Cognitive state prediction using an EM algorithm applied to Gamma distributed data

Behavioral tests are widely used to quantify features of cognitive processing. For a large class of behavioral signals, the observed variables are non-Gaussian and dynamic; classical estimation algorithms are ill-suited to modeling such data. In this research, we propose a mathematical framework to...

Full description

Saved in:
Bibliographic Details
Published in2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2015; pp. 7819 - 7824
Main Authors Yousefi, Ali, Paulk, Angelique C., Deckersbach, Thilo, Dougherty, Darin D., Eskandar, Emad N., Widge, Alik S., Eden, Uri T.
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.08.2015
Subjects
Algorithms
Cognition - physiology
Data models
Distributed databases
Heuristic algorithms
Humans
Interference
Mathematical model
Models, Theoretical
Prediction algorithms
Psychophysics - statistics & numerical data
Reaction Time
Statistical Distributions
Switches
Online AccessGet full text

Cover

More Information
Summary:Behavioral tests are widely used to quantify features of cognitive processing. For a large class of behavioral signals, the observed variables are non-Gaussian and dynamic; classical estimation algorithms are ill-suited to modeling such data. In this research, we propose a mathematical framework to predict a cognitive state variable related to behavioral signals, which are best modeled using a Gamma distribution. The proposed algorithm combines a Gamma Smoother and EM algorithm in the prediction process. The algorithm is applied to reaction time recorded from subjects performing a Multi-Source Interference Task (MSIT) to dynamically quantify their cognitive flexibility through the course of the experiment.
ISSN:1094-687X
1557-170X
DOI:10.1109/EMBC.2015.7320205