Date of Award
Summer 2025
Document Type
Open Access Thesis
Department
Computer Science and Engineering
First Advisor
Ramtin Zand
Second Advisor
Homayoun Valafar
Abstract
Competitive swimming performance analysis has traditionally relied on manual video review and multi-sensor systems, both of which are resource-intensive and impractical for everyday training use. This study investigates whether a single wrist-worn inertial measurement unit (IMU) can be used to automatically segment and classify swimming activities with high accuracy. We propose a multi-task deep learning pipeline based on the MTHARS (Multi-Task Human Activity Recognition and Segmentation) architecture introduced by Duan et al. to perform stroke classification, lap segmentation, stroke count estimation, and underwater kick count estimation. Data were collected from eleven collegiate-level swimmers wearing left-wrist-mounted IMUs, each performing five 100-yard sets per stroke (butterfly, backstroke, breaststroke, freestyle, and individual medley) in a 25-yard pool. This pipeline delivers a reliable multi-metric evaluation while significantly reducing the complexity and cost of sensor setups. In leave-one-subject-out validation, the accelerometer-only model achieved a micro-F₁ of 0.7405 (macro-F₁ 0.5894), which improved to 0.7709 (macro-F₁ 0.6565) when gyroscope data were added. This work contributes to the growing field of wearable-based athlete monitoring and has the potential to empower coaches and athletes with real-time, fine-grained performance feedback in competitive swimming using minimal hardware.
Rights
© 2025, Mark Shperkin
Recommended Citation
Shperkin, M.(2025). Multi-Task Deep Learning Approach for Segmenting and Classifying Competitive Swimming Activities Using a Single IMU. (Master's thesis). Retrieved from https://scholarcommons.sc.edu/etd/8556