A cross-sectional evaluation of meditation experience on electroencephalography data by artificial neural network and support vector machine classifiers

Lee, Yu-Hao; Hsieh, Ya-Ju; Shiah, Yung‐Jong; Lin, Yu-Huei; Chen, Chiao-Yun; Tyan, Yu‐Chang; GengQiu, JiaCheng; Hsu, Chung‐Yao; Chen, Sharon Chia-Ju

doi:10.1097/md.0000000000006612

Cited by 11 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Hinterberger et al ( 2011 ) used a linear classifier and could classify subjects in distinct pre-induced meditation states, while Ahani et al ( 2013 , 2014 ) using the Support Vector Machine (SVM) algorithm, associated EEG with respiration to discriminate whether stressed subjects engage or not in a 6-weeks intervention. In addition, Lee et al ( 2017 ) also used the SVM and an artificial neuronal network (ANN) based on spectral features to classify meditation expertise of focused breathing practitioners (CDM-FA), and Sharma et al ( 2019 ) employed ANN to differentiate meditators and non-meditators.…”

Section: Discussionmentioning

confidence: 99%

A Critical Analysis on Characterizing the Meditation Experience Through the Electroencephalogram

Deolindo

Ribeiro

Aratanha

et al. 2020

Front. Syst. Neurosci.

View full text Add to dashboard Cite

Meditation practices, originated from ancient traditions, have increasingly received attention due to their potential benefits to mental and physical health. The scientific community invests efforts into scrutinizing and quantifying the effects of these practices, especially on the brain. There are methodological challenges in describing the neural correlates of the subjective experience of meditation. We noticed, however, that technical considerations on signal processing also don't follow standardized approaches, which may hinder generalizations. Therefore, in this article, we discuss the usage of the electroencephalogram (EEG) as a tool to study meditation experiences in healthy individuals. We describe the main EEG signal processing techniques and how they have been translated to the meditation field until April 2020. Moreover, we examine in detail the limitations/assumptions of these techniques and highlight some good practices, further discussing how technical specifications may impact the interpretation of the outcomes. By shedding light on technical features, this article contributes to more rigorous approaches to evaluate the construct of meditation.

show abstract

Section: Discussionmentioning

confidence: 99%

A Critical Analysis on Characterizing the Meditation Experience Through the Electroencephalogram

Deolindo

Ribeiro

Aratanha

et al. 2020

Front. Syst. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Nevertheless, our traditional machine learning method FBCSP + SVM, and the deep learning methods shallow and deep ConvNets for MBSR1/MBSR2 classification all perform almost perfectly on non-inter-subject classification scenarios, with respective classification accuracy as 91.16, 99.81, and 99.95% for mix-subject classification. As a comparison, in the mix-subject classification scenario, the classification of senior/junior/novice Tibetan Nyingmapa meditation expertise attains an average accuracy of 99.05% as reported in Lee et al (2017) , and the classification of expert/novice Kriya yoga meditation experience using SVM and kernel SVM (k-SVM) has classification accuracy of 85.54 and 90.83%, respectively, as reported in Shaw and Routray (2016) . However, for inter-subject classification, the two deep learning ConvNets do not perform satisfactorily, while the traditional machine learning methods CSP + SVM and FBCSP + SVM still perform reasonably well with classification accuracy of 88.66 and 85.00%, respectively, comparable to 91.01, 90.57, and 88.73% reported in Pandey and Miyapuram (2021) for a theoretically more discriminative task of experts/non-experts/non-meditators classification.…”

Section: Discussionmentioning

confidence: 96%

“…Meditation expertise increases through training and practice, and there will be both state and trait effects which can be characterized in either behavioral data or brain activities such as resting EEG for trait effect and meditating EEG for state effect ( Cahn and Polich, 2006 ; Zarka et al, 2022 ). There is lack of studies on classification of brain states for different training and practicing stages longitudinally for individual meditation practitioners, but some efforts have been spent on classifying subjects with different levels of meditation expertise using EEG in either the meditating states ( Shaw and Routray, 2016 ; Lee et al, 2017 ; Pandey and Miyapuram, 2021 ) or the resting states ( Sharma et al, 2019 ), as detailed in Table 6 , where the results of our study in this paper on meditation stage classification using meditation EEG (MBSR1/MBSR2) and resting state EEG (REST1/REST2), are also presented for ease of comparison.…”

Section: Discussionmentioning

confidence: 99%

EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning

Shang,

Duan,

et al. 2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionThis study examines the state and trait effects of short-term mindfulness-based stress reduction (MBSR) training using convolutional neural networks (CNN) based deep learning methods and traditional machine learning methods, including shallow and deep ConvNets as well as support vector machine (SVM) with features extracted from common spatial pattern (CSP) and filter bank CSP (FBCSP).MethodsWe investigated the electroencephalogram (EEG) measurements of 11 novice MBSR practitioners (6 males, 5 females; mean age 35.7 years; 7 Asians and 4 Caucasians) during resting and meditation at early and late training stages. The classifiers are trained and evaluated using inter-subject, mix-subject, intra-subject, and subject-transfer classification strategies, each according to a specific application scenario.ResultsFor MBSR state effect recognition, trait effect recognition using meditation EEG, and trait effect recognition using resting EEG, from shallow ConvNet classifier we get mix-subject/intra-subject classification accuracies superior to related previous studies for both novice and expert meditators with a variety of meditation types including yoga, Tibetan, and mindfulness, whereas from FBSCP + SVM classifier we get inter-subject classification accuracies of 68.50, 85.00, and 78.96%, respectively.ConclusionDeep learning is superior for state effect recognition of novice meditators and slightly inferior but still comparable for both state and trait effects recognition of expert meditators when compared to the literatures. This study supports previous findings that short-term meditation training has EEG-recognizable state and trait effects.

show abstract

“…In this technique, the HRV features (linear and nonlinear) are transformed to auditory signal pitch, timbres, etc., by a process known as sonification. On implementation of machine learning-based discrimination of Deka and Deka BioMedical Engineering OnLine (2023) 22:35 meditative and pre-meditative state it has been noticed that only a few works [14,27,93,94] employ machine learning techniques (pattern recognition, SVM, pNN, LVQ, etc., classifiers) to distinguish the meditative state from non-meditative state, probably due to the small size of publicly available datasets. However data augmentation strategy [14] such as window slicing, concatenation based techniques can be very effective to enable machine learning-based classification works; whereas, in studies related to cardiac pathologies, comparatively larger (adequate) amount data are available in public domain.…”

Section: Discussionmentioning

confidence: 99%

Nonlinear analysis of heart rate variability signals in meditative state: a review and perspective

Deka

2023

BioMed Eng OnLine

View full text Add to dashboard Cite

Introduction In recent times, an upsurge in the investigation related to the effects of meditation in reconditioning various cardiovascular and psychological disorders is seen. In majority of these studies, heart rate variability (HRV) signal is used, probably for its ease of acquisition and low cost. Although understanding the dynamical complexity of HRV is not an easy task, the advances in nonlinear analysis has significantly helped in analyzing the impact of meditation of heart regulations. In this review, we intend to present the various nonlinear approaches, scientific findings and their limitations to develop deeper insights to carry out further research on this topic. Results Literature have shown that research focus on nonlinear domain is mainly concentrated on assessing predictability, fractality, and entropy-based dynamical complexity of HRV signal. Although there were some conflicting results, most of the studies observed a reduced dynamical complexity, reduced fractal dimension, and decimated long-range correlation behavior during meditation. However, techniques, such as multiscale entropy (MSE) and multifractal analysis (MFA) of HRV can be more effective in analyzing non-stationary HRV signal, which were hardly used in the existing research works on meditation. Conclusions After going through the literature, it is realized that there is a requirement of a more rigorous research to get consistent and new findings about the changes in HRV dynamics due to the practice of meditation. The lack of adequate standard open access database is a concern in drawing statistically reliable results. Albeit, data augmentation technique is an alternative option to deal with this problem, data from adequate number of subjects can be more effective. Multiscale entropy analysis is scantily employed in studying the effect of meditation, which probably need more attention along with multifractal analysis. Methods Scientific databases, namely PubMed, Google Scholar, Web of Science, Scopus were searched to obtain the literature on “HRV analysis during meditation by nonlinear methods”. Following an exclusion criteria, 26 articles were selected to carry out this scientific analysis.

show abstract

A cross-sectional evaluation of meditation experience on electroencephalography data by artificial neural network and support vector machine classifiers

Abstract: Supplemental Digital Content is available in the text

Cited by 11 publications

References 41 publications

A Critical Analysis on Characterizing the Meditation Experience Through the Electroencephalogram

A Critical Analysis on Characterizing the Meditation Experience Through the Electroencephalogram

EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning

Nonlinear analysis of heart rate variability signals in meditative state: a review and perspective

Contact Info

Product

Resources

About