Date Thesis Awarded

5-2018

Document Type

Honors Thesis

Degree Name

Bachelors of Science (BS)

Department

Computer Science

Advisor

Gang Zhou

Committee Members

Kevin Weng

Denys Poshyvanyk

S. Laurie Sanderson

Timothy Davis, Kevin Weng

Abstract

This paper introduces a novel method for classifying turning in sandbar sharks from accelerometer data. Because marine organisms are difficult to observe visually, attachable tags are often used instead, typically including only an accelerometer for power reasons; measuring complex motions, such as turning, is difficult without a gyroscope. Six features, including a novel metric designed to detect turning direction, are used. To deal with sample imbalance, a mixture of SMOTE and modified bootstrap sampling is employed. The classifier has 79\% accuracy and can highlight periods of heightened turning activity as well as determine the direction of swimming.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS