Wearable computing systems (Fig 1., left half) play an increasingly important role in recreational and elite sports. They comprise of two parts. First, sensors for physiological (ECG, EMG, ...) and biomechanical (accelerometer, gyroscope, ...) data recording are embedded into clothes and equipment. Second, embedded microprocessors (e.g. in smartphones) are used for monitoring and analysis of the recorded data. Together, these systems can provide real-time information and feedback for scientific studies in real sports situations. In order to implement these systems, several challenges have to be addressed. Our work focuses on four of the most prevalent of these: • Integration: sensors and microprocessors have to be embedded unobtrusively and have to record a variety of signals. • Communication: sensors and microprocessors have to communicate in body-area-networks in a secure, safe and energy-saving manner. • Interpretation: physiological and biomechanical data have to be interpreted using signal processing and machine learning methods. • Simulation and modeling: understanding of sensor data is needed to model processes in sports more accurately, simulation methodologies help here to provide basic information to drive those models. Data mining concepts provide tools for analyzing the considerable amount of physiological and biomechanical data that is generated in sports science studies. Especially when using wearable computing systems, the number of participants and variety of measured data is unlimited in general. Traditional statistical analysis methods commonly cannot handle this amount of data easily. Thus, the analysis is often restricted to individual variables rather than multidimensional dependencies and a considerable amount of information is neglected. Moreover, the results are frequently biased by the expectation of the researcher. Here, the objective, data-driven methods from data mining (Fig 1., right half) can contribute by offenng useful tools for the analysis tasks. These tools have the ability to deal with large data sets, to analyze multiple dimensions simultaneously, to work data-driven rather than hypothesis-driven, and to provide valuable insights into training effects and injury risks.
© Copyright 2016 Sportinformatik XI : Jahrestagung der dvs-Sektion Sportinformatik 2016 in Magdeburg. Veröffentlicht von Shaker Verlag. Alle Rechte vorbehalten.