L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark

2026-05-21

AI Summary

This study addresses the lack of longitudinal, multi-style meditation EEG datasets and standardized evaluation benchmarks for investigating the neural mechanisms of meditation. To this end, we present a dataset comprising EEG recordings and psychological assessments from 74 university students collected before and after a six-week intervention involving three distinct meditation practices. We propose three benchmark tasks: cognitive state decoding, fine-grained meditation type classification, and cross-session transfer learning. Our work provides the first publicly available, longitudinally tracked, multi-style meditation EEG resource, accompanied by a standardized preprocessing pipeline and an open-source evaluation framework. Comprehensive baseline results are established using both classical machine learning and deep learning approaches. The full dataset, code, and benchmark suite are released to advance research in computational meditation and EEG-based machine learning.

Abstract

We introduce a novel Longitudinal Focused Attention Meditation Electroencephalography (L-FAME) dataset and an accompanying benchmark, designed to foster research into the neural effects of various meditation practices and the evolution of these effects over a six-week training period. The dataset contains EEG recordings and psychological assessments from 74 healthy college participants, collected at two distinct time points: pre-intervention and post-intervention. Participants were randomly assigned to one of three distinct meditation groups: two mantra-based techniques (SA-TA-NA-MA and Hare Krishna) and one Breath Focus practice. Leveraging this unique longitudinal and comparative dataset, we propose a benchmark suite comprising three distinct classification tasks: (1) cognitive state decoding to distinguish between resting and meditation states, (2) fine-grained classification of the specific meditation techniques, and (3) cross-session adaptation to evaluate model generalization across the longitudinal time gap. We provide comprehensive baseline results for these tasks utilizing a range of classical machine learning algorithms and deep learning architectures. The complete dataset, preprocessing pipelines, and benchmark evaluation code will be publicly released, offering a valuable resource and a standardized framework for the development and comparison of new analytical methods in computational meditation research and EEG-based machine learning. The dataset is available at https://huggingface.co/datasets/L-FAME-Dataset-Benchmark/L-FAME

Problem

• meditation
• EEG
• longitudinal study
• cognitive state decoding
• benchmark

Innovation

• longitudinal EEG dataset
• meditation classification
• cross-session adaptation
• cognitive state decoding
• benchmark framework