Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning

Abstract

In human activity recognition har(human activity recognition (HAR)), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be applied to marginal sports, where available data are sparse and costly to acquire. Thus, we recorded and annotated inertial measurement unit (IMU) data containing different types of Ultimate Frisbee throws to investigate whether Convolutional Neural Network (CNNs) and transfer learning can solve this. The relevant actions were automatically detected and were classified using a CNN. The proposed pipeline reaches an accuracy of 66.6%, distinguishing between nine different fine-grained classes. For the classification of the three basic throwing techniques, we achieve an accuracy of 89.9%. Furthermore, the results were compared to a transfer learning-based approach using a beach volleyball dataset as the source. Even if transfer learning could not improve the classification accuracy, the training time was significantly reduced. Finally, the effect of transfer learning on a reduced dataset, i.e., without data augmentations, is analyzed. While having the same number of training subjects, using the pre-trained weights improves the generalization capabilities of the network, i.e., increasing the accuracy and F1 score. This shows that transfer learning can be beneficial, especially when dealing with small datasets, as in marginal sports, and therefore, can improve the tracking of marginal sports.

Leakage Prediction in Machine Learning Models When Using Data from Sports Wearable Sensors

“…The dataset comprises three-dimensional acceleration data from joint actions of beach volleyball athletes, each of whom was fitted with an accelerometer worn on the wrist and sampled at 39 Hz. The signal was recorded at 14 bits per axis and then compressed to 16 g. The x , y , and z axes relate to the athletes' spatial arrangement, which is recorded in an independent coordinate system based on the sensor configuration, as there was no transfer to real-world coordinates [ 45 , 46 ]. The 30 athletes recorded ranged in expertise from novice to professional volleyball players.…”

Convolutional Neural Network Classification of Exhaled Aerosol Images for Diagnosis of Obstructive Respiratory Diseases

“…[22][23][24]. However, CNN-based transfer learning sometimes does not perform as expected, giving unexpectedly lower prediction accuracy in the testing stage despite a high accuracy rate in the training and validation stages [25]. For a given medical image dataset, which usually has a limited number of images and small image differences, overfitting is a common problem using the popular CNN models, which often have over 10 layers with 60+ million trained parameters and have been trained on a large dataset (imageJ) containing 1000 categories.…”

xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning

“…In future work, we will investigate if methods from the area of out-of-distribution generalization can further improve the algorithm’s precision to unseen venues and athletes [ 45 ]. Other possibilities include using transfer learning to utilize IMU data from other application areas, where data are more readily available, as completed in earlier work [ 46 ].…”