EEG Signal based Classification Before and After combined Yoga and Sudarshan Kriya.

Author: Sharma H1, Juneja M2, Raj R3
Affiliation: <sup>1</sup>Department of Computer Science and Engineering, Panjab University, Chandigarh, India. Electronic address: himikasharma3@gmail.com. <sup>2</sup>Department of Computer Science and Engineering, Panjab University, Chandigarh, India. <sup>3</sup>Department of Psychiatry, Government Medical College, Rajindra Hospital, Patiala, India.
Conference/Journal: Neurosci Lett.
Date published: 2019 Jun 7
Other: Volume ID: 134300 , Special Notes: doi: 10.1016/j.neulet.2019.134300. [Epub ahead of print] , Word Count: 280


Nowadays, the style of living is restless and busy which has resulted in increased stress among many people. Stress causes various mental and health illness such as depression, anxiety, mood disorders, and aggressive behavior. Yoga and Sudarshan Kriya (SK) meditation are healthy ways to eradicate stress from people's lives. Based on the previous study, it has been analyzed that SK practice helps to enhance relaxation, management of emotion, alertness, focus, and antidepressant effect. In this paper, the combined impact of yoga and SK meditation has been analyzed on brain signals by using statistical parameters. To the best of the authors' knowledge, no such study has been conducted in the past. In this study, the pre and post Electroencephalogram (EEG) signals were captured from the control and study group before and after three months regular practice of combined yoga and SK. Discrete Wavelet Transform (DWT) has been used to decompose the signal into 6 sub-bands (0-4, 4-8, 8-16, 16-32, 32-64, 64-128) hertz (Hz) by using db4 wavelet for analysis, statistical features such as variance, standard deviation, kurtosis, zero crossing, maximum and minimum have been calculated from each sub-band. The obtained parameters have been validated by using Kruskal-Wallis statistical test. Further, Artificial Neural Network (ANN) has been applied on aforementioned statistical parameters to classify subjects as meditators and non-meditators. The experimental results indicated that the proposed method achieved 87.2% accuracy for classification and could be further extended to construct an accurate classification system for detection of meditators and non-meditators. This study forms a scientific foundation to encourage the use of meditation in clinical practices.

Copyright © 2019. Published by Elsevier B.V.

KEYWORDS: Artificial Neural Network; Classification; DWT; EEG; Sudarshan Kriya; Yoga

PMID: 31181300 DOI: 10.1016/j.neulet.2019.134300