Next Article in Journal
Gain-Phase Errors Calibration for a Linear Array Based on Blind Signal Separation
Next Article in Special Issue
Using Magneto-Inertial Measurement Units to Pervasively Measure Hip Joint Motion during Sports
Previous Article in Journal
A Systematic Review of IoT Solutions for Smart Farming
Previous Article in Special Issue
The Influence of Proprioceptive Training with the Use of Virtual Reality on Postural Stability of Workers Working at Height
 
 
Article

Classification of Alpine Skiing Styles Using GNSS and Inertial Measurement Units

1
Salzburg Research Forschungsgesellschaft m.b.H., Techno-Z III, Jakob-Haringer-Straße 5, 5020 Salzburg, Austria
2
Department of Sport and Exercise Science, University of Salzburg, Schlossallee 49, 5400 Hallein/Rif, Austria
3
Athlete Performance Center—Red Bull Sports, 5020 Salzburg, Austria
4
Atomic Austria GmbH, Atomic Strasse 1, 5541 Altenmarkt, Austria
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(15), 4232; https://doi.org/10.3390/s20154232
Received: 26 May 2020 / Revised: 22 July 2020 / Accepted: 28 July 2020 / Published: 29 July 2020
(This article belongs to the Special Issue Human and Animal Motion Tracking Using Inertial Sensors)
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. View Full-Text
Keywords: accelerometer; decision trees; gradient boosted trees; gyroscope; random forests; sensors; ski; sports analytics accelerometer; decision trees; gradient boosted trees; gyroscope; random forests; sensors; ski; sports analytics
Show Figures

Figure 1

MDPI and ACS Style

Neuwirth, C.; Snyder, C.; Kremser, W.; Brunauer, R.; Holzer, H.; Stöggl, T. Classification of Alpine Skiing Styles Using GNSS and Inertial Measurement Units. Sensors 2020, 20, 4232. https://doi.org/10.3390/s20154232

AMA Style

Neuwirth C, Snyder C, Kremser W, Brunauer R, Holzer H, Stöggl T. Classification of Alpine Skiing Styles Using GNSS and Inertial Measurement Units. Sensors. 2020; 20(15):4232. https://doi.org/10.3390/s20154232

Chicago/Turabian Style

Neuwirth, Christina, Cory Snyder, Wolfgang Kremser, Richard Brunauer, Helmut Holzer, and Thomas Stöggl. 2020. "Classification of Alpine Skiing Styles Using GNSS and Inertial Measurement Units" Sensors 20, no. 15: 4232. https://doi.org/10.3390/s20154232

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop