Doctor of Philosophy (PhD), Wright State University, 2019, Computer Engineering

Human brain analysis and understanding pose several challenges due to the great complexity of the structural organization and the functional connectivity that characterizes the human brain. The ability of the brain to adapt in dynamic changes over time such as normal aging, neurodegenerative diseases or congenital brain malformations renders the brain's exploration a particularly demanding and difficult task. In recent years, advances in brain imaging modalities and lately the multimodal fusion, combined with improvements in related technologies have greatly assisted the development of brain maps by providing insights regarding the overall brain structure and functionality. Even though the existence of sensory and motor maps for the human brain is known to some degree, the formation process is still subject to research. Electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) are the two mostly used non-invasive brain imaging modalities that can track the changes in brain activity. Due to their complementary nature, high temporal resolution from EEG and high spatial resolution from fMRI, the fusion of simultaneous acquired EEG and fMRI recordings aims to provide complementary information about the brain functionality. In an effort to extend the current research in the field of brain understanding, a novel Brain Mapping Model (BMM) based on EEG and fMRI is proposed within this Ph.D. dissertation. The proposed BMM is based on the synergy of state-of-the-art computational techniques to associate the brain regional activities provided by the EEG-fMRI fusion. In more details, first, a novel formal model for the EEG signals' representation is proposed. The proposed formal model enables the analysis and extraction of structural EEG features. The proposed method is based on the Syntactic Aggregate approXimation (SAX) algorithm, that in this work is improved by the Local-Global (LG) graph technique, to compose a Context Free-Grammar (CFG). Moreover (open full item for complete abstract)

Committee: Nikolaos G. Bourbakis Ph.D. (Advisor); Soon M. Chung Ph.D. (Committee Member); Bin Wang Ph.D. (Committee Member); Konstantinos Michalopoulos Ph.D. (Committee Member) Subjects: Computer Engineering

Master of Sciences (Engineering), Case Western Reserve University, 2008, EECS - Computer Engineering

This thesis explores the use of machine learning in the context of autonomous mobile robots driving on roads, with the focus on improving the robot's internal map. Early chapters cover the mapping efforts of DEXTER, Team Case's entry in the 2007 DARPA Urban Challenge. Competent driving may include the use of a priori information, such as road maps, and online sensory information, including vehicle position and orientation estimates in absolute coordinates as well as error coordinates relative to a sensed road. An algorithm may select the best of these typically flawed sources, or more robustly, use all flawed sources to improve an uncertain world map, both globally in terms of registration corrections and locally in terms of improving knowledge of obscured roads. It is shown how unsupervised learning can be used to train recognition of sensor credibility in a manner applicable to optimal data fusion.

Committee: Wyatt Newman PhD (Advisor); M. Cenk Cavusoglu PhD (Committee Member); Francis Merat PhD (Committee Member) Subjects: Computer Science; Engineering; Robots