Guided Learning Algorithms: An Application of Constrained Spectral Partitioning to Functional Magnetic Resonance Imaging (fMRI)

Innovations in neuro-technology have created a potential gap in our ability to measure human performance and decision making in dynamic environments. Therefore, a need exists to create more reliable testing methodologies and data analytic solutions. The primary aim of this paper is to describe work...

Full description

Saved in:
Bibliographic Details
Published inFoundations of Augmented Cognition pp. 709 - 716
Main Authors Phillips, Henry L., Walker, Peter B., Kennedy, Carrie H., Carmichael, Owen, Davidson, Ian N.
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2013
SeriesLecture Notes in Computer Science
Subjects
augmented cognition
fMRI
functional connectivity
Online AccessGet full text

Cover

More Information
Summary:Innovations in neuro-technology have created a potential gap in our ability to measure human performance and decision making in dynamic environments. Therefore, a need exists to create more reliable testing methodologies and data analytic solutions. The primary aim of this paper is to describe work to integrate subject matter expertise with algorithms designed to measure human brain activity in real time. Specifically, Guided Learning using constrained spectral partitioning to increase the reliability and interpretability of fMRI data is explicated and applied as a test case to the Default Mode Network in the elderly population. How Guided Learning can be further applied to other neuro-imaging technologies that may be more conducing to furthering the field of augmented cognition is discussed.
ISBN:9783642394539
3642394531
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-39454-6_76