Identifying Cross Country Skiing Techniques Using Power Meters in Ski Poles

  • Moa JohanssonEmail author
  • Marie Korneliusson
  • Nickey Lizbat Lawrence
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1056)


Power meters are widely used for measuring training and racing effort in cycling, and the use of such sensors is now spreading also to other sports. Data collected from athletes’ power meters are used to help coaches analyse and understand training load, racing efforts, technique etc. In this pilot project, we have collaborated with Skisens AB, a company producing handles for cross country ski poles equipped with power meters. We have conducted a pilot study on the use of machine learning techniques on sensor data from Skisens poles to identify which sub-technique a skier is using (double poling or gears 2–4 in skating). The dataset contain labelled time-series data from three individual skiers using four different sub-techniques recorded in varied locations and varied terrain. We evaluated three machine learning models based on neural networks, with best results obtained by a LSTM network (accuracy of 95% correctly classified strokes), when a subset of data from all three skiers was used for training. As expected, accuracy dropped to 78% when the model was trained on data from only two skiers and tested on the third.


  1. 1.
    Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18, 602–610 (2005)CrossRefGoogle Scholar
  2. 2.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  3. 3.
    Hols, A., Jonasson, A.: Classification of movement patterns in skiing. In: Frontiers in Artificial Intelligence and Applications: Twelfth Scandinavian Conference on Artificial Intelligence, vol. 257 (2013)Google Scholar
  4. 4.
    Jang, J., et al.: A unified deep-learning model for classifying the cross-country skiing techniques using wearable gyroscope sensors. Sensors 18(11), 3819 (2018)CrossRefGoogle Scholar
  5. 5.
    Johansson, M., Korneliusson, M., Lizbat Lawrence, N.: Identifying cross country skiing techniques using power meters in skipoles. (2019)
  6. 6.
    Marshland, F., Lyons, K., Anson, J., Waddington, G., Macintosh, C., Chapman, D.: Identification of cross-country skiing movement patterns using micro-sensors. Sensors 12(4), 5047–5066 (2012)CrossRefGoogle Scholar
  7. 7.
    Nilsson, J., Tveit, P., Eikrehagen, O.: Effects of speed on temporal patterns in classical style and freestyle cross-country skiing. Sports Biomech. 3(1), 85–107 (2004)CrossRefGoogle Scholar
  8. 8.
    Rindal, O., Seeberg, T., Tjønnås, J., Haugnes, P., Sandbakk, Ø.: Automatic classification of sub-techniques in classical cross-country skiing using a machine learning algorithm on micro-sensor data. Sensors 18(2), 75 (2017)CrossRefGoogle Scholar
  9. 9.
    Sakurai, Y., Zenya, F., Ishige, Y.: Automated identification and evaluation of subtechniques in classical-style roller skiing. J. Sports Sci. Med. 13, 651–657 (2014)Google Scholar
  10. 10.
    Sakurai, Y., Zenya, F., Ishige, Y.: Automatic identification of subtechniques in skating-style roller skiing using inertial sensors. Sensors 16, 473 (2016)CrossRefGoogle Scholar
  11. 11.
    Stöggl, T., et al.: Automatic classification of the sub-techniques (gears) used in cross-country ski skating employing a mobile phone. Sensors 14, 20589–20601 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Moa Johansson
    • 1
    Email author
  • Marie Korneliusson
    • 1
  • Nickey Lizbat Lawrence
    • 1
  1. 1.Chalmers University of TechnologyGothenburgSweden

Personalised recommendations