Pandey, PankajPankajPandeyMiyapuram, Krishna PrasadKrishna PrasadMiyapuram2025-08-312025-08-312021-01-01[9781665401265]10.1109/BIBM52615.2021.96694572-s2.0-85125200077https://d8.irins.org/handle/IITG2025/26370With an increasing effort from the scientific community to quantify the effects of meditation practices, various approaches have been used to establish neural correlates of experienced meditators. Numerous techniques have been studied to identify meditation-related changes in brain signals, including network analysis, synchronization metrics, and spectral features. Here, we employ nonlinear measures to explore the dynamical aspects of electroencephalography (EEG) signals in participants who had completed an 8-week Mindfulness Based Stress Reduction training program via pre-post intervention changes. Three nonlinear complexity measures comprising Detrended Fluctuation Analysis (DFA), Higuchi fractal dimension (FD), and Katz FD are implemented to measure the complexity of EEG signals. We examine theta and alpha frequency bands with a specific focus on four sub-bands, along with four anterior and posterior regions. Random Forest (RF) with SHAP explainability method is used to generate the results. RF models are trained for classification on features extracted from pre- and post-session. Our findings reveal that (a) Higuchi FD exhibits a decline post-training session and delivers the best classifying results; (b) the alpha wave contributes the most in the left-right frontal and parietal regions; (c) and overall, the right hemisphere has greater involvement. These findings add to the growing body of knowledge about the neural correlates of meditation. This research's implications for designing neurotechnology products that improve attention, awareness, and kindness have been discussed.falseDFA | EEG | Fractal Dimension | Machine Learning | Mindfulness Meditation | SHAP ExplanabilityConference Paper3051-3057202114cpConference Proceeding11