
Date of Award
Summer 8-2020
Document Type
Thesis
Degree Name
Master of Science (MS)
Department/Program
Forensic Science
Language
English
First Advisor or Mentor
Angelique Corthals
Second Reader
Nicholas D. K. Petraco
Third Advisor
Rosemarie Zimmerman
Abstract
Simple methods to aid in the determination of forensic or archaeologic relevancy of skeletonized remains have been researched since the 1950s. With advances in microscopic imaging techniques and machine learning computer data analysis methods the relevancy of decontextualized, comingled remains has room for improvement. This thesis is a study done to pioneer a new approach to analyzing dental skeletal remains to determine forensic relevancy.
Archaeological dental samples collected from the ancient city of Ur in modern day southern Iraq in addition to modern dental extractions were processed for scanning electron microscopy imaging. Archaeological and modern samples displayed different surface and dentinal tubule opening characteristics. The image files were then analyzed using a custom-built convolutional neural net model. The model’s performance metrics indicate that the model made better than random predictions based on learned associations. Thus, the use of scanning electron microscopy and machine learning analysis techniques has potential in distinguishing archaeological dental samples from modern dental samples.
Recommended Citation
Vincenty, Jessica A., "Archaeology or crime scene? Teeth micro and macro structure analysis as dating variable" (2020). CUNY Academic Works.
https://academicworks.cuny.edu/jj_etds/170
Included in
Archaeological Anthropology Commons, Biological and Physical Anthropology Commons, Forensic Science and Technology Commons
Comments
Python code repository can be accessed at the following GitHub link: https://github.com/jho9/Deep-Learning-Analysis-of-Teeth-Scans