Classification of Alpine Skiing Styles Using GNSS and Inertial Measurement Units

In alpine skiing, four commonly used turning styles are snowplow, snowplow-steering, drifting and carving. They differ significantly in speed, directional control and difficulty to execute. While they are visually distinguishable, data-driven classification is underexplored. The aim of this work is to classify alpine skiing styles based on a global navigation satellite system (GNSS) and inertial measurement units (IMU). Data of 2000 turns of 20 advanced or expert skiers were collected with two IMU sensors on the upper cuff of each ski boot and a mobile phone with GNSS. After feature extraction and feature selection, turn style classification was applied separately for parallel (drifted or carved) and non-parallel (snowplow or snowplow-steering) turns. The most important features for style classification were identified via recursive feature elimination. Three different classification methods were then tested and compared: Decision trees, random forests and gradient boosted decision trees. Classification accuracies were lowest for the decision tree and similar for the random forests and gradient boosted classification trees, which both achieved accuracies of more than 93% in the parallel classification task and 88% in the non-parallel case. While the accuracy might be improved by considering slope and weather conditions, these first results suggest that IMU data can classify alpine skiing styles reasonably well.

[1]  Kamiar Aminian,et al.  The Use of Body Worn Sensors for Detecting the Vibrations Acting on the Lower Back in Alpine Ski Racing , 2017, Front. Physiol..

[2]  Kate Button,et al.  Inertial Measurement Units for Clinical Movement Analysis: Reliability and Concurrent Validity , 2018, Sensors.

[3]  H. Wickham,et al.  A Grammar of Data Manipulation , 2015 .

[4]  Kevin King,et al.  Bowling ball dynamics revealed by miniature wireless MEMS inertial measurement unit , 2011 .

[5]  Richard Brunauer,et al.  Development and Validation of a Gyroscope-Based Turn Detection Algorithm for Alpine Skiing in the Field , 2019, Front. Sports Act. Living.

[6]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[7]  Byung-Kil Han,et al.  Context-Aware Winter Sports Based on Multivariate Sequence Learning , 2019, Sensors.

[8]  Larsson Omberg,et al.  Detecting the impact of subject characteristics on machine learning-based diagnostic applications , 2019, npj Digital Medicine.

[9]  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.

[10]  John P. Sullivan,et al.  A Critical Review of Consumer Wearables, Mobile Applications, and Equipment for Providing Biofeedback, Monitoring Stress, and Sleep in Physically Active Populations , 2018, Front. Physiol..

[11]  C J Dillman,et al.  Muscle activity in wedge, parallel, and giant slalom skiing. , 1997, Medicine and science in sports and exercise.

[12]  Matej Supej,et al.  Estimation of Alpine Skier Posture Using Machine Learning Techniques , 2014, Sensors.

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

[14]  Shuping Xiong,et al.  A Unified Deep-Learning Model for Classifying the Cross-Country Skiing Techniques Using Wearable Gyroscope Sensors , 2018, Sensors.

[15]  Richard Brunauer,et al.  From Sensor Data to Coaching in Alpine Skiing – A Software Design to Facilitate Immediate Feedback in Sports , 2019, Proceedings of the 12th International Symposium on Computer Science in Sport (IACSS 2019).

[16]  C. Furlanello,et al.  Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products , 2006 .

[17]  Mateusz Janiak,et al.  Deep Recurrent Neural Networks for Human Activity Recognition During Skiing , 2019, ICMMI.

[18]  David Harrison,et al.  Review on Wearable Technology Sensors Used in Consumer Sport Applications , 2019, Sensors.

[19]  Max Kuhn,et al.  caret: Classification and Regression Training , 2015 .

[20]  Aaron Martínez,et al.  Development of an Automatic Alpine Skiing Turn Detection Algorithm Based on a Simple Sensor Setup , 2019, Sensors.

[21]  Erich Müller,et al.  Potential Mechanisms Leading to Overuse Injuries of the Back in Alpine Ski Racing , 2015, The American journal of sports medicine.

[22]  Erich Müller,et al.  Biomechanical aspects of new techniques in alpine skiing and ski-jumping , 2003, Journal of sports sciences.

[23]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[24]  Björn Eskofier,et al.  Wearable trick classification in freestyle snowboarding , 2016, 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[25]  Avi Rosenfeld,et al.  Explainability in human–agent systems , 2019, Autonomous Agents and Multi-Agent Systems.

[26]  Alaa Tharwat,et al.  Classification assessment methods , 2020, Applied Computing and Informatics.

[27]  R. Kipp,et al.  Alpine Ski Motion Characteristics in Slalom , 2020, Frontiers in Sports and Active Living.

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  B. Ripley,et al.  Recursive Partitioning and Regression Trees , 2015 .

[30]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[31]  Kamiar Aminian,et al.  Three-Dimensional Body and Centre of Mass Kinematics in Alpine Ski Racing Using Differential GNSS and Inertial Sensors , 2016, Remote. Sens..

[32]  Ole Marius Hoel Rindal,et al.  Automatic Classification of Sub-Techniques in Classical Cross-Country Skiing Using a Machine Learning Algorithm on Micro-Sensor Data , 2017, Sensors.

[33]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[34]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[35]  Pedro M. Valero-Mora,et al.  ggplot2: Elegant Graphics for Data Analysis , 2010 .

[36]  Kamiar Aminian,et al.  Capturing human motion using body‐fixed sensors: outdoor measurement and clinical applications , 2004, Comput. Animat. Virtual Worlds.

[37]  Anton Umek,et al.  The role of science and technology in sport , 2017, IIKI.

[38]  Max A. Little,et al.  Using and understanding cross-validation strategies. Perspectives on Saeb et al. , 2017, GigaScience.

[39]  Konrad P. Kording,et al.  The need to approximate the use-case in clinical machine learning , 2017, GigaScience.

[40]  Erik Andersson,et al.  Automatic Classification of the Sub-Techniques (Gears) Used in Cross-Country Ski Skating Employing a Mobile Phone , 2014, Sensors.

[41]  Bhumika Gupta,et al.  Analysis of Various Decision Tree Algorithms for Classification in Data Mining , 2017 .

[42]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[43]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[44]  Peter Federolf,et al.  Finite element simulation of the ski–snow interaction of an alpine ski in a carved turn , 2010 .

[45]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[46]  E. Valuations.  A REVIEW ON EVALUATION METRICS FOR DATA CLASSIFICATION EVALUATIONS , 2015 .