Individualized pattern recognition for detecting mind wandering from EEG during live lectures

• DOI: 10.1371/journal.pone.0222276
• Publication Date: 2019-09-12T18:36:27Z
• Authors: Kiret Dhindsa; Anita Acai; Natalie Wagner; Dan Bosynak; Stephen Kelly; Mohit Bhandari; Brad Petrisor; Ranil R. Sonnadara
• Keywords: Mind Wandering

Neural correlates of mind wandering The ability to detect as it occurs is an important step towards improving our understanding this phenomenon and studying its effects on learning performance. Current detection methods typically rely observable behaviour in laboratory settings, which do not capture the underlying neural processes may translate well into real-world settings. We address both these issues by recording electroencephalography (EEG) simultaneously from 15 participants during live lectures research orthopedic surgery. performed traditional group-level analysis found that are similar those some studies, including a decrease occipitoparietal alpha power frontal, temporal, occipital beta power. However, individual-level same data revealed patterns brain activity associated with were more broadly distributed highly individualized than analysis. Mind To apply findings detection, we used data-driven method known common spatial discover scalp topologies for each individual reflects their differences when versus attending lectures. This approach avoids reliance primarily established through statistics. Using machine EEG, able achieve average accuracy 80–83%. Conclusions Modelling at level reveal details about reflected using observational statistical methods. techniques purpose can provide new insight varieties involved wandering, while also enabling real-time naturalistic