Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.jneumeth.2011.11.023
Title: A spatio-temporal filtering approach to denoising of single-trial ERP in rapid image triage
Authors: Yu, K.
Shen, K. 
Shao, S. 
Ng, W.C. 
Kwok, K. 
Li, X. 
Keywords: Correlation filtering
Rapid image triage
Single-trial
Spatio-temporal
Issue Date: 15-Mar-2012
Source: Yu, K., Shen, K., Shao, S., Ng, W.C., Kwok, K., Li, X. (2012-03-15). A spatio-temporal filtering approach to denoising of single-trial ERP in rapid image triage. Journal of Neuroscience Methods 204 (2) : 288-295. ScholarBank@NUS Repository. https://doi.org/10.1016/j.jneumeth.2011.11.023
Abstract: Conventional search for images containing points of interest (POI) in large-volume imagery is costly and sometimes even infeasible. The rapid image triage (RIT) system which is a human cognition guided computer vision technique is potentially a promising solution to the problem. In the RIT procedure, images are sequentially presented to a subject at a high speed. At the instant of observing a POI image, unique POI event-related potentials (ERP) characterized by P300 will be elicited and measured on the scalp. With accurate single-trial detection of such unique ERP, RIT can differentiate POI images from non-POI images. However, like other brain-computer interface systems relying on single-trial detection, RIT suffers from the low signal-to-noise ratio (SNR) of the single-trial ERP. This paper presents a spatio-temporal filtering approach tailored for the denoising of single-trial ERP for RIT. The proposed approach is essentially a non-uniformly delayed spatial Gaussian filter that attempts to suppress the non-event related background electroencephalogram (EEG) and other noises without significantly attenuating the useful ERP signals. The efficacy of the proposed approach is illustrated by both simulation tests and real RIT experiments. In particular, the real RIT experiments on 20 subjects show a statistically significant and meaningful average decrease of 9.8% in RIT classification error rate, compared to that without the proposed approach. © 2011 Elsevier B.V.
Source Title: Journal of Neuroscience Methods
URI: http://scholarbank.nus.edu.sg/handle/10635/59271
ISSN: 01650270
DOI: 10.1016/j.jneumeth.2011.11.023
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

4
checked on Dec 7, 2017

WEB OF SCIENCETM
Citations

4
checked on Nov 22, 2017

Page view(s)

32
checked on Dec 17, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.