JISAR

Journal of Information Systems Applied Research

Volume 15

V15 N3 Pages 13-23

Oct 2022


Classification of Hunting-Stressed Wolf Populations Using Machine Learning


John Stewart
Robert Morris University
Pittsburgh, PA USA

Gary Alan Davis
Robert Morris University
Pittsburgh, PA USA

Diane Igoche
Robert Morris University
Pittsburgh, PA USA

Abstract: The preservation of Wolf populations in North America has been controversial for hundreds of years. The preservation of ecosystems or the reintroduction of wolf populations in areas to redress the ecological balance has taken place in recent decades. In other areas, wolves are hunted in an effort to manage them. Previous studies have identified physiological characteristics as an indicator of higher stress levels in individual wolf subjects in heavily hunted populations. This stress impacts reproduction, social structure and pack dynamics. The current study supports a prior study that used statistics to show elevated stress levels in hunted wolf populations. Using machine learning (k-nearest neighbor) we were able to classify individual wolf subjects as belonging to hunting-based stressed populations based on physiological data with high accuracy.

Download this article: JISAR - V15 N3 Page 13.pdf


Recommended Citation: Stewart, J., Davis, G., Igoche, D., (2022). Classification of Hunting-Stressed Wolf Populations Using Machine Learning. Journal of Information Systems Applied Research15(3) pp 13-23. http://JISAR.org/2022-3/ ISSN : 1946 - 1836. A preliminary version appears in The Proceedings of CONISAR 2021