Committee Chair

Liang, Yu

Committee Member

Wu, Dalei; Hogg, Jennifer

Department

Dept. of Computational Science

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

Athlete performance scoring within climbing presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill level is valuable as it can be used to mark training progress and help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. Solutions to the classification problem included light-weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Acknowledgments

I would like to give a special thank you to Mr. Benjamin Spannuth for collecting the climbing data used throughout this study and allowing me to use it. Furthermore, I would like to thank my advisors, Dr. Liang and Dr. Wu, for offering me guidance during my time in the graduate program. Thank you Dr. Jennifer Hogg for allowing me to work on one of your projects and helping me with mine. Thank you Dr. Kimberly Carter for helping to keep my tenses straight and fixing all of my other grammatical problems.

Degree

M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.

Date

5-2022

Subject

Data sets; Machine learning; Rock climbing

Keyword

classification; climbing; data imbalance; data scarcity; machine learning; time sequence

Document Type

Masters theses

DCMI Type

Text

Extent

x, 33 leaves

Language

English

Rights

http://rightsstatements.org/vocab/InC/1.0/

License

http://creativecommons.org/licenses/by/4.0/

Download

Share

COinS