AUTHOR=Goodin Peter , Gardner Andrew J. , Dokani Nasim , Nizette Ben , Ahmadizadeh Saeed , Edwards Suzi , Iverson Grant L. 

TITLE=Development of a Machine-Learning-Based Classifier for the Identification of Head and Body Impacts in Elite Level Australian Rules Football Players

JOURNAL=Frontiers in Sports and Active Living

VOLUME=Volume 3 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2021.725245

DOI=10.3389/fspor.2021.725245

ISSN=2624-9367

ABSTRACT=Background: Exposure to thousands of head and body impacts during a career in contact and collision sports may contribute to current or later in life issues with brain health. Wearable technology enables the measurement of impact exposure. The validation of impact detection is required for accurate exposure monitoring. In this paper, we present a method of automatic identification (classification) of head and body impacts using an instrumented mouth guard, video verified impacts, and machine learning algorithms.
Methods: Time series data were collected via the Nexus A9 mouth guard from 60 elite level men (mean age = 26.33; SD = 3.79) and 4 women (mean age = 25.50; SD = 5.91) Australian Rules Football players from 8 clubs, participating in 119 games during the 2020 season. Ground truth data labelling on the captures used in this machine learning study was performed through analysis of game footage by two expert video reviewers using SportCode and Catapult Vision. The visual labelling process occurred independently of the mouth guard time series data. True positive captures (captures where the reviewer directly observed contact between the mouth guard wearer and another player, the ball, or the ground) were defined as hits. Spectral and convolutional kernel based features were extracted from time series data. Performances of untuned classification algorithms from scikit-learn in addition to XGBoost were assessed to select the best performing baseline method for tuning.
Results: Based on performance, XGBoost was selected as the classifier algorithm for tuning. A total of 13,712 video verified captures were collected and used to train and validate the classifier. True positive detection ranged from 94.67% in the Test set to 100% in the hold out set. True negatives ranged from 95.65% to 96.83% in the Test and Rest sets respectively.
Discussion: The current study employed machine learning to design and validate a head and body impact detection method for elite Australian Rules Football players. A strength of the study was the use of game-footage video verification of head and body impacts recorded by the sensors. The XGBoost based model showed high performance for classifying body and head impacts.