Performance Analysis of Machine Learning Models for EEG Pathology Detection in MRI Dataset
- Version
- Download 20
- File Size 318.65 KB
- File Count 1
- Create Date 21 February 2026
- Last Updated 21 February 2026
Performance Analysis of Machine Learning Models for EEG Pathology Detection in MRI Dataset
Vandna
Research Scholar
Baba Mastnath University
Rohtak, Haryana, India
Dr. Banita
Professor
Baba Mastnath University
Rohtak, Haryana, India
Abstract- Electroencephalography (EEG) is a common non-invasive way to keep an eye on brain activity. This study aimed to analyze EEG pathology within MRI datasets using machine learning techniques to enhance diagnostic accuracy and efficiency in neuroimaging. By integrating EEG-derived pathological features with MRI data, the research sought to uncover correlations betweenbrain activity patterns and structural abnormalities. A survey-based methodology was employed, supported by computational models that classified and predicted pathological conditions.The approach combined feature extraction, dimensionality reduction, and supervised learning algorithms to improve detection rates. The findings demonstrated that machine learning could effectively bridge the gap between functional and structural brain analysis, offering a more comprehensive understanding of neurological disorders.
Keywords: Electroencephalography (EEG), Machine Learning, MRI Dataset, Feature Extraction etc.
Download