Modelling of Cognitive Functions in Driving Environment using EEG
-
1
University of South Australia, Information Technology, Engineering and Environment, Australia
-
2
PSG College of Technology, Department of Applied Mathematics and Computational Sciences, India
There is an increased interest in the field of cognitive modelling based upon the study of behavioural data such as analysis of latency and error rate. The advances in brain imaging techniques such as Electroencephalogram (EEG), Magnetoencephalogram (MEG), functional Magnetic Resonance Imaging (fMRI) along with robust and advanced signal analysis and computational techniques during the last three decades have enabled the emergence of new cognitive modelling approaches.
In our work, we have proposed a methodology to model the cognitive functions by relating various EEG parameters such as latency, amplitude, power, spectra of Event Related Potential (ERP) to different stimuli features to predict the cognitive state. By using the input stimuli features and their corresponding EEG responses, we aim to undertake system identification to characterize the cognitive function.
We are primarily using driving simulator to selectively perturb cognitive functions such as memory, arousal, fatigue, distraction, etc. and try to recognize the features of corresponding brains signals (brain stamps). The experiments are conducted in a simulated driving environment. The processed EEG data is subjected to different feature classifier and clustering techniques to identify and model the cognitive functions. A Graph Database is also set up by computing Pearson Correlation Coefficients to determine the functional relationships between EEG electrode sites during normal and cognitive load conditions. The functional brain network under cognitive load has already produced some patterns such as existence of new neural connections during cognitive load, highly cohesive sub networks, etc. Some interesting results relating to cognitive modelling and functional brain networks during cognitive state will be presented.
Keywords:
cognitive model,
EEG features,
pattern recognition,
computational neuroscience,
feature extraction
Conference:
ACNS-2012 Australasian Cognitive Neuroscience Conference, Brisbane, Australia, 29 Nov - 2 Dec, 2012.
Presentation Type:
Poster Presentation
Topic:
Other
Citation:
Dahal
N,
Nandagopal
N,
Vijayalakshimi
R,
Cocks
B,
Nafalski
A and
Nedic
Z
(2012). Modelling of Cognitive Functions in Driving Environment using EEG.
Conference Abstract:
ACNS-2012 Australasian Cognitive Neuroscience Conference.
doi: 10.3389/conf.fnhum.2012.208.00135
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
24 Sep 2012;
Published Online:
17 Nov 2012.
*
Correspondence:
Mr. Nabaraj Dahal, University of South Australia, Information Technology, Engineering and Environment, Adelaide, Australia, nabaraj.dahal@unisa.edu.au