Novel machine learning-driven comparative analysis of CSP, STFT, and CSP-STFT fusion for EEG data classification across multiple meditation and non-meditation sessions in BCI pipeline
Nalinda D. Liyanagedera, Corinne A. Bareham, Heather Kempton, Hans W. Guesgen
Brain Informatics February 8, 2025 DOI: 10.1186/s40708-025-00251-4 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Experimental study Peer reviewed |
|---|---|
| Sample size | 12 |
| Population | Participants providing EEG data during loving-kindness meditation and non-meditation |
| Topics | Meditation |
| Keywords | Pipeline software Electroencephalography Short-time fourier transform Artificial intelligence Speech recognition Machine learning Pattern recognition psychology |
| Citations | 4 |
| Key findings | A pipeline combining CSP and STFT feature extraction achieved 72.9% overall classification accuracy for distinguishing meditation from non-meditation EEG, outperforming either method alone. |
Abstract
This study focuses on classifying multiple sessions of loving kindness meditation (LKM) and non-meditation electroencephalography (EEG) data. This novel study focuses on using multiple sessions of EEG data from a single individual to train a machine learning pipeline, and then using a new session data from the same individual for the classification. Here, two meditation techniques, LKM-Self and LKM-Others were compared with non-meditation EEG data for 12 participants. Among many tested, three BCI pipelines we built produced promising results, successfully detecting features in meditation/ non-meditation EEG data. While testing different feature extraction algorithms, a common neural network structure was used as the classification algorithm to compare the performance of the feature extraction algorithms. For two of those pipelines, Common Spatial Patterns (CSP) and Short Time Fourier Transform (STFT) were successfully used as feature extraction algorithms where both these algorithms are significantly new for meditation EEG. As a novel concept, the third BCI pipeline used a feature extraction algorithm that fused the features of CSP and STFT, achieving the highest classification accuracies among all tested pipelines. Analyses were conducted using EEG data of 3, 4 or 5 sessions, totaling 3960 tests on the entire dataset. At the end of the study, when considering all the tests, the overall classification accuracy using SCP alone was 67.1%, and it was 67.8% for STFT alone. The algorithm combining the features of CSP and STFT achieved an overall classification accuracy of 72.9% which is more than 5% higher than the other two pipelines. At the same time, the highest mean classification accuracy for the 12 participants was achieved using the pipeline with the combination of CSP STFT algorithm, reaching 75.5% for LKM-Self/ non-meditation for the case of 5 sessions of data. Additionally, the highest individual classification accuracy of 88.9% was obtained by the participant no. 14. Furthermore, the results showed that the classification accuracies for all three pipelines increased with the number of training sessions increased from 2 to 3 and then to 4. The study was successful in classifying a new session of EEG meditation/ non-meditation data after training machine learning algorithms using a different set of session data, and this achievement will be beneficial in the development of algorithms that support meditation.
Comparable studies
Other experimental studies on meditation, most cited first.
| Study | Year | Design | Participants |
|---|---|---|---|
| The benefits of being present: Mindfulness and its role in psychological well-being. Cancer patients (clinical intervention study) | 2003 | Mixed methods: scale development, correlational, quasi-experimental, laboratory, experience-sampling, and clinical intervention study | |
| Loving-kindness meditation increases social connectedness. | 2008 | Controlled laboratory experiment | |
| Mindfulness and mind-wandering: Finding convergence through opposing constructs. | 2012 | Two studies: correlational study and experimental study | |
| Mental Training Enhances Attentional Stability: Neural and Behavioral Evidence | 2009 | Experimental study | |
| Mindfulness meditation and substance use in an incarcerated population. Incarcerated population | 2006 | Quasi-experimental with treatment-as-usual control condition |
Citations in the library
Cited by 2
- Exploring EEG biomarkers in meditation, yoga, and mantra practices: a review of neural correlates and methodologies Neural Computing and Applications March 5, 2026
- Advanced Analysis of Alpha EEG Patterns for Identifying Meditative States in Alpha Power Activation Yoga (APAY) International Research Journal of Multidisciplinary Technovation March 30, 2025
Cites 44
- Neural correlates of attentional expertise in long-term meditation practitioners Proceedings of the National Academy of Sciences June 28, 2007
- Mindfulness on-the-go: Effects of a mindfulness meditation app on work stress and well-being. Journal of Occupational Health Psychology May 3, 2018
- Frontal theta EEG activity correlates negatively with the default mode network in resting state International Journal of Psychophysiology July 13, 2007
- Review of the Neural Oscillations Underlying Meditation Frontiers in Neuroscience March 26, 2018
- Quantitative change of EEG and respiration signals during mindfulness meditation Journal of NeuroEngineering and Rehabilitation May 14, 2014
and 39 more in the library