 |
 |
EEG-Annotate
Tool: |
EEG-Annotate |
Site: |
https://github.com/VisLab/EEG-Annotate |
Authors: |
Kyung-Min Su and Kay Robbins (UTSA), W. David Hairston (ARL) |
Software Language: |
MATLAB 2014 or later |
Software Type: |
command line with scripting for large-scale analysis |
What it does:
EEG-Annotate is an integrated event-identification toolbox that uses machine learning to train classifiers based on labeled event data and then to locate potential similar events in continuous EEG signals. EEG-Annotate employs notions of timing slack and various adaptive thresholding as well as sophisticated transfer learning classifiers. EEG-Annotate includes tools for training, labeling, analyzing, and visualizing results.
Why is this important? EEG acquired in real-world settings is becoming increasingly important, but event markers are often not available. EEG-Annotate is a first step in creating event markers at likely locations based on signal features.
Principal publication:
K. Su, W. D. Hairston, and K. Robbins (2018). EEG-Annotate: Automated identification and labeling of events in continuous signals with applications to EEG, J. Neuroscience Methods, 293(1), 359-374, PMID: 29061343, DOI: 10.1016/j.jneumeth.2017.10.011.
Related publications:
K. Robbins, K-M Su, and W. D. Hairston (2018). An 18-subject EEG data collection using a visual-oddball task, designed for benchmarking algorithms and headset performance comparisons, Data in Brief, 16, Feb. 2018, p 227-230, PMID: 29226211 PMCID: PMC5712810, https://doi.org/10.1016/j.dib.2017.11.032.
K-M. Su, W. Hairston, and K. Robbins (2016). Adaptive thresholding and reweighting to improve domain transfer learning for unbalanced data with applications to EEG, ICMLA 2016 (Dec. 18-20, Anaheim, CA).
