Date of Graduation
5-2016
Document Type
Thesis
Degree Name
Bachelor of Science in Industrial Engineering
Degree Level
Undergraduate
Department
Industrial Engineering
Advisor/Mentor
Rainwater, Chase E.
Committee Member/Reader
Ricke, Steven
Abstract
The food science discipline has many issues requiring research within academia in order to protect the food that gets distributed from industry. The team within the Center for Food Safety at the University of Arkansas’ Division of Agriculture has been studying the gastrointestinal microbial community in broiler chickens in order to control pathogenic bacteria and improve gut health within the chickens to promote a healthy adult microbiota. This has many positive effects on the quality of the chickens. The team performs a standard method of analysis on every experiment run within a software called QIIME to determine if a treatment had a significant effect on the chickens. QIIME also offers a supervised learning script that attempts to label the treatment for each of the samples within a test using the microbial data alone which allows a researcher to see if there is a significant difference between the treatments. This script performs similarly to how a machine learning algorithm would perform. Machine learning is a tool that could provide a lot of important insight on the microbial data offered from the sequencing of the DNA from the chickens. The goal of this thesis is to demonstrate that statistical learning tools within machine learning could serve as effective tools within food science.
Citation
Hacker, J. C. (2016). Statistical Learning Tools with Food Science. Industrial Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/ineguht/44
