Date Thesis Awarded


Access Type

Honors Thesis -- Access Restricted On-Campus Only

Degree Name

Bachelors of Science (BS)


Computer Science


Gang Zhou

Committee Members

Kevin Weng

Denys Poshyvanyk

S. Laurie Sanderson

Timothy Davis, Kevin Weng


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.

On-Campus Access Only