Highly efficient training is a must in professional sports. Presently, this means doing exercises in high number and quality with some sort of data logging. In American football many things are logged, but there is no wearable sensor that logs a catch or a drop. Therefore, the goal of this paper was to develop and verify a sensor that is able to do exactly that. In a first step a sensor platform was used to gather nine degrees of freedom motion and audio data of both hands in 759 attempts to catch a pass. After preprocessing, the gathered data was used to train a neural network to classify all attempts, resulting in a classification accuracy of 93%. Additionally, the significance of each sensor signal was analysed. It turned out that the network relies most on acceleration and magnetometer data, neglecting most of the audio and gyroscope data. Besides the results, the paper introduces a new type of dataset and the possibility of autonomous training in American football to the research community.

This article focuses on the development of release velocity and spin prediction models for oval shaped footballs with a state-of-the-art passing machine. Since the trajectory of the ball can be predicted with aerodynamic models, the state of the ball at release time is of interest. At present, no prediction model for this initial state exists. This study measured release spin and velocity. A prediction model was developed based on various ball wear and measured release spin and velocity for different machine configurations. To sensor the motion, a high-speed camera with post image processing was used and release spin and velocity were calculated via regressions. The goal was to predict the release velocity within ±3% in 90% of all relevant cases, depending on the passing machine’s configuration. In addition, the dependency on the wear of the football was investigated. The results show that the release velocity can be predicted, independently of the wear of the ball, with the required accuracy for a reasonable range of machine configurations. For the release spin, a less accurate prediction model was developed. Both prediction models, their limitations and determination are presented in graphical form.

Data analysis plays an increasingly valuable role in sports. The better the data that is analysed, the more concise training methods that can be chosen. Several solutions already exist for this purpose in the tennis industry; however, none of them combine data generation with a wristband and classification with a deep convolutional neural network (CNN). In this article, we demonstrate the development of a reliable shot detection trigger and a deep neural network that classifies tennis shots into three and five shot types. We generate a dataset for the training of neural networks with the help of a sensor wristband, which recorded 11 signals, including an inertial measurement unit (IMU). The final dataset included 5682 labelled shots of 16 players of age 13–70 years, predominantly at an amateur level. Two state-of-the-art architectures for time series classification (TSC) are compared, namely a fully convolutional network (FCN) and a residual network (ResNet). Recent advances in the field of machine learning, like the Mish activation function and the Ranger optimizer, are utilized. Training with the rather inhomogeneous dataset led to an F1 score of 96% in classification of the main shots and 94% for the expansion. Consequently, the study yielded a solid base for more complex tennis analysis tools, such as the indication of success rates per shot type.

Most commercial cadence-measurement systems in road cycling are strictly limited in their function to the measurement of cadence. Other relevant signals, such as roll angle, inclination or a round kick evaluation, cannot be measured with them. This work proposes an alternative cadence-measurement system with less of the mentioned restrictions, without the need for distinct cadence-measurement apparatus attached to the pedal and shaft of the road bicycle. The proposed design applies an inertial measurement unit (IMU) to the seating pole of the bike. In an experiment, the motion data were gathered. A total of four different road cyclists participated in this study to collect different datasets for neural network training and evaluation. In total, over 10 h of road cycling data were recorded and used to train the neural network. The network’s aim was to detect each revolution of the crank within the data. The evaluation of the data has shown that using pure accelerometer data from all three axes led to the best result in combination with the proposed network architecture. A working proof of concept was achieved with an accuracy of approximately 95% on test data. As the proof of concept can also be seen as a new method for measuring cadence, the method was compared with the ground truth. Comparing the ground truth and the predicted cadence, it can be stated that for the relevant range of 50 rpm and above, the prediction over-predicts the cadence with approximately 0.9 rpm with a standard deviation of 2.05 rpm. The results indicate that the proposed design is fully functioning and can be seen as an alternative method to detect the cadence of a road cyclist.

In American football, high quality training focused on catching is currently not done with passing machines due to their poor pass accuracy and precision. From a coach’s point of view, accurate and precise passing machines are needed to relieve the quarterback from too much training effort. The two aims of this study were to increase the precision of a passing machine and develop an accurate pass prediction model for it. To meet the two aims and provide evidence that a passing machine can be precise and accurate enough for high quality training, an automated passing machine was developed and two experiments were carried out. The results of the first experiment showed that the machine performs with a precision within ±1% of the throwing distance for 218 of the 225 passes. The second experiment resulted in a pass prediction model, which is based on 55 videos and a fitting approach using a neural network. The model estimates the machine configuration for a pass to a targeted point in space. In regard to precision and accuracy, the performance of the machine exceeds the performance of a skilled quarterback. This project improves the state of the art of passing machines for American football and opens possibilities for research in various fields like motion analysis for catches, hand-eye coordination and performance analysis of athletes.