A new dataset, L-FAME, provides EEG recordings and psychological assessments from 74 healthy college participants who were randomly assigned to one of three meditation practices (two mantra-based techniques and one breath focus) and measured before and after a six-week training period. The dataset supports three benchmark tasks: distinguishing resting from meditation states, classifying which specific technique was used, and testing whether machine learning models can generalize across the two time points. Baseline results using classical and deep learning methods are reported, and the dataset, preprocessing code, and evaluation framework are publicly released to advance computational meditation research and EEG-based machine learning.
Two types of mantra meditation produce distinct brain activity patterns. Novice practitioners were randomly assigned to chant either the Hare Krishna (HK) or Sa-Ta-Na-Ma (SA) mantra. EEG measurements showed that HK meditation led to widespread decreases in alpha power and increases in alpha frequency during and after practice, suggesting a more activating, attentionally focused state. In contrast, SA meditation produced localized alpha power reduction and, after training, a significant decrease in alpha frequency, indicating a more relaxed state. Both groups reported reduced stress. These results challenge the idea that all mantra meditation is the same and underscore the need to differentiate practices for targeted mental health applications.