An Evaluation of Wearable Inertial Sensor Configuration and Supervised Machine Learning Models for Automatic Punch Classification in Boxing

Machine learning is a powerful tool for data classification and has been used to classify movement data recorded by wearable inertial sensors in general living and sports. Inertial sensors can provide valuable biofeedback in combat sports such as boxing; however, the use of such technology has not had a global uptake. If simple inertial sensor configurations can be used to automatically classify strike type, then cumbersome tasks such as video labelling can be bypassed and the foundation for automated workload monitoring of combat sport athletes is set. This investigation evaluates the classification performance of six different supervised machine learning models (tuned and untuned) when using two simple inertial sensor configurations (configuration 1—inertial sensor worn on both wrists; configuration 2—inertial sensor worn on both wrists and third thoracic vertebrae [T3]). When trained on one athlete, strike prediction accuracy was good using both configurations (sensor configuration 1 mean overall accuracy: 0.90 ± 0.12; sensor configuration 2 mean overall accuracy: 0.87 ± 0.09). There was no significant statistical difference in prediction accuracy between both configurations and tuned and untuned models (p > 0.05). Moreover, there was no significant statistical difference in computational training time for tuned and untuned models (p > 0.05). For sensor configuration 1, a support vector machine (SVM) model with a Gaussian rbf kernel performed the best (accuracy = 0.96), for sensor configuration 2, a multi-layered perceptron neural network (MLP-NN) model performed the best (accuracy = 0.98). Wearable inertial sensors can be used to accurately classify strike-type in boxing pad work, this means that cumbersome tasks such as video and notational analysis can be bypassed. Additionally, automated workload and performance monitoring of athletes throughout training camp is possible. Future investigations will evaluate the performance of this algorithm on a greater sample size and test the influence of impact window-size on prediction accuracy. Additionally, supervised machine learning models should be trained on data collected during sparring to see if high accuracy holds in a competition setting. This can help move closer towards automatic scoring in boxing. View Full-Text

[1]  Richard James Neil Helmer,et al.  Development of an automated scoring system for amateur boxing , 2010 .

[2]  Matthew T. O. Worsey,et al.  Anytime, Anywhere! Inertial Sensors Monitor Sports Performance , 2019, IEEE Potentials.

[3]  Alan Godfrey,et al.  Inertial Sensor Technology for Elite Swimming Performance Analysis: A Systematic Review , 2015, Sensors.

[4]  Eamonn Delahunt,et al.  Classification of deadlift biomechanics with wearable inertial measurement units. , 2017, Journal of biomechanics.

[5]  Valentina Camomilla,et al.  Trends Supporting the In-Field Use of Wearable Inertial Sensors for Sport Performance Evaluation: A Systematic Review , 2018, Sensors.

[6]  Faicel Chamroukhi,et al.  Physical Human Activity Recognition Using Wearable Sensors , 2015, Sensors.

[7]  AbdiHervé,et al.  Principal Component Analysis , 2010, Essentials of Pattern Recognition.

[8]  Said El Ashker Technical and tactical aspects that differentiate winning and losing performances in boxing , 2011 .

[9]  Jonathan B. Shepherd,et al.  A Literature Review Informing an Operational Guideline for Inertial Sensor Propulsion Measurement in Wheelchair Court Sports , 2018, Sports.

[10]  Tom Stewart,et al.  Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review , 2020 .

[11]  B. Elliott,et al.  Long-axis rotation: The missing link in proximal-to-distal segmental sequencing , 2000, Journal of sports sciences.

[12]  David V. Thiel,et al.  A Systematic Review of Performance Analysis in Rowing Using Inertial Sensors , 2019 .

[13]  Matthew T. O. Worsey,et al.  Features Observed Using Multiple Inertial Sensors for Running Track and Hard-Soft Sand Running: A Comparison Study , 2020, Proceedings.

[14]  Yuji Ohgi,et al.  Sensor Data Mining on the Kinematical Characteristics of the Competitive Swimming , 2014 .

[15]  James Nicholson,et al.  Activity Recognition for Quality Assessment of Batting Shots in Cricket using a Hierarchical Representation , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[16]  Marek R. Ogiela,et al.  Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes , 2017, Sensors.

[17]  H. Abdi,et al.  Principal component analysis , 2010 .

[18]  Sam Robertson,et al.  Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance , 2018, Journal of sports sciences.

[19]  R. Nagahara,et al.  Measurement of Pelvic Orientation Angles during Sprinting Using a Single Inertial Sensor , 2020, Proceedings.

[20]  Damian Farrow,et al.  Development of a Skill Acquisition Periodisation Framework for High-Performance Sport , 2017, Sports Medicine.

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  Tom Stewart,et al.  Cricket fast bowling detection in a training setting using an inertial measurement unit and machine learning , 2018, Journal of sports sciences.

[23]  Samir A. Rawashdeh,et al.  Wearable IMU for Shoulder Injury Prevention in Overhead Sports , 2016, Sensors.

[24]  Julius Hannink,et al.  Activity recognition in beach volleyball using a Deep Convolutional Neural Network , 2017, Data Mining and Knowledge Discovery.

[25]  David Rowlands,et al.  Development and Validation of a Single Wrist Mounted Inertial Sensor for Biomechanical Performance Analysis of an Elite Netball Shot , 2017, IEEE Sensors Letters.

[26]  Dong Seog Han,et al.  Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network , 2018, Sensors.

[27]  David V. Thiel,et al.  Predicting Ground Reaction Forces in Sprint Running Using a Shank Mounted Inertial Measurement Unit , 2018 .

[28]  David Whiteside,et al.  Monitoring Hitting Load in Tennis Using Inertial Sensors and Machine Learning. , 2017, International journal of sports physiology and performance.

[29]  David V. Thiel,et al.  Evaluating the Use of Inertial-Magnetic Sensors to Assess Fatigue in Boxing During Intensive Training , 2017, IEEE Sensors Letters.

[30]  Matthew T. O. Worsey,et al.  Inertial Sensors for Performance Analysis in Combat Sports: A Systematic Review , 2019, Sports.