@article{DavidsonDuekingZinneretal.2020,
  author    = {Davidson, Padraig and D{\"u}king, Peter and Zinner, Christoph and Sperlich, Billy and Hotho, Andreas},
  title     = {Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study},
  series = {Sensors},
  volume    = {20},
  journal   = {Sensors},
  number    = {9},
  issn      = {1424-8220},
  doi       = {10.3390/s20092637},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205686},
  year      = {2020},
  abstract  = {The rating of perceived exertion (RPE) is a subjective load marker and may assist in individualizing training prescription, particularly by adjusting running intensity. Unfortunately, RPE has shortcomings (e.g., underreporting) and cannot be monitored continuously and automatically throughout a training sessions. In this pilot study, we aimed to predict two classes of RPE (≤15 "Somewhat hard to hard" on Borg's 6-20 scale vs. RPE >15 in runners by analyzing data recorded by a commercially-available smartwatch with machine learning algorithms. Twelve trained and untrained runners performed long-continuous runs at a constant self-selected pace to volitional exhaustion. Untrained runners reported their RPE each kilometer, whereas trained runners reported every five kilometers. The kinetics of heart rate, step cadence, and running velocity were recorded continuously ( 1 Hz ) with a commercially-available smartwatch (Polar V800). We trained different machine learning algorithms to estimate the two classes of RPE based on the time series sensor data derived from the smartwatch. Predictions were analyzed in different settings: accuracy overall and per runner type; i.e., accuracy for trained and untrained runners independently. We achieved top accuracies of 84.8 \% for the whole dataset, 81.8 \% for the trained runners, and 86.1 \% for the untrained runners. We predict two classes of RPE with high accuracy using machine learning and smartwatch data. This approach might aid in individualizing training prescriptions.},
  language  = {en}
}
@article{SteiningerKobsDavidsonetal.2021,
  author    = {Steininger, Michael and Kobs, Konstantin and Davidson, Padraig and Krause, Anna and Hotho, Andreas},
  title     = {Density-based weighting for imbalanced regression},
  series = {Machine Learning},
  volume    = {110},
  journal   = {Machine Learning},
  number    = {8},
  issn      = {1573-0565},
  doi       = {10.1007/s10994-021-06023-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-269177},
  pages     = {2187-2211},
  year      = {2021},
  abstract  = {In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point's influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.},
  language  = {en}
}