Background: Electrophotonic Imaging (EPI) also known as Gas Discharge Visualization (GDV)is one of the instrument to capture the internal activities based on the stimulation of photon and electron emissions from the surface of the object.
Meditation is a family of complex emotional and attentional regulatory training mechanism and it involves uninterrupted monitoring to capture subtle internal processes. Several instruments are used to understand the impact of meditation by monitoring the brain waves online or by understanding the activities in the Default Mode Network. The objective of this study is to use the EPI data to establish a frame work for intervention recognition by training a neural network by capturing the subtler aspects of meditation.
Methods: A single group pre-post intervention study was carried out on 51 adults (32 males and 19 females) at Pyramid Valley International, Bengaluru, India. Anapanasati a focused attention meditation was given for 5 days. EPI data was captured before and after the intervention. The data was analyzed using IBM SPSS Neural network software.
Results: Meditation was found to have a significant impact on EPI parameters. Neural network was able to classify pre and post meditative population using EPI data with an accuracy ranging from 84% to 100%. The receiver operating characteristics (ROC) was captured for each of the classification and the area under the curve was close to unity.
Conclusion: Electrophonic Imaging combined with neural network works as a good framework for intervention recognition.