In order to gain insight into skiing performance, it is necessary to determine the point where each turn begins. Recent developments in sensor technology have made it possible to develop simpler automatic turn detection methodologies, however they are not feasible for regular use. The aim of this study was to develop a sensor set up and an algorithm to precisely detect turns during alpine ski, which is feasible for a daily use. An IMU was attached to the posterior upper cuff of each ski boot. Turn movements were reproduced on a ski-ergometer at different turn durations and slopes. Algorithms were developed to analyze vertical, medio-lateral, anterior-posterior axes, and resultant accelerometer and gyroscope signals. Raw signals, and signals filtered with 3, 6, 9, and 12 Hz cut-offs were used to identify turn switch points. Video recordings were assessed to establish a reference turn-switch and precision (mean bias = 5.2, LoA = 51.4 ms). Precision was adjusted based on reference and the best signals were selected. The z-axis and resultant gyroscope signals, filtered at 3Hz are the most precise signals (0.056 and 0.063 s, respectively) to automatically detect turn switches during alpine skiing using this simple system.

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.

Floating car data (FCD) recorded with the Global Positioning System (GPS) are an important data source for traffic research. However, FCD are subject to error, which can relate either to the accuracy of the recordings (measurement error) or to the temporal rate at which the data are sampled (interpolation error). Both errors affect movement parameters derived from the FCD, such as speed or direction, and consequently influence conclusions drawn about the movement. In this paper we combined recent findings about the autocorrelation of GPS measurement error and well-established findings from random walk theory to analyse a set of real-world FCD. First, we showed that the measurement error in the FCD was affected by positive autocorrelation. We explained why this is a quality measure of the data. Second, we evaluated four metrics to assess the influence of interpolation error. We found that interpolation error strongly affects the correct interpretation of the car’s dynamics (speed, direction), whereas its impact on the path (travelled distance, spatial location) was moderate. Based on these results we gave recommendations for recording of FCD using the GPS. Our recommendations only concern time-based sampling, change-based, location-based or event-based sampling are not discussed. The sampling approach minimizes the effects of error on movement parameters while avoiding the collection of redundant information. This is crucial for obtaining reliable results from FCD.