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.
© Copyright 2019 Nordic Artificial Intelligence Research and Development. NAIS 2019. Communications in Computer and Information Science, vol 1056.. Veröffentlicht von Springer. Alle Rechte vorbehalten.