Authors: Vernon Lawhern (ARL/UTSA), Kay Robbins (UTSA), W. David Hairston and Scott Kerick (ARL)
Software Language(s): MATLAB 2014 or later
Software Type: command line / EEGLAB plugin with GUI


What it does: Detect is a toolbox that allows users to quickly train a classifier based on multiple signal classes (usually artifacts). Detect then applies the classifier to unlabeled data. Detect has visualization tools that allow users to scroll through the data and adjust boundaries of identified artifacts. The resulting labeled data can be used to quickly perform manual artifact identification or to check results from automated methods.

Why is this important? The form of EEG artifacts varies dramatically across recordings. Detect allows researchers to manually label artifacts in part of a signal and then to apply the results to continuous detection in the remainder of the signal.

Principal publication:

V. Lawhern, W. D. Hairston, K. A. Robbins (2013). DETECT: A MATLAB toolbox for event detection and identification in time series, with applications to artifact detection in EEG signals, PLoS ONE, 8(4): e62944, PMC3634773.

Related publications:

V. Lawhern, S. Kerick, K. Robbins (2013). Detection of alpha spindling and frequency shifts using discounted AR models, BMC Neuroscience, 14:101, PMC3848457, DOI:10.1186/1471-2202-14-101.

V. Lawhern, W. D. Hairston, K. McDowell, M. Westerfield, and K. A. Robbins (2012). Detection and classification of subject-generated artifacts in EEG signals using autoregressive models, J. Neuroscience Methods 208:181-189. PMID: 22634706.

V Lawhern, WD Hairston, K Robbins (2013). Optimal feature selection for artifact classification in EEG time series HCI International 2013 (July 21-26, Las Vegas), appearing in Foundations of Augmented Cognition, 326-334, Springer-Verlag.