Mantra chanting, a meditative practice, influences brainwave activity. In 11 experienced practitioners (aged 37 ± 6 years, with 3 to 8 years of experience), EEG data collected during three minutes of “OM” mantra chanting showed significant increases in Alpha (10%), Gamma (13%), Beta (23%), and Delta (16%) power compared to before chanting. These changes suggest a deeper state of relaxation and focus during the practice, indicating that mantra chanting impacts cognitive processes and brainwave activity in experienced individuals.
A deep hybrid model combining convolutional neural networks, bidirectional long short-term memory networks, and attention mechanisms achieved 99.46% accuracy in classifying EEG recordings from experienced meditation practitioners into resting or mantra-listening brain states. Wavelet-based time-frequency features were extracted from EEG data recorded before and during auditory mantra stimulation. The model outperformed simpler architectures including CNN alone (76.92%), LSTM alone (75.30%), CNN+LSTM (84.62%), and CNN+BiLSTM (88.65%). Receiver operating characteristic analysis confirmed high discriminative capability with an AUC near 1.0. The approach demonstrates that combining convolutional, recurrent, and attention methods substantially improves spatial-temporal feature learning for distinguishing brain states.