AN INFORMATION THEORETIC REPRESENTATION OF HUMAN BRAIN FOR DECODING MENTAL STATES OF COMPLEX PROBLEM SOLVING

2022-2
Gunal Degirmendereli, Gonul
In this thesis, we propose an information theoretic method for the representation of human brain activity to decode mental states of a high-order cognitive process, complex problem solving (CPS) using functional magnetic resonance images. First, we aim to identify the active regions and represent underlying cognitive states by measuring the information content of anatomical regions for expert and novice problem solvers during the main phases of problem solving, namely planning and execution. Based on Shannon's entropy definition, we define two new measures: static and dynamic entropy. We investigate the relationship between problem solving phases and the entropy values of anatomical regions. The defined entropy measures successfully identify active brain regions involved in complex problem solving. Anatomical regions with low entropy are consistent with active regions recognized by experimental neuroscience. Then, we introduce a novel method to estimate static and dynamic brain networks using Kulback-Leibler divergence (relative entropy) for representing the complex problem solving task. We investigate the validity of the estimated brain networks by modeling the planning and execution phases of the complex problem solving. The suggested computational network model is tested by a classification algorithm to discriminate the two phases of complex problem solving. It is observed that the suggested computational models successfully discriminate the planning and execution phases of the complex problem solving with more than 90\% accuracy. Our results show that the proposed entropy and relative entropy measures hold strong promise for identifying active regions, detecting mind states and predicting brain networks associated with complex problem solving.

Suggestions

On the Entropy of Brain Anatomic Regions for Complex Problem Solving
Degirmendereli, Gonul Gunal; Newman, Sharlene D.; Yarman Vural, Fatoş Tunay (2019-01-01)
In this paper, we aim to measure the information content of brain anatomic regions using the functional magnetic resonance images (fMRI) recorded during a complex problem solving (CPS) task. We, also, analyze the brain regions, activated in different phases of the problem solving process. Previous studies have widely used machine learning approaches to examine the active anatomic regions for cognitive states of human subjects based on their fMRI data. This study proposes an information theoretic method for ...
A Sparse Temporal Mesh Model for Brain Decoding
Afrasiyabi, Arman; Onal, Itir; Yarman Vural, Fatoş Tunay (2016-08-23)
One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI) is the very high dimension of feature space which consists of thousands of voxels in sequence of brain volumes, recorded during a cognitive stimulus. In this study, we propose a new architecture, called Sparse Temporal Mesh Model (STMM), which reduces the dimension of the feature space by combining the voxel selection methods with the mesh learning method. We, first, select the "most discriminative" voxels usin...
An Information Theoretic Approach to Classify Cognitive States Using fMRI
Onal, Itir; Ozay, Mete; Firat, Orhan; GİLLAM, İLKE; Yarman Vural, Fatoş Tunay (2013-11-13)
In this study, an information theoretic approach is proposed to model brain connectivity during a cognitive processing task, measured by functional Magnetic Resonance Imaging (fMRI). For this purpose, a local mesh of varying size is formed around each voxel. The arc weights of each mesh are estimated using a linear regression model by minimizing the squared error. Then, the optimal mesh size for each sample, that represents the information distribution in the brain, is estimated by minimizing various inform...
Functional Mesh Learning for Pattern Analysis of Cognitive Processes
Firat, Orhan; Ozay, Mete; Onal, Itir; GİLLAM, İLKE; Yarman Vural, Fatoş Tunay (2013-07-18)
We propose a statistical learning model for classifying cognitive processes based on distributed patterns of neural activation in the brain, acquired via functional magnetic resonance imaging (fMRI). In the proposed learning machine, local meshes are formed around each voxel. The distance between voxels in the mesh is determined by using functional neighborhood concept. In order to define functional neighborhood, the similarities between the time series recorded for voxels are measured and functional connec...
A Hierarchical representation and decoding of fMRI data by partitioning a brain network
Moğultay, Hazal; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2017)
In this study, we propose a hierarchical network representation of human brain extracted from fMRI data. This representation consists of two levels. In the first level, we form a network among the voxels, smallest building block of fMRI data. In the second level, we define a set of supervoxels by partitioning the first level network into a set of subgraphs, which are assu med to represent homogeneous brain regions with respect to a predefined criteria. For this purpose, we develop a novel brain parcellation...
Citation Formats
G. Gunal Degirmendereli, “AN INFORMATION THEORETIC REPRESENTATION OF HUMAN BRAIN FOR DECODING MENTAL STATES OF COMPLEX PROBLEM SOLVING,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.