In this paper, we present an analysis to identify a sensor location for an inertial measurement unit (IMU) on the body of a skier and propose the best location to capture turn motions for training. We also validate the manner in which the data from the IMU sensor on the proposed location can characterize ski turns and performance with a series of statistical analyses, including a comparison with data collected from foot pressure sensors. The goal of the study is to logically identify the ideal location on the skier’s body to attach the IMU sensor and the best use of the data collected for the skier. The statistical analyses and the hierarchical clustering method indicate that the pelvis is the best location for attachment of an IMU, and numerical validation shows that the data collected from this location can effectively estimate the performance and characteristics of the skier. Moreover, placement of the sensor at this location does not distract the skier’s motion, and the sensor can be easily attached and detached. The findings of this study can be used for the development of a wearable device for the routine training of professional skiers.
The automatic classification of cross-country (XC) skiing techniques using data from wearable sensors has the potential to provide insights for optimizing the performance of professional skiers. In this paper, we propose a unified deep learning model for classifying eight techniques used in classical and skating styles XC-skiing and optimize this model for the number of gyroscope sensors by analyzing the results for five different configurations of sensors. We collected data of four professional skiers on outdoor flat and natural courses. The model is first trained over the flat course data of two skiers and tested over the flat and natural course data of a third skier in a leave-one-out fashion, resulting in a mean accuracy of ~80% over three combinations. Secondly, the model is trained over the flat course data of three skiers and tested over flat course and natural course data of one new skier, resulting in a mean accuracy of 87.2% and 95.1% respectively, using the optimal sensor configuration (five gyroscope sensors: both hands, both feet, and the pelvis). High classification accuracy obtained using both approaches indicates that this deep learning model has the potential to be deployed for real-time classification of skiing techniques by professional skiers and coaches.