Date of Award

Fall 12-2021

Document Type


Degree Name

Master of Science (MS)


Computational and Data Sciences

First Advisor

Erik Linstead

Second Advisor

Rene German

Third Advisor

Dennis Dixon


Machine learning and deep learning methods are becoming increasingly used in the understanding, identification, and improvement of the diagnosis and treatment of Autism Spectrum Disorder. People with ASD often exemplify challenging behaviors that can put their safety, education, and general quality of life at risk. Challenging behaviors are driven by one of four functions. The combination of common occurrences of challenging behaviors and their respective behavioral functions are unique to the individual and circumstance, and the most successful therapies account for both challenging behaviors and their respective functions. Therefore, it is important that research is done on these concepts to lead to improvements in therapy and outcomes.

In this thesis, we apply a cluster analysis to a sample of 1,416 individuals with Autism Spectrum Disorder. The aim is to find groupings of patients based on the relative frequency of each unique challenging behavior and function pair. As the first machine learning study to focus on combining the behavioral functions and challenging behaviors of ASD, we find that there are some patterns to be found based on eight identified clusters. The results of the study could impact the way that treatment and therapy plans are paved for children with Autism Spectrum Disorder.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.