A Systematic Review of EEG Signal Processing and AI Driven Techniques in Brain–Computer Interface
Samata V. Athawale, Ratnashil N. Khobragade
Multidisciplinary Journal of Research in Engineering and Technology June 16, 2026 DOI: 10.65521/mjret.v13i2s.3565 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Review Peer reviewed |
|---|---|
| Key findings | Argues that machine learning techniques have improved the accuracy of classifying and interpreting meditative EEG signals, and reviews the frameworks for EEG acquisition, preprocessing, feature extraction, and classification used in BCI systems for meditation analysis. The authors also outline current challenges and future research needs for reliable meditation-focused BCI systems. |
Abstract
In the field of neuroscience, Meditation has gained significant focus because of its positive effects on cognitive performance and mental health. With the help of Brain Computer Interface (BCI), communication between the brain and other devices can be made possible through the analysis of brain signals. As Electroencephalography (EEG) is non-invasive in nature and has high temporal resolution, it is widely used in BCI applications. Meditative EEG signals have attracted attention because meditation alters brain activity patterns, which can be analyzed for cognitive and mental health applications in recent years. The accuracy of EEG signal classification and interpretation has significantly improved with advanced machine learning techniques. This paper reviews and explores the frameworks used for analyzing meditative EEG signals using machine learning algorithms. It discusses EEG signal acquisition, signal pre-processing methods, feature extraction techniques, and classification approaches. Moreover, the paper points out present challenges and potential areas for future research in creating reliable BCI systems for analyzing meditation.