNet) has shown improved classification accuracy. Techniques such as transfer learning, Vision Transformers (ViT), and Data Uncertainty Learning (DUL) are employed to enhance prediction robustness. Particularly, noteworthy is the introduction of MIN2Net, an innovative algorithm that incorporates deep metric learning within a multi-task autoencoder, leading to significant improvements in the classification of EEG signals using motor imagery. Moreover, the study delves into the integration of prior medical knowledge, cloud computing, and big data analytics to ensure scalability and real-time application. These advancements present promising opportunities for automated and accurate diagnosis, continuous real-time monitoring, and management of neurological disorders, demonstrating substantial potential in healthcare informatics and clinical applications.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
