Summary

In this project, we explored the possibility and challenges associated with conducting experiments with children in a stimulating complex public environment. We also explored the feasibility of using deep learning techniques to help identify relevant patterns of brain activity associated with different conditions: rest versus video game play, and male versus female. This approach could be an efficient tool to be used in studies to uncover patterns from electrophysiological data. We also investigated the age-related changes in spectral features in EEG in the temporo-parietal channels. Similar to prior research work, we observed that absolute power decreased with age in all frequency bands, particularly in the slower frequency bands. The general trend observed in this study were again in agreement with prior research, which associates the reduction in slow wave activity with the reduction in gray matter as we develop/mature. The relative power had a trend of correlating negatively with age for delta and theta bands while the faster bands like alpha and beta correlated positively with age. This trend is consistent with what is observed in previous studies in laboratory environment. However only the theta band in TP9 was found to be statistically significant in our analysis. Overall, the current study contributes to a better understanding of how deep learning can be used as a data driven approach to identify patterns in your data and explored the issues and the potential of conducting experiments involving children in a natural and engaging environment.

”

Outputs:

Ravindran AS, Mobiny A, Cruz‐Garza JG, Paek A, Kopteva A, and Vidal JLC. Assaying neural activity of children during video game play in public spaces: a deep learning approach. Journal of neural engineering 2019;16:036028. DOI: 10.1088/1741‐2552/ab1876.