Padraig Davidson, M.Sc.

Chair of Data Science (Informatik X)
University of Würzburg
Am Hubland
97074 Würzburg
Germany

Email: davidson <at> informatik.uni-wuerzburg.de

Phone: (+49 931) 31-89114

Office: Room B108 (Computer Science Building M2)

Projects and Research Interests

I received my 1. State Examination for the teaching profession at grammar schools (Computer Science and Physics) in 2016. Afterwards I graduated in 2018 with my Master's Degree in Computer Sciences. In May 2018 I started my PhD in machine learning at the Data Mining and Information Retrieval Group.

I'm currently working on the applications of machine learning in the we4bee project.

Teaching

Summer Term 2018:

Interactive Artificial Intelligence

Winter Term 2018/19:

Algorithms and Datastructures

Summer Term 2019:

Interactive Artificial Intelligence

Summer Term 2020:

Interactive Artificial Intelligence

Winter Term 2020/21:

Summer Term 2021:

Praktikum: Machine Learning for Time Series Analysis

Winter Term 2021/22:

Interactive Artificial Intelligence

Winter Term 2022/23:

Interactive Artificial Intelligence

Publications

2022[ to top ]

Davidson, P., Steininger, M., Huhn, A., Krause, A., Hotho, A. (2022) Semi-unsupervised Learning for Time Series Classification, Milets@KDD, available: https://doi.org/10.48550/ARXIV.2207.03119.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected data is rich in information, as one can detect accidents (e.g. cars) in real time, or assess injury/sickness over a given time span (e.g. health devices). Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually. Furthermore new classes within the data could emerge over time (contrary to e.g. handwritten digits), which would require relabeling the data. In this paper we present SuSL4TS, a deep generative Gaussian mixture model for semi-unsupervised learning, to classify time series data. With our approach we can alleviate manual labeling steps, since we can detect sparsely labeled classes (semi-supervised) and identify emerging classes hidden in the data (unsupervised). We demonstrate the efficacy of our approach with established time series classification datasets from different domains.

@article{davidson2022semiunsupervised, abstract = {Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected data is rich in information, as one can detect accidents (e.g. cars) in real time, or assess injury/sickness over a given time span (e.g. health devices). Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually. Furthermore new classes within the data could emerge over time (contrary to e.g. handwritten digits), which would require relabeling the data. In this paper we present SuSL4TS, a deep generative Gaussian mixture model for semi-unsupervised learning, to classify time series data. With our approach we can alleviate manual labeling steps, since we can detect sparsely labeled classes (semi-supervised) and identify emerging classes hidden in the data (unsupervised). We demonstrate the efficacy of our approach with established time series classification datasets from different domains.}, author = {Davidson, Padraig and Steininger, Michael and Huhn, André and Krause, Anna and Hotho, Andreas}, journal = {Milets@KDD}, keywords = {timeseries}, publisher = {arXiv}, title = {Semi-unsupervised Learning for Time Series Classification}, year = 2022 }
Davidson, P., Steininger, M., Lautenschlager, F., Krause, A., Hotho, A. (2022) Anomaly Detection in Beehives: An Algorithm Comparison, in Sensor Networks, Cham: Springer International Publishing, 1–20, available: https://link.springer.com/chapter/10.1007/978-3-031-17718-7_1.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@inproceedings{davidson2022anomaly, address = {Cham}, author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas}, booktitle = {Sensor Networks}, keywords = {we4bee}, pages = {1-20}, publisher = {Springer International Publishing}, title = {Anomaly Detection in Beehives: An Algorithm Comparison}, year = 2022 }

2021[ to top ]

Janetzky, P., Davidson, P., Steininger, M., Krause, A., Hotho, A. (2021) DETECTING PRESENCE OF SPEECH IN ACOUSTIC DATA OBTAINED FROM BEEHIVES, DCASE Workshop.
- [ BibTeX ]
- [ Download ]
@article{janetzkydetecting, author = {Janetzky, Pascal and Davidson, Padraig and Steininger, Michael and Krause, Anna and Hotho, Andreas}, journal = {DCASE Workshop}, keywords = {we4bee}, title = {DETECTING PRESENCE OF SPEECH IN ACOUSTIC DATA OBTAINED FROM BEEHIVES}, year = 2021 }
Davidson, P., Buckermann, F., Steininger, M., Krause, A., Hotho, A. (2021) Semi-unsupervised Learning: An In-depth Parameter Analysis, in Edelkamp, S., M{\"o}ller, R. and Rueckert, E., eds., KI 2021: Advances in Artificial Intelligence, Cham: Springer International Publishing, 51–66, available: https://link.springer.com/chapter/10.1007/978-3-030-87626-5_5.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm.

@inproceedings{10.1007/978-3-030-87626-5_5, abstract = {Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm.}, address = {Cham}, author = {Davidson, Padraig and Buckermann, Florian and Steininger, Michael and Krause, Anna and Hotho, Andreas}, booktitle = {KI 2021: Advances in Artificial Intelligence}, editor = {Edelkamp, Stefan and M{\"o}ller, Ralf and Rueckert, Elmar}, keywords = {susl}, pages = {51–66}, publisher = {Springer International Publishing}, title = {Semi-unsupervised Learning: An In-depth Parameter Analysis}, year = 2021 }
Steininger, M., Kobs, K., Davidson, P., Krause, A., Hotho, A. (2021) Density-based weighting for imbalanced regression, Machine Learning, available: https://doi.org/10.1007/s10994-021-06023-5.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
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 modeltraining 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.

@article{steininger2021densitybased, 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 modeltraining 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.}, author = {Steininger, Michael and Kobs, Konstantin and Davidson, Padraig and Krause, Anna and Hotho, Andreas}, editor = {Appice, Annalisa and Escalera, Sergio and Gamez, Jose A. and Trautmann, Heike}, journal = {Machine Learning}, keywords = {regression}, title = {Density-based weighting for imbalanced regression}, year = 2021 }

2020[ to top ]

Lautenschlager, F., Becker, M., Kobs, K., Steininger, M., Davidson, P., Krause, A., Hotho, A. (2020) OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning, Atmospheric Environment, 233, 117535, available: https://doi.org/https://doi.org/10.1016/j.atmosenv.2020.117535.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.

@article{lautenschlager2020openlur, abstract = {To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.}, author = {Lautenschlager, Florian and Becker, Martin and Kobs, Konstantin and Steininger, Michael and Davidson, Padraig and Krause, Anna and Hotho, Andreas}, journal = {Atmospheric Environment}, keywords = {myown}, pages = 117535, title = {OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning}, volume = 233, year = 2020 }
Davidson, P., Düking, P., Zinner, C., Sperlich, B., Hotho, A. (2020) Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study, Sensors, available: https://doi.org/10.3390/s20092637.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{davidson2020smartwatchderived, author = {Davidson, Padraig and Düking, Peter and Zinner, Christoph and Sperlich, Billy and Hotho, Andreas}, journal = {Sensors}, keywords = {timeseries-analysis}, month = {may}, title = {Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study}, year = 2020 }
Davidson, P., Steininger, M., Lautenschlager, F., Kobs, K., Krause, A., Hotho, A. (2020) Anomaly Detection in Beehives using Deep Recurrent Autoencoders, in Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020), SCITEPRESS – Science and Technology Publications, Lda., 142–149.
- [ BibTeX ]
- [ Download ]
@inproceedings{davidson2020anomaly, author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Kobs, Konstantin and Krause, Anna and Hotho, Andreas}, booktitle = {Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020)}, keywords = {we4bee}, number = 9, pages = {142-149}, publisher = {SCITEPRESS – Science and Technology Publications, Lda.}, title = {Anomaly Detection in Beehives using Deep Recurrent Autoencoders}, year = 2020 }

Other scientific activities

PC Member ECML/PKDD 2021 and 2022
Subreviewer for several conferences and journals

Projects and Research Interests

Teaching

Publications

Other scientific activities

Data privacy protection

Data privacy protection

Picture credits