Publication Date
Spring 2026
Degree Type
Master's Project
Degree Name
Master of Science in Bioinformatics (MSBI)
Department
Computer Science
First Advisor
Leonard Wesley, Ph.D.
Second Advisor
William Andreopoulous, Ph.D.
Third Advisor
Fabio Di Troia, Ph.D.
Keywords
Evidential Reasoning, Expectation Maximization, Compatibility Relationships, Lysine Acetyltransferases, Drug Development, Machine Learning
Abstract
The presented expectation maximization informed evidential reasoning model extends the ability of the evidential reasoning calculus to support decision making by integrating an adaptive model learning capability. Compatibility relationships in Evidential Reasoning models are traditionally built by human domain experts. This process is labor-intensive, especially for large and complex models. Additionally, when new data becomes available, compatibility relationships must be reconstructed. Using machine learning and the expectation maximization algorithm, it is demonstrated that compatibility relationships can be constructed that learn relationships between domain knowledge that is used to make decisions. Using drug development as a domain of application, a traditional mass distribution was modeled, discounting procedures were applied and an “Unknown” category is introduced to represent latent decision-related variables. Lastly, the results highlight how the decision model adapts over time with the incorporation of additional data. By reducing reliance on human domain experts and incorporating an adaptive capability, the EM-ER approach offers a cost-effective alternative for constructing Evidential Reasoning frameworks.
Recommended Citation
Thomas, Ella Jolie, "Match Made in ML: Developing Compatibility Relationships in Evidential Reasoning Approaches with Machine Learning" (2026). Master's Projects. 1668.
https://scholarworks.sjsu.edu/etd_projects/1668
