Brain-Computer Interface (BCI) technology offers potential for improving meditation practices via real-time neural feedback. Traditional EEG signal processing often fails to account for temporal and inter-channel relationships in the data. This study addresses the gap by modeling EEG signals using a multivariate auto-regressive (MVAR) approach, capturing both temporal dynamics and inter-channel interactions. Sparsity is introduced using the group least absolute shrinkage and selection operator (GLASSO), reducing volume conduction issues. From the sparse coefficient matrix, brain connectivity features such as average energy value (EV), phase lag value (PLV), mean absolute correlation (MAC) and magnitude squared coherence (MSC) are extracted. Statistical analyses and scatter plots highlight the influence of these features on cognitive states during meditation. EEG data is classified into EM, NM and CO states using decision trees (DT), Gaussian naive Bayes (GNB), k-nearest neighbor (KNN), and a multi-layer feed-forward neural network (MLFFNN). Metrics include precision, recall, F1-score and accuracy. DT achieved the best performance with 97.12% accuracy, 96.12% precision, 97.39% recall and an F1-score of 97.01%. This study enhances the EEG classification of meditation states by adding sparsity to the MVAR model. Future work could focus on real-time applications for feedback-driven meditation enhancement.
BraboszczCHahusseauSDelormeA. Integrative clinical psychology, psychiatry and behavioral medicine: perspectives, practices and research. Springer Publishing Company, 2010.
2.
PagnoniGCekicM. Age effects on gray matter volume and attentional performance in zen meditation. Neurobiol Aging2007; 28: 1623–1627.
3.
YoganandaP. Autobiography of a Yogi: The Original 1946 Edition plus Bonus Material. Nevada City, CA: Crystal Clarity Publishers, 2005.
4.
BablaniAEdlaDRKupilliV, et al.Lie detection using fuzzy ensemble approach with novel defuzzification method for classification of eeg signals. IEEE Trans Instrum Meas2021; 70: 1–13.
5.
AnsariMFEdlaDRDodiaS, et al.Brain-computer interface for wheelchair control operations: An approach based on fast fourier transform and on-line sequential extreme learning machine. Clin Epidemiol Glob Health2019; 7: 274–278.
6.
EdlaDRMangalorekarKDhavalikarG, et al.Classification of eeg data for human mental state analysis using random forest classifier. Procedia Comput Sci2018; 132: 1523–1532.
7.
DingMChenYBresslerSL. Granger causality: basic theory and application to neuroscience. Handb Time Ser Anal: Recent Theor Dev Appl2006; 30: 437–460.
8.
BaccaláLASameshimaK. Partial directed coherence: a new concept in neural structure determination. Biol Cybern2001; 84: 463–474.
9.
KamińskiMDingMTruccoloWA, et al.Evaluating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment of significance. Biol Cybern2001; 85: 145–157.
10.
SameshimaKBaccaláLA. Methods in Brain Connectivity Inference Through Multivariate Time Series Analysis. Boca Raton, FL: CRC Press, 2014.
11.
PandeyPGuptaPMiyapuramKP. Brain connectivity based classification of meditation expertise. In: International conference on brain informatics, 2021, pp.89–98. Springer.
12.
ShawLRoutrayA. A new framework to infer intra-and inter-brain sparse connectivity estimation for eeg source information flow. IEEE Sens J2018; 18: 10134–10144.
13.
SharmaHRajRJunejaM. Eeg signal based classification before and after combined yoga and sudarshan kriya. Neurosci Lett2019; 707: 134300.
14.
ShawLRoutrayA. Statistical features extraction for multivariate pattern analysis in meditation eeg using pca. In: 2016 IEEE EMBS International student conference (ISC), 2016, pp.1–4. IEEE.
15.
MunjalRVarshneyTChoudharyA, et al.A deep learning approach for effective classification of himalayan yoga meditative mind and non-meditative mind. Available at SSRN 2021; SSRN 4579711.
16.
VidaurreDBielzaCLarranagaP. Classification of neural signals from sparse autoregressive features. Neurocomputing2013; 111: 21–26.
17.
GulerIUbeyliED. Multiclass support vector machines for eeg-signals classification. IEEE Trans Inf Technol Biomed2007; 11: 117–126.
18.
LiYYuZLBiN, et al.Sparse representation for brain signal processing: a tutorial on methods and applications. IEEE Signal Process Mag2014; 31: 96–106.
19.
MominRMirHAl-NashashH. Cortical source localization and signal estimation without exact knowledge of the leadfield matrix. IEEE Sens J2016; 17: 450–458.
20.
TiwariNEdlaDRDodiaS, et al.Brain computer interface: A comprehensive survey. Biolog Insp Cognit Archit2018; 26: 118–129.
21.
PennyWHarrisonL. Statistical parametric mapping: the analysis of functional brain images. Amsterdam: Academic Press, 2007.
BrandmeyerTDelormeA. Reduced mind wandering in experienced meditators and associated eeg correlates. Exp Brain Res2018; 236: 2519–2528.
25.
BraboszczCCahnBRLevyJ, et al.Increased gamma brainwave amplitude compared to control in three different meditation traditions. PLoS ONE2017; 12: e0170647.
26.
DelormeAMakeigS. Eeglab: an open source toolbox for analysis of single-trial eeg dynamics including independent component analysis. J Neurosci Methods2004; 134: 9–21.
27.
Pion-TonachiniLKreutz-DelgadoKMakeigS. Iclabel: An automated electroencephalographic independent component classifier, dataset, and website. NeuroImage2019; 198: 181–197.
28.
ShawLRoutrayA. Brain state classification with group l 1–norm sparse pdc as novel features for eeg. IEEE Sens J2021; 21: 13506–13513.
29.
HaufeSTomiokaRNolteG, et al.Modeling sparse connectivity between underlying brain sources for eeg/meg. IEEE Trans Biomed Eng2010; 57: 1954–1963.
30.
Valdés-SosaPASánchez-BornotJMLage-CastellanosA, et al.Estimating brain functional connectivity wi sparse multivariate autoregression. Philosoph Trans R Soc B: Biol Sci2005; 360: 969–981.
31.
LeeHLeeDSKangH, et al.Sparse brain network recovery under compressed sensing. IEEE Trans Med Imaging2011; 30: 1154–1165.
32.
ChiangJWangZJMcKeownMJ. Sparse multivariate autoregressive (mar)-based partial directed coherence (pdc) for electroencephalogram (eeg) analysis. In: 2009 IEEE International conference on acoustics, speech and signal processing, 2009, pp.457–460. IEEE.
33.
CohenMX. Effects of time lag and frequency matching on phase-based connectivity. J Neurosci Methods2015; 250: 137–146.
34.
ZouLChenXDangG, et al.Removing muscle artifacts from eeg data via underdetermined joint blind source separation: A simulation study. IEEE Trans Circ Syst II: Express Briefs2019; 67: 187–191.
35.
MalekpourSGubnerJASetharesWA. Measures of generalized magnitude-squared coherence: Differences and similarities. J Franklin Inst2018; 355: 2932–2950.
36.
BablaniAEdlaDRDodiaS. Classification of eeg data using k-nearest neighbor approach for concealed information test. Procedia Comput Sci2018; 143: 242–249.
37.
RussellSJNorvigP. Artificial intelligence: a modern approach. Upper Saddle River, NJ, 2010.
38.
EdlaDRDodiaSBablaniA, et al.An efficient deep learning paradigm for deceit identification test on eeg signals. ACM Trans Manag Inform Syst (TMIS)2021; 12: 1–20.
39.
PandeyPMiyapuramKP. Brain2depth: Lightweight cnn model for classification of cognitive states from eeg recordings. In: Medical image understanding and analysis: 25th Annual conference, MIUA 2021, Oxford, United Kingdom, July 12–14, 2021, Proceedings 25, 2021, pp.394–407. Springer.
PandeyPGuptaPMiyapuramKP. Exploration of brain network measures across three meditation traditions. NeuroRegulation2022; 9: 113–113.
42.
SinghSPandeyPChaudharyS, et al.Towards the development of personalized and generalized interfaces for brain signals across different styles of meditation. In: Proceedings of the thirteenth indian conference on computer vision, graphics and image processing, 2022, pp.1–9.
