Identifier

etd-11182013-162101

Degree

Doctor of Philosophy (PhD)

Department

Electrical and Computer Engineering

Document Type

Dissertation

Abstract

Psychological analysis related to voluntary reciprocal trust games were obtained using functional magnetic resonance imaging (fMRI) hyperscanning for 44 pairs of strangers throughout 36 trust games (TG) and 16 control games (CG). Hidden Markov models (HMMs) are proposed to train and classify the fMRI data acquired from these brain regions and extract the essential features of the initial decision of the first player to trust or not trust the second player. These results are evaluated using the different versions of the multifold cross-validation technique and compared to other speech data and other advanced signal processing techniques including linear classification, support vector machines (SVMs), and HMMs. With above 80% classification accuracy for HMM as compared to no more than 66% classification accuracy of a linear classifier and SVM, the corresponding experimental results demonstrate that the HMMs can be adopted as an outstanding paradigm to predict the psychological financial (trust/non-trust) activities reflected by the neural responses recorded using fMRI. Additionally, extracting the specific decision period and clustering the continuous time series proved to increase the classification accuracy by almost 20%.

Date

2013

Document Availability at the Time of Submission

Secure the entire work for patent and/or proprietary purposes for a period of one year. Student has submitted appropriate documentation which states: During this period the copyright owner also agrees not to exercise her/his ownership rights, including public use in works, without prior authorization from LSU. At the end of the one year period, either we or LSU may request an automatic extension for one additional year. At the end of the one year secure period (or its extension, if such is requested), the work will be released for access worldwide.

Committee Chair

Wu, Hsiao-Chun

Share

COinS