Online Program Home
My Program

Abstract Details

Activity Number: 521 - Contributed Poster Presentations: Mental Health Statistics Section
Type: Contributed
Date/Time: Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
Sponsor: Mental Health Statistics Section
Abstract #305234
Title: ERP Algorithmic Source Separation (ERPASS) in Multi-Task EEG Experiments
Author(s): Emilie Campos*
Companies: UCLA
Keywords: dimension reduction; source separation; multi-task EEG; group ICA
Abstract:

Electroencephalogram (EEG) is a noninvasive technology used commonly in studying psychiatric disorders where the data is typically analyzed within a single task. However, an increasing number of studies collect EEG on the same set of subjects across multiple tasks. For joint analysis of data from multi-task EEG experiments, Event Related Potential Algorithmic Source Separation (ERPASS) is proposed. ERPASS contains dimension reduction through principal components analysis (PCA) at the electrode and subject levels and utilizes FastICA for ERP source separation. A combination of PCA and ICA algorithms have been used to analyze multi-subject EEG data previously. However, ERPASS departs from this literature in pooling information across multiple tasks in deriving at the underlying ERP components which can be further used to decompose ERP data across tasks. These decompositions can lead to further analysis of the variability in the data across tasks, electrodes and subjects. We demonstrate the effectiveness of ERPASS through extensive simulations and data analysis on subjects diagnosed with Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD).


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program