Next Article in Journal
CMOS Time-Resolved, Contact, and Multispectral Fluorescence Imaging for DNA Molecular Diagnostics
Previous Article in Journal
Wireless Sensor Networks for Heritage Object Deformation Detection and Tracking Algorithm
Open AccessArticle

Automatic Classification of the Sub-Techniques (Gears) Used in Cross-Country Ski Skating Employing a Mobile Phone

1
Department of Sport Science and Kinesiology, University of Salzburg, Hallein/Rif 5400, Austria
2
Swedish Winter Sports Research Centre, Department of Health Sciences, Mid Sweden University, Östersund 83140, Sweden
3
Swedish Institute of Computer Science, Kista 16440, Sweden
4
School of Computer Science and Communication, Royal Institute of Technology, Stockholm 10044, Sweden
5
Swedish Olympic Committee, Stockholm 11433, Sweden
*
Author to whom correspondence should be addressed.
Sensors 2014, 14(11), 20589-20601; https://doi.org/10.3390/s141120589
Received: 17 September 2014 / Revised: 25 October 2014 / Accepted: 27 October 2014 / Published: 31 October 2014
(This article belongs to the Section Physical Sensors)
The purpose of the current study was to develop and validate an automatic algorithm for classification of cross-country (XC) ski-skating gears (G) using Smartphone accelerometer data. Eleven XC skiers (seven men, four women) with regional-to-international levels of performance carried out roller skiing trials on a treadmill using fixed gears (G2left, G2right, G3, G4left, G4right) and a 950-m trial using different speeds and inclines, applying gears and sides as they normally would. Gear classification by the Smartphone (on the chest) and based on video recordings were compared. Formachine-learning, a collective database was compared to individual data. The Smartphone application identified the trials with fixed gears correctly in all cases. In the 950-m trial, participants executed 140 ± 22 cycles as assessed by video analysis, with the automatic Smartphone application giving a similar value. Based on collective data, gears were identified correctly 86.0% ± 8.9% of the time, a value that rose to 90.3% ± 4.1% (P < 0.01) with machine learning from individual data. Classification was most often incorrect during transition between gears, especially to or from G3. Identification was most often correct for skiers who made relatively few transitions between gears. The accuracy of the automatic procedure for identifying G2left, G2right, G3, G4left and G4right was 96%, 90%, 81%, 88% and 94%, respectively. The algorithm identified gears correctly 100% of the time when a single gear was used and 90% of the time when different gears were employed during a variable protocol. This algorithm could be improved with respect to identification of transitions between gears or the side employed within a given gear. View Full-Text
Keywords: algorithm; collective classification; gaussian filter; individual classification; markov chain; machine learning; smartphone algorithm; collective classification; gaussian filter; individual classification; markov chain; machine learning; smartphone
MDPI and ACS Style

Stöggl, T.; Holst, A.; Jonasson, A.; Andersson, E.; Wunsch, T.; Norström, C.; Holmberg, H.-C. Automatic Classification of the Sub-Techniques (Gears) Used in Cross-Country Ski Skating Employing a Mobile Phone. Sensors 2014, 14, 20589-20601.

Show more citation formats Show less citations formats

Article Access Map

1
Only visits after 24 November 2015 are recorded.
Back to TopTop