Detection of freely moving thoughts using SVM and EEG signals

Poster Session C - Sunday, April 14, 2024, 5:00 – 7:00 pm EDT, Sheraton Hall ABC

Sairamya Nanjappan Jothiraj¹ (sairamya.nanjappanjo@ucalgary.ca), Caitlin Mills², Zachary C. Irving³, Julia Kam⁴; ¹Postdoctoral Associate, University of Calgary, ²Assistant Professor, University of Minnesota, ³Assistant Professor, University of Virginia, ⁴Assistant Professor, University of Calgary

Freely moving thought is a type of thinking that shifts from one topic to another without any overarching direction or aim. The ability to detect when freely moving thought occurs may help us promote its beneficial outcomes, such as creative thinking and positive mood. Despite these benefits, no studies thus far have used machine learning to detect freely moving thought using “objective” (e.g. neural or physiological) measures. Our study fills this gap, using event-related potential (ERP) and spectral features of EEG signals in machine learning to detect freely moving thought. Specifically, our classification models detect freely moving thought based on previously collected EEG signals during a simple attention task. The statistical and entropy features of the P3 ERP and alpha spectral measures were entered as inputs to the support vector machine (SVM) for detecting freely moving thoughts. EEG features were first examined with both inter-subject and intra-subject strategies. The best combination of EEG features achieving higher classification performance in both strategies were then selected to combine with behavioral features to further enhance classification performance. Our best performing model has an MCC and AUC of 0.3105 and 0.6665 for inter-subject models and 0.2815 and 0.6407 for intra-subject models respectively. The above chance level performance in both strategies using EEG and behavioral features shows great promise for machine learning approaches to detect freely moving thought and highlights their potential for real-time prediction of freely moving thought.

Topic Area: OTHER