Graduation Year
2023
Document Type
Dissertation
Degree
Ph.D.
Degree Name
Doctor of Philosophy (Ph.D.)
Degree Granting Department
Computer Science and Engineering
Major Professor
Shaun Canavan, Ph.D.
Committee Member
Dmitry Goldgof, Ph.D.
Committee Member
Heather Agazzi, Ph.D.
Committee Member
Tempestt Neal, Ph.D.
Committee Member
Pei-Sung Lin, Ph.D.
Keywords
Autism, Emotion, Expression, Age
Abstract
Human behavior analysis is an important application area of artificial intelligence. Usingdata collected from sensors (e.g., cameras), human behavior including, but not limited to, emotions, expressions, body movement, and eye gaze are analyzed. This analysis is useful in applications in diverse fields ranging from healthcare, defense, education, and marketing. Considering this, in this dissertation, we have proposed new approaches to emotion and expression recognition, subject identification, and classification of autism spectrum disorder. More specifically, this dissertation has the following contributions: 1) A new approach for multimodal ubiquitous emotion recognition is proposed; 2) Investigation into the impact of large expression variations on 3D subject identification is detailed; 3) An approach to generalizing expression across age ranges (children vs. elderly) is proposed; 4) This is the first work to propose using self-report questionnaire data to classify autism spectrum disorder across age ranges; and (5) This is the first work to proposed a context-based approach to classifying videos of children at risk for autism spectrum disorder.
Scholar Commons Citation
Jannat, Sk Rahatul, "Multimodal Assessment of Human Behavior with Applications in Analysis of Autism Spectrum Disorder" (2023). USF Tampa Graduate Theses and Dissertations.
https://digitalcommons.usf.edu/etd/10760
