Schedule of Events | Search Abstracts | Symposia | Invited Symposia | Poster Sessions | Data Blitz Sessions

Poster F85

EEG-based classification algorithms reveal differential neural processing of words and images

Poster Session F - Tuesday, April 16, 2024, 8:00 – 10:00 am EDT, Sheraton Hall ABC

Neda R. Morakabati1 (, Alison S. Thiha1, Eitan Schechtman1; 1Department of Neurobiology and Behavior and Center for the Neurobiology of Learning and Memory, University of California, Irvine, CA, USA

Machine learning methods employing neuroimaging data are useful for monitoring the activation and reactivation of neural representations in the brain. Specifically, they can be used for observing brain networks that are recruited for processing specific categories of items. This approach has been used predominantly with functional magnetic resonance imaging data, and more rarely with electroencephalography (EEG) data. Here, we developed a task, analytic pipeline, and stimulus dataset to optimize category classification with EEG. Participants (N=30) viewed a series of images and words belonging to five categories (Animals, Tools, Food, Scenes, and Vehicles) and responded when items from the same category were presented consecutively. We trained support vector machines on their EEG activity and found that both images and words yielded significant category classification accuracy levels, with the former showing higher accuracy than the latter. When comparing category pairs, some were more distinguishable than others (e.g., Animals vs. Scenes were more distinguishable than Vehicles vs. Food). Electrodes over the occipital lobe contributed more to image classification, whereas electrodes over the temporal lobes contributed more to word classification. Our data and analytic pipeline yielded high classification accuracies, at least for image stimuli, providing support for the utility of EEG data for neural decoding. We believe these methods can be instrumental for exploring the activation and reactivation of neural representations on the category level in both wakefulness and, potentially, in sleep as well.

Topic Area: METHODS: Electrophysiology


CNS Account Login


April 13–16  |  2024