EEG Spectral Analysis of Mindfulness Based on EEMD and GNNs

View at publisher Summarise with VIRAT
Authors: Siddharth S. Pedanekar, Dattaprasad A. Torse
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The paper presents a hybrid EEMD-GNN system to study the EEG patterns that are happening in the process of mindfulness and non-mindfulness meditation. The EEMD technique breaks down EEG signals into intrinsic mode functions (IMFs) to adaptively extract theta and beta band information in a noise-resilient manner, and the GNNs to learn the spatial-temporal connectivity of EEG channels based on phase-locking value and coherence. Tests on both public data sets indicate that the suggested model is highly accurate, with 94% accuracy, which is better than the traditional spectral techniques and performs well in tracking beta and theta variation in frontal and parietal regions. Signal decomposition/graph-based learning can be an effective method to understand the reader in neural dynamics during meditation.

Fields of Study & Subjects

EEG and Brain-Computer Interfaces Mindfulness and Compassion Interventions Neural dynamics and brain function

Publication details

Journal / source
International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT)
Pages
424–429
Publication date
4 February 2026
Language
EN