Machine Learning Models for Brain Signal Classification: A Focus on EEG Analysis in Epilepsy Cases

Electroencephalography (EEG) provides critical insights into brain function and neurological disorders. However, analyzing and classifying EEG signals remains challenging. Manual review is time-consuming, prone to bias, and lacks scalability. Hence, developing automated EEG classification has become vital for clinical assessment and treatment of epilepsy. This study presents a machine learning framework for classifying normal and epileptic EEG recordings. The approach involves feature extraction using discrete wavelet transform (DWT) and statistical methods, feature selection to identify the most discriminative attributes, followed by classification across multiple algorithms. Specifically, DWT decomposes non-stationary signals for time-frequency representation. Principal component analysis and cosine similarity assist in selecting robust features. Supervised classifiers including naive Bayes, decision trees, neural networks, k-nearest neighbors, random forest, and support vector machines categorize the signals. Results demonstrate 100% accuracy with neural networks, indicating highly reliable automated classification is achievable. By comparing multiple techniques, the optimal machine learning pipeline emerges. This epilepsy EEG classification framework demonstrates the potential for AI to significantly improve screening, diagnosis, treatment, and management of neurological disorders. Ongoing research aims to further enhance efficiency, scalability, and real-time capabilities.

Перевод пока недоступен