@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} } @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{KoopmannStubbemannKapaetal.2021, author = {Koopmann, Tobias and Stubbemann, Maximilian and Kapa, Matthias and Paris, Michael and Buenstorf, Guido and Hanika, Tom and Hotho, Andreas and J{\"a}schke, Robert and Stumme, Gerd}, title = {Proximity dimensions and the emergence of collaboration: a HypTrails study on German AI research}, series = {Scientometrics}, volume = {126}, journal = {Scientometrics}, number = {12}, issn = {1588-2861}, doi = {10.1007/s11192-021-03922-1}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-269831}, pages = {9847-9868}, year = {2021}, abstract = {Creation and exchange of knowledge depends on collaboration. Recent work has suggested that the emergence of collaboration frequently relies on geographic proximity. However, being co-located tends to be associated with other dimensions of proximity, such as social ties or a shared organizational environment. To account for such factors, multiple dimensions of proximity have been proposed, including cognitive, institutional, organizational, social and geographical proximity. Since they strongly interrelate, disentangling these dimensions and their respective impact on collaboration is challenging. To address this issue, we propose various methods for measuring different dimensions of proximity. We then present an approach to compare and rank them with respect to the extent to which they indicate co-publications and co-inventions. We adapt the HypTrails approach, which was originally developed to explain human navigation, to co-author and co-inventor graphs. We evaluate this approach on a subset of the German research community, specifically academic authors and inventors active in research on artificial intelligence (AI). We find that social proximity and cognitive proximity are more important for the emergence of collaboration than geographic proximity.}, language = {en} } @article{SirbuBeckerCaminitietal.2015, author = {S{\^i}rbu, Alina and Becker, Martin and Caminiti, Saverio and De Baets, Bernard and Elen, Bart and Francis, Louise and Gravino, Pietro and Hotho, Andreas and Ingarra, Stefano and Loreto, Vittorio and Molino, Andrea and Mueller, Juergen and Peters, Jan and Ricchiuti, Ferdinando and Saracino, Fabio and Servedio, Vito D.P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca and Van den Bossche, Joris}, title = {Participatory Patterns in an International Air Quality Monitoring Initiative}, series = {PLoS ONE}, volume = {10}, journal = {PLoS ONE}, number = {8}, doi = {10.1371/journal. pone.0136763}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-151379}, pages = {e0136763}, year = {2015}, abstract = {The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.}, language = {en} } @article{DuekingHothoHolmbergetal.2016, author = {D{\"u}king, Peter and Hotho, Andreas and Holmberg, Hans-Christer and Fuss, Franz Konstantin and Sperlich, Billy}, title = {Comparison of Non-Invasive Individual Monitoring of the Training and Health of Athletes with Commercially Available Wearable Technologies}, series = {Frontiers in Physiology}, volume = {7}, journal = {Frontiers in Physiology}, number = {71}, doi = {10.3389/fphys.2016.00071}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-165516}, year = {2016}, abstract = {Athletes adapt their training daily to optimize performance, as well as avoid fatigue, overtraining and other undesirable effects on their health. To optimize training load, each athlete must take his/her own personal objective and subjective characteristics into consideration and an increasing number of wearable technologies (wearables) provide convenient monitoring of various parameters. Accordingly, it is important to help athletes decide which parameters are of primary interest and which wearables can monitor these parameters most effectively. Here, we discuss the wearable technologies available for non-invasive monitoring of various parameters concerning an athlete's training and health. On the basis of these considerations, we suggest directions for future development. Furthermore, we propose that a combination of several wearables is most effective for accessing all relevant parameters, disturbing the athlete as little as possible, and optimizing performance and promoting health.}, language = {en} }