Ensemble Learning based EEG Classification – Investigating the Effects of Combined Yoga and Rajyog Meditation
Journal of Scientific & Industrial Research January 1, 2025 Shobhika Madhu, Prashant Kumar, Sushil Chandra 4 citations
An ensemble machine-learning model that combines bidirectional long-short-term memory (BiLSTM) with a decision tree (DT) classified EEG data from 69 students before and after a yoga and Rajyoga meditation session with 82% accuracy, outperforming CNN-based models. Post-meditation EEG showed higher band powers and wavelet coefficients than the control condition. The BiLSTM-DT ensemble model is proposed as an objective marker for distinguishing meditation from non-meditation states, with potential use in monitoring psychological health in young people.