Artificial Intelligence for Objective Assessment of Acrobatic Movements: Applying Machine Learning for Identifying Tumbling Elements in Cheer Sports
Open Access
Abstract
Over the past four decades, cheerleading evolved from a sideline activity at major sporting events into a professional, competitive sport with growing global popularity. Evaluating tumbling elements in cheerleading relies on both objective measures and subjective judgments, such as difficulty and execution quality. However, the complexity of tumbling—encompassing team synchronicity, ground interactions, choreography, and artistic expression—makes objective assessment challenging. Artificial intelligence (AI) revolutionised various scientific fields and industries through precise data-driven analyses, yet their application in acrobatic sports remains limited despite significant potential for enhancing performance evaluation and coaching. This study investigates the feasibility of using an AI-based approach with data from a single inertial measurement unit to accurately identify and objectively assess tumbling elements in standard cheerleading routines. A sample of 16 participants (13 females, 3 males) from a Division I collegiate cheerleading team wore a single inertial measurement unit at the dorsal pelvis. Over a 4-week seasonal preparation period, 1102 tumbling elements were recorded during regular practice sessions. Using triaxial accelerations and rotational speeds, various ML algorithms were employed to classify and evaluate the execution of tumbling manoeuvres. Our results indicate that certain machine learning models can effectively identify different tumbling elements with high accuracy despite inter-individual variability and data noise. These findings demonstrate the significant potential for integrating AI-driven assessments into cheerleading and other acrobatic sports in order to provide objective metrics that complement traditional judging methods.Keywords
All Related Versions
Funding Information
- German Research Foundation (Deutsche Forschungsgemeinschaft, DFG) (545264300)
- Magdeburg-Stendal University of Applied Sciences (545264300)
This publication has 44 references indexed in Scilit:
- Artificial intelligence and Machine Learning approaches in sports: Concepts, applications, challenges, and future perspectivesBrazilian Journal of Physical Therapy, 2024
- TacticAI: an AI assistant for football tacticsNature Communications, 2024
- Image expression of time series data of wearable IMU sensor and fusion classification of gymnastics actionExpert Systems with Applications, 2023
- Measuring biomechanical loads and asymmetries in junior elite long-distance runners through triaxial inertial sensorsSports Orthopaedics and Traumatology, 2019
- Unmasking Clever Hans predictors and assessing what machines really learnNature Communications, 2019
- Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunitiesJournal of Biomechanics, 2018
- Random ForestsMachine Learning, 2001
- Linear unlearning for cross-validationAdvances in Computational Mathematics, 1996
- Comparing partitionsJournal of Classification, 1985
- Generalized harmonic analysisActa Mathematica, 1930