Date of Award:
5-2026
Document Type:
Dissertation
Degree Name:
Doctor of Philosophy (PhD)
Department:
Mathematics and Statistics
Committee Chair(s)
Kevin Moon
Committee
Kevin Moon
Committee
Soukaina Filali Boubrahimi
Committee
Shuhan Yuan
Committee
Alan Wisler
Committee
Aryn Kamerer
Committee
Yan Sun
Abstract
This dissertation explores how modern artificial intelligence techniques can be used to better understand complex biological data. Specifically, it develops new machine learning based methods and applies them to two important biomedical problems: analyzing brain signals and studying protein behavior.
The first part of the work introduces a new machine learning approach designed to improve how computers classify structured data. Traditional neural networks are powerful but can sometimes generalize poorly. This research proposes a method that combines the flexibility of neural networks with the reliability of ensemble techniques, leading to more robust and accurate predictions across different types of datasets.
The second part focuses on auditory brainstem responses (ABRs), which are electrical signals generated by the brain in response to sound. These signals are commonly analyzed by clinicians, but feature extraction is often performed manually and requires training. This dissertation presents an automated system that models key features of these brain waves mathematically, allowing important characteristics such as timing and amplitude to be measured accurately and consistently.
The third part addresses how proteins unfold when heated, a process measured using differential scanning calorimetry. In complex biological mixtures, interpreting these measurements can be challenging. This work develops a computational framework that can adjust for measurement scaling differences and even learn previously unknown protein behavior directly from data.
Together, these studies demonstrate how artificial intelligence and optimization techniques can extract meaningful structure from complex biological signals, potentially improving biomedical research and future diagnostic tools.
Recommended Citation
Mau, Jarrod, "Gradient Based Optimization Methods for Robust Learning and Biomedical Signal Modeling" (2026). All Graduate Theses and Dissertations, Fall 2023 to Present. 805.
https://digitalcommons.usu.edu/etd2023/805
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .