Dr. Chun-An (Joe) Chou from the Systems Science & Industrial Engineering Department - Binghamton University will present Pattern Analysis of Cognitive Representations with fMRI Data on Thursday, December 5th from 10am to 11am in the Engineering & Science Building, room 2008W, as part of the CoCo Seminar Series. Multi-voxel pattern analysis (MVPA) of functional magnetic resonance imaging (fMRI) data is an emerging approach for probing the neural correlates of cognition. MVPA allows cognitive states to be modeled as distributed patterns of neural activity and classified according to stimulus conditions. In practice, building a robust, generalizable classification model can be challenging in machine learning because the number of voxels (features) far exceeds the number of stimulus instances/data observations. To avoid model overfitting, feature selection is a key step to select informative voxels before building a classification model. In this study, we present an embedded feature selection framework using information theory and sparse optimization techniques, applied to various cognitive fMRI datasets. Assessment metrics are introduced to quantify the consistency of cognitive structure and demonstrate their utility in evaluating feature selection approaches. The experimental results suggest that highly informative voxels may provide meaningful insights into the functional-anatomic relationship of neural activity and stimulus conditions. Dr. Chou is an Assistant Professor in Systems Science and Industrial Engineering. His research interests include mathematical optimization modeling and computation, data mining/machine learning, medical applications, computational biology, and engineering systems management. For more information on the CoCo Seminar Series, contact Hiroki Sayama ([email protected]) or visit coco.binghamton.edu/
Posted on: Mon, 02 Dec 2013 18:35:17 +0000
Trending Topics
Recently Viewed Topics
© 2015