Machine Learning for Ecosystems and Climate Modeling

ConvMOS: climate model output statistics with deep learning. Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas. In Data Mining and Knowledge Discovery, 37(1), pp. 136–166. 2023.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

@article{steininger2023convmos,
  abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.},
  author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas},
  journal = {Data Mining and Knowledge Discovery},
  keywords = {author:KRAUSE},
  number = 1,
  pages = {136–166},
  title = {ConvMOS: climate model output statistics with deep learning},
  volume = 37,
  year = 2023
}

DynaBench: A Benchmark Dataset for Learning Dynamical Systems from Low-Resolution Data. Dulny, Andrzej; Hotho, Andreas; Krause, Anna. In Machine Learning and Knowledge Discovery in Databases: Research Track, D. Koutra, C. Plant, M. Gomez Rodriguez, E. Baralis, F. Bonchi (eds.), pp. 438–455. Springer Nature Switzerland, Cham, 2023.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ Download ]

Previous work on learning physical systems from data has focused on high-resolution grid-structured measurements. However, real-world knowledge of such systems (e.g. weather data) relies on sparsely scattered measuring stations. In this paper, we introduce a novel simulated benchmark dataset, DynaBench, for learning dynamical systems directly from sparsely scattered data without prior knowledge of the equations. The dataset focuses on predicting the evolution of a dynamical system from low-resolution, unstructured measurements. We simulate six different partial differential equations covering a variety of physical systems commonly used in the literature and evaluate several machine learning models, including traditional graph neural networks and point cloud processing models, with the task of predicting the evolution of the system. The proposed benchmark dataset is expected to advance the state of art as an out-of-the-box easy-to-use tool for evaluating models in a setting where only unstructured low-resolution observations are available. The benchmark is available at https://professor-x.de/dynabench.

@inproceedings{10.1007/978-3-031-43412-9_26,
  abstract = {Previous work on learning physical systems from data has focused on high-resolution grid-structured measurements. However, real-world knowledge of such systems (e.g. weather data) relies on sparsely scattered measuring stations. In this paper, we introduce a novel simulated benchmark dataset, DynaBench, for learning dynamical systems directly from sparsely scattered data without prior knowledge of the equations. The dataset focuses on predicting the evolution of a dynamical system from low-resolution, unstructured measurements. We simulate six different partial differential equations covering a variety of physical systems commonly used in the literature and evaluate several machine learning models, including traditional graph neural networks and point cloud processing models, with the task of predicting the evolution of the system. The proposed benchmark dataset is expected to advance the state of art as an out-of-the-box easy-to-use tool for evaluating models in a setting where only unstructured low-resolution observations are available. The benchmark is available at https://professor-x.de/dynabench.},
  address = {Cham},
  author = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna},
  booktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track},
  editor = {Koutra, Danai and Plant, Claudia and Gomez Rodriguez, Manuel and Baralis, Elena and Bonchi, Francesco},
  keywords = {selected},
  pages = {438–455},
  publisher = {Springer Nature Switzerland},
  title = {DynaBench: A Benchmark Dataset for Learning Dynamical Systems from Low-Resolution Data},
  year = 2023
}

Swarming Detection in Smart Beehives Using Auto Encoders for Audio Data. Janetzky, Pascal; Schaller, Melanie; Krause, Anna; Hotho, Andreas. In 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 1–5. 2023.

[ Abstract ]
[ BibTeX ]
[ DOI ]
[ Download ]

—Swarming is the natural mechanism by which bee colonies reproduce, but for beekeepers it is a challenge. Precision beekeeping can aid their work through early notifications about impending swarms. In this work, we focus on identifying swarms and their early indicators in audio data captured from a smart beehive. The challenge with such domain-specific data is the low availability of labelled samples, the strong label imbalance, and the recording of undesired sources. We approach this challenge through a two-step setup: First, we use an auto encoder network to detect sounds from mechanical sources and then use it to clean data. Secondly, on the cleaned data we then employ a second network to identify event-related bee sounds. Using spectrogram features, our networks are able to reach a balanced accuracy score of more than 99 % in the detection of special bee events. The findings of this initial study can serve as the starting point for further research on handling imbalanced data collections from smart, remote sensor environments that also contain undesired signals.

@inproceedings{10180253,
  abstract = {—Swarming is the natural mechanism by which bee colonies reproduce, but for beekeepers it is a challenge. Precision beekeeping can aid their work through early notifications about impending swarms. In this work, we focus on identifying swarms and their early indicators in audio data captured from a smart beehive. The challenge with such domain-specific data is the low availability of labelled samples, the strong label imbalance, and the recording of undesired sources. We approach this challenge through a two-step setup: First, we use an auto encoder network to detect sounds from mechanical sources and then use it to clean data. Secondly, on the cleaned data we then employ a second network to identify event-related bee sounds. Using spectrogram features, our networks are able to reach a balanced accuracy score of more than 99 % in the detection of special bee events. The findings of this initial study can serve as the starting point for further research on handling imbalanced data collections from smart, remote sensor environments that also contain undesired signals.},
  author = {Janetzky, Pascal and Schaller, Melanie and Krause, Anna and Hotho, Andreas},
  booktitle = {2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)},
  keywords = {author:KRAUSE},
  pages = {1-5},
  title = {Swarming Detection in Smart Beehives Using Auto Encoders for Audio Data},
  year = 2023
}

Automatic Speech Detection on a Smart Beehive’s Raspberry Pi. Janetzky, Pascal; Lissmann, Philipp; Hotho, Andreas; Krause, Anna. In LWDA 2023 - Learning, Knowledge, Data, and Analysis. 2023.

[ BibTeX ]
[ Download ]

@inproceedings{janetzky2023automatic,
  author = {Janetzky, Pascal and Lissmann, Philipp and Hotho, Andreas and Krause, Anna},
  booktitle = {LWDA 2023 - Learning, Knowledge, Data, and Analysis},
  keywords = {author:LISSMANN},
  title = {Automatic Speech Detection on a Smart Beehive's Raspberry Pi},
  year = 2023
}

ConvMOS: Climate Model Output Statistics with Deep Learning. Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas. In Data Mining and Knowledge Discovery, P. Cellier; K. Dembczynski; A. Zimmermann; E. Devijver (eds.). Springer, 2022.

[ Abstract ]
[ BibTeX ]
[ DOI ]
[ Download ]

Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

@article{steininger2022convmos,
  abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.},
  author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas},
  editor = {Cellier, Peggy and Dembczynski, Krzysztof and Zimmermann, Albrecht and Devijver, Emilie},
  journal = {Data Mining and Knowledge Discovery},
  keywords = {from:msteininger},
  month = 10,
  publisher = {Springer},
  title = {ConvMOS: Climate Model Output Statistics with Deep Learning},
  year = 2022
}

A sensor-driven approach for analyzing a beehive’s state. Davidson, Padraig; Hotho, Andreas; Krause, Anna. 2022.

[ Abstract ]
[ BibTeX ]
[ URL ]

Assessing a colony’s state is one of the key components in apiculture. In recent years precision apiculture has emerged as a field of study to quantify the analysis of beehives with objective sensors (e.g. temperature within the beehive). One objective of analysis is the study of semantically consecutive time spans, sometimes covering several months. A common task for example could be detecting the different breeding periods in a year. A change in semantics is called a change point, which can be detected by rule-based knowledge (for example from the beekeeper), or an automated procedure called change point detection (CPD). Detecting the onset of succinct periods enables the beekeeper to provide specific care for each period. Within these longer time spans, short term events can occur, mostly specific to the semantic context. For example swarming can only occur in the summer breed rearing period. On the other hand, the death of a colony is more likely to happen during the winter seasons. These events are also known as anomalies, as they deviate from the expected normal behavior during that time span. Like for CPD, anomalies can be detected via certain rules, or automatically detected using an anomaly detection algorithm. In this study we investigate the use of machine learning algorithms to analyze a beehive’s state. With the data from multiple precision apiculture projects (BeeConnected, we4bee, HOBOS), we evaluate different algorithms to this end. This also enables us to not only study behavior at different locations but also with different sensor setups. We study the usage of single and multiple temperature sensors, but also integrate a scale for our purposes, and evaluate which combination of sensors yields the best results from an algorithmic standpoint. Besides quality of detection, we can also assess the applicability of specific sensors for beekeepers, keeping ease of use in mind. We hope our studies support beekeepers to gain new insight into their colonies for a better understanding. This also creates a feedback loop with the algorithms to improve prediction quality in the future.

@presentation{davidson2022sensordriven,
  abstract = {Assessing a colony’s state is one of the key components in apiculture. In recent years precision apiculture has emerged as a field of study to quantify the analysis of beehives with objective sensors (e.g. temperature within the beehive). One objective of analysis is the study of semantically consecutive time spans, sometimes covering several months. A common task for example could be detecting the different breeding periods in a year. A change in semantics is called a change point, which can be detected by rule-based knowledge (for example from the beekeeper), or an automated procedure called change point detection (CPD). Detecting the onset of succinct periods enables the beekeeper to provide specific care for each period. Within these longer time spans, short term events can occur, mostly specific to the semantic context. For example swarming can only occur in the summer breed rearing period. On the other hand, the death of a colony is more likely to happen during the winter seasons. These events are also known as anomalies, as they deviate from the expected normal behavior during that time span. Like for CPD, anomalies can be detected via certain rules, or automatically detected using an anomaly detection algorithm. In this study we investigate the use of machine learning algorithms to analyze a beehive’s state. With the data from multiple precision apiculture projects (BeeConnected, we4bee, HOBOS), we evaluate different algorithms to this end. This also enables us to not only study behavior at different locations but also with different sensor setups. We study the usage of single and multiple temperature sensors, but also integrate a scale for our purposes, and evaluate which combination of sensors yields the best results from an algorithmic standpoint. Besides quality of detection, we can also assess the applicability of specific sensors for beekeepers, keeping ease of use in mind. We hope our studies support beekeepers to gain new insight into their colonies for a better understanding. This also creates a feedback loop with the algorithms to improve prediction quality in the future.},
  author = {Davidson, Padraig and Hotho, Andreas and Krause, Anna},
  keywords = {bee_connected},
  title = {A sensor-driven approach for analyzing a beehive’s state},
  year = 2022
}

Evaluating the multi-task learning approach for land use regression modelling of air pollution. Dulny, Andrzej; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas. In Journal of Physics: Conference Series, 1834(1), p. 012004. {IOP} Publishing, 2021.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.

@article{dulny2021evaluating,
  abstract = {Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.},
  author = {Dulny, Andrzej and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas},
  journal = {Journal of Physics: Conference Series},
  keywords = {from:msteininger},
  month = {03},
  number = 1,
  organization = {IOP Publishing},
  pages = {012004},
  publisher = {{IOP} Publishing},
  title = {Evaluating the multi-task learning approach for land use regression modelling of air pollution},
  volume = 1834,
  year = 2021
}

Anomaly Detection in Beehives: An Algorithm Comparison. Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas. In International Conference on Sensor Networks, Vol. 1674 of Communications in Computer and Information Science, A. Ahrens, R. Prasad, C. Benavente-Peces, N. Ansari (eds.), pp. 1–20. Springer, 2021.

[ BibTeX ]
[ DOI ]
[ Download ]

@inproceedings{davidson2021anomaly,
  author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas},
  booktitle = {International Conference on Sensor Networks},
  editor = {Ahrens, A. and Prasad, R.V. and Benavente-Peces, C. and Ansari, N.},
  keywords = {author:hotho},
  pages = {1–20},
  publisher = {Springer},
  series = {Communications in Computer and Information Science},
  title = {Anomaly Detection in Beehives: An Algorithm Comparison},
  volume = 1674,
  year = 2021
}

NeuralPDE: Modelling Dynamical Systems from Data. Dulny, Andrzej; Hotho, Andreas; Krause, Anna. 2021.

[ Abstract ]
[ BibTeX ]
[ URL ]

Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an emerging research field. However, current methods are restricted in various ways: they require prior knowledge about the governing equations, and are limited to linear or first-order equations. In this work we propose NeuralPDE, a model which combines convolutional neural networks (CNNs) with differentiable ODE solvers to model dynamical systems. We show that the Method of Lines used in standard PDE solvers can be represented using convolutions which makes CNNs the natural choice to parametrize arbitrary PDE dynamics. Our model can be applied to any data without requiring any prior knowledge about the governing PDE. We evaluate NeuralPDE on datasets generated by solving a wide variety of PDEs, covering higher orders, non-linear equations and multiple spatial dimensions.

@misc{dulny2021neuralpde,
  abstract = {Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an emerging research field. However, current methods are restricted in various ways: they require prior knowledge about the governing equations, and are limited to linear or first-order equations. In this work we propose NeuralPDE, a model which combines convolutional neural networks (CNNs) with differentiable ODE solvers to model dynamical systems. We show that the Method of Lines used in standard PDE solvers can be represented using convolutions which makes CNNs the natural choice to parametrize arbitrary PDE dynamics. Our model can be applied to any data without requiring any prior knowledge about the governing PDE. We evaluate NeuralPDE on datasets generated by solving a wide variety of PDEs, covering higher orders, non-linear equations and multiple spatial dimensions.},
  author = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna},
  keywords = {from:hotho},
  note = {cite arxiv:2111.07671},
  title = {NeuralPDE: Modelling Dynamical Systems from Data},
  year = 2021
}

Detecting Presence Of Speech In Acoustic Data Obtained From Beehives. Janetzky, Pascal; Davidson, Padraig; Steininger, Michael; Krause, Anna; Hotho, Andreas. In DCASE Workshop. 2021.

[ BibTeX ]
[ Download ]

@article{janetzkydetecting,
  author = {Janetzky, Pascal and Davidson, Padraig and Steininger, Michael and Krause, Anna and Hotho, Andreas},
  journal = {DCASE Workshop},
  keywords = {from:msteininger},
  title = {Detecting Presence Of Speech In Acoustic Data Obtained From Beehives},
  year = 2021
}

Semi-Supervised Learning for Grain Size Distribution Interpolation. Kobs, Konstantin; Schäfer, Christian; Steininger, Michael; Krause, Anna; Baumhauer, Roland; Paeth, Heiko; Hotho, Andreas. In Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10--15, 2021, Proceedings, Part VI, pp. 34–44. Springer International Publishing, 2021.

[ BibTeX ]
[ Download ]

@inproceedings{kobs2021semi,
  author = {Kobs, Konstantin and Schäfer, Christian and Steininger, Michael and Krause, Anna and Baumhauer, Roland and Paeth, Heiko and Hotho, Andreas},
  booktitle = {Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021, Proceedings, Part VI},
  keywords = {author:KRAUSE},
  organization = {Springer International Publishing},
  pages = {34–44},
  title = {Semi-Supervised Learning for Grain Size Distribution Interpolation},
  year = 2021
}

Density-based weighting for imbalanced regression. Steininger, Michael; Kobs, Konstantin; Davidson, Padraig; Krause, Anna; Hotho, Andreas. In Machine Learning, A. Appice; S. Escalera; J. A. Gamez; H. Trautmann (eds.). 2021.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

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 = {selected},
  title = {Density-based weighting for imbalanced regression},
  year = 2021
}

OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning. Lautenschlager, Florian; Becker, Martin; Kobs, Konstantin; Steininger, Michael; Davidson, Padraig; Krause, Anna; Hotho, Andreas. In Atmospheric Environment, 233, p. 117535. 2020.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ 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 = {pollution},
  month = {07},
  pages = 117535,
  title = {OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning},
  volume = 233,
  year = 2020
}

MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images. Steininger, Michael; Kobs, Konstantin; Zehe, Albin; Lautenschlager, Florian; Becker, Martin; Hotho, Andreas. In ACM Trans. Spatial Algorithms Syst., 6(3). Association for Computing Machinery, New York, NY, USA, 2020.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. In order to illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.

@article{10.1145/3380973,
  abstract = {Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. In order to illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.},
  address = {New York, NY, USA},
  author = {Steininger, Michael and Kobs, Konstantin and Zehe, Albin and Lautenschlager, Florian and Becker, Martin and Hotho, Andreas},
  journal = {ACM Trans. Spatial Algorithms Syst.},
  keywords = {pollution},
  month = {04},
  number = 3,
  publisher = {Association for Computing Machinery},
  title = {MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images},
  volume = 6,
  year = 2020
}

Evaluating the multi-task learning approach for land use regression modelling of air pollution. Dulny, Andrzej; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas. In International Conference on Frontiers of Artificial Intelligence and Machine Learning. IASED, 2020.

[ Abstract ]
[ BibTeX ]
[ Download ]

Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.

@inproceedings{dulny2020evaluating,
  abstract = {Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.},
  author = {Dulny, Andrzej and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas},
  booktitle = {International Conference on Frontiers of Artificial Intelligence and Machine Learning},
  keywords = {from:msteininger},
  organization = {IASED},
  title = {Evaluating the multi-task learning approach for land use regression modelling of air pollution},
  year = 2020
}

Deep Learning for Climate Model Output Statistics. Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas. In Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020. 2020.

[ BibTeX ]
[ URL ]
[ Download ]

@article{steininger2020deep,
  author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas},
  journal = {Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020},
  keywords = {from:msteininger},
  title = {Deep Learning for Climate Model Output Statistics},
  year = 2020
}

Anomaly Detection in Beehives using Deep Recurrent Autoencoders. Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Kobs, Konstantin; Krause, Anna; Hotho, Andreas. In Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020), pp. 142–149. SCITEPRESS – Science and Technology Publications, Lda., 2020.

[ 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 = {author:hotho},
  number = 9,
  pages = {142-149},
  publisher = {SCITEPRESS – Science and Technology Publications, Lda.},
  title = {Anomaly Detection in Beehives using Deep Recurrent Autoencoders},
  year = 2020
}

EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data. Lautenschlager, Florian; Becker, Martin; Steininger, Michael; Hotho, Andreas. In Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018, D. Burghardt, S. Chen, G. Andrienko, N. Andrienko, R. Purves, A. Diehl (eds.). KOPS, 2018.

[ BibTeX ]
[ Download ]

@inproceedings{lautenschlager2018everyaware,
  author = {Lautenschlager, Florian and Becker, Martin and Steininger, Michael and Hotho, Andreas},
  booktitle = {Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018},
  editor = {Burghardt, Dirk and Chen, Siming and Andrienko, Gennady and Andrienko, Nathalia and Purves, Ross and Diehl, Alexandra},
  keywords = {p2map2:antrag:own},
  month = 10,
  publisher = {KOPS},
  title = {EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data},
  year = 2018
}

Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data. Kibanov, Mark; Becker, Martin; Müller, Juergen; Atzmüller, Martin; Hotho, Andreas; Stumme, Gerd. In Proceedings of the 33rd Annual ACM Symposium on Applied Computing, of SAC ’18, pp. 857–865. ACM, Pau, France, 2018.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.

@inproceedings{kibanov2018adaptive,
  abstract = {The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.},
  address = {New York, NY, USA},
  author = {Kibanov, Mark and Becker, Martin and Müller, Juergen and Atzmüller, Martin and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 33rd Annual ACM Symposium on Applied Computing},
  keywords = {kassel},
  pages = {857–865},
  publisher = {ACM},
  series = {SAC '18},
  title = {Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data},
  year = 2018
}

Air Trails -- Urban Air Quality Campaign Exploration Patterns. Becker, Martin; Lautenschlager, Florian; Hotho, Andreas. 2018.

[ BibTeX ]
[ Download ]

@article{becker2018air,
  author = {Becker, Martin and Lautenschlager, Florian and Hotho, Andreas},
  keywords = {human},
  title = {Air Trails – Urban Air Quality Campaign Exploration Patterns},
  year = 2018
}

Participatory sensing, opinions and collective awareness. Loreto, Vittorio; Haklay, Mordechai; Hotho, Andreas; Servedio, Vito C. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca. Springer, 2017.

[ BibTeX ]
[ Download ]

@book{loreto2017participatory,
  editor = {Loreto, Vittorio and Haklay, Mordechai and Hotho, Andreas and Servedio, Vito C. P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca},
  keywords = {participatory},
  publisher = {Springer},
  title = {Participatory sensing, opinions and collective awareness},
  year = 2017
}

Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson. Gravino, Pietro; S{\^\i}rbu, Alina; Becker, Martin; Servedio, Vito DP; Loreto, Vittorio. In Participatory Sensing, Opinions and Collective Awareness, pp. 337–362. Springer, 2017.

[ BibTeX ]
[ Download ]

@incollection{gravino2017experimental,
  author = {Gravino, Pietro and S{\^\i}rbu, Alina and Becker, Martin and Servedio, Vito DP and Loreto, Vittorio},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  keywords = {everyaware},
  pages = {337–362},
  publisher = {Springer},
  title = {Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson},
  year = 2017
}

Collective Sensing Platforms. Atzmueller, Martin; Becker, Martin; Mueller, Juergen. In Participatory Sensing, Opinions and Collective Awareness, pp. 115–133. Springer, 2017.

[ BibTeX ]
[ Download ]

@incollection{atzmueller2017collective,
  author = {Atzmueller, Martin and Becker, Martin and Mueller, Juergen},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  keywords = {everyaware},
  pages = {115–133},
  publisher = {Springer},
  title = {Collective Sensing Platforms},
  year = 2017
}

Applications for Environmental Sensing in EveryAware. Atzmueller, Martin; Becker, Martin; Molino, Andrea; Mueller, Juergen; Peters, Jan; S{\^\i}rbu, Alina. In Participatory Sensing, Opinions and Collective Awareness, pp. 135–155. Springer, 2017.

[ BibTeX ]
[ Download ]

@incollection{atzmueller2017applications,
  author = {Atzmueller, Martin and Becker, Martin and Molino, Andrea and Mueller, Juergen and Peters, Jan and S{\^\i}rbu, Alina},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  keywords = {participatory},
  pages = {135–155},
  publisher = {Springer},
  title = {Applications for Environmental Sensing in EveryAware},
  year = 2017
}

Participatory Patterns in an International Air Quality Monitoring Initiative. Sîrbu, Alina; Becker, Martin; Caminiti, Saverio; De Baets, Bernard; Elen, Bart; Francis, Louise; Gravino, Pietro; Hotho, Andreas; Ingarra, Stefano; Loreto, Vittorio; Molino, Andrea; Mueller, Juergen; Peters, Jan; Ricchiuti, Ferdinando; Saracino, Fabio; Servedio, Vito D. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca; Van den Bossche, Joris. In PLoS ONE, 10(8), p. e0136763. Public Library of Science, 2015.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

<p>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.</p>

@article{10.1371/journal.pone.0136763,
  abstract = {<p>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.</p>},
  author = {Sîrbu, 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},
  journal = {PLoS ONE},
  keywords = {pollution},
  month = {08},
  number = 8,
  pages = {e0136763},
  publisher = {Public Library of Science},
  title = {Participatory Patterns in an International Air Quality Monitoring Initiative},
  volume = 10,
  year = 2015
}

Subjective vs. Objective Data: Bridging the Gap. Becker, Martin; Hotho, Andreas; Mueller, Juergen; Kibanov, Mark; Atzmueller, Martin; Stumme, Gerd. 2014.

[ Abstract ]
[ BibTeX ]
[ URL ]

Sensor data is objective. But when measuring our environment, measured values are contrasted with our perception, which is always subjective. This makes interpreting sensor measurements difficult for a single person in her personal environment. In this context, the EveryAware projects directly connects the concepts of objective sensor data with subjective impressions and perceptions by providing a collective sensing platform with several client applications allowing to explicitly associate those two data types. The goal is to provide the user with personalized feedback, a characterization of the global as well as her personal environment, and enable her to position her perceptions in this global context. In this poster we summarize the collected data of two EveryAware applications, namely WideNoise for noise measurements and AirProbe for participatory air quality sensing. Basic insights are presented including user activity, learning processes and sensor data to perception correlations. These results provide an outlook on how this data can further be used to understand the connection between sensor data and perceptions.

@misc{becker2014subjective,
  abstract = {Sensor data is objective. But when measuring our environment, measured values are contrasted with our perception, which is always subjective. This makes interpreting sensor measurements difficult for a single person in her personal environment. In this context, the EveryAware projects directly connects the concepts of objective sensor data with subjective impressions and perceptions by providing a collective sensing platform with several client applications allowing to explicitly associate those two data types. The goal is to provide the user with personalized feedback, a characterization of the global as well as her personal environment, and enable her to position her perceptions in this global context. In this poster we summarize the collected data of two EveryAware applications, namely WideNoise for noise measurements and AirProbe for participatory air quality sensing. Basic insights are presented including user activity, learning processes and sensor data to perception correlations. These results provide an outlook on how this data can further be used to understand the connection between sensor data and perceptions.},
  author = {Becker, Martin and Hotho, Andreas and Mueller, Juergen and Kibanov, Mark and Atzmueller, Martin and Stumme, Gerd},
  howpublished = {CSSWS 2014, Poster},
  keywords = {from:hotho},
  title = {Subjective vs. Objective Data: Bridging the Gap},
  year = 2014
}

Awareness and Learning in Participatory Noise Sensing. Becker, Martin; Caminiti, Saverio; Fiorella, Donato; Francis, Louise; Gravino, Pietro; Haklay, Mordechai (Muki); Hotho, Andreas; Loreto, Vittorio; Mueller, Juergen; Ricchiuti, Ferdinando; Servedio, Vito D. P.; Sîrbu, Alina; Tria, Francesca. In PLoS ONE, 8(12), p. e81638. Public Library of Science, 2013.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ DOI ]
[ Download ]

<p>The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments.</p>

@article{10.1371/journal.pone.0081638,
  abstract = {<p>The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments.</p>},
  author = {Becker, Martin and Caminiti, Saverio and Fiorella, Donato and Francis, Louise and Gravino, Pietro and Haklay, Mordechai (Muki) and Hotho, Andreas and Loreto, Vittorio and Mueller, Juergen and Ricchiuti, Ferdinando and Servedio, Vito D. P. and Sîrbu, Alina and Tria, Francesca},
  journal = {PLoS ONE},
  keywords = {from:hotho},
  month = 12,
  number = 12,
  pages = {e81638},
  publisher = {Public Library of Science},
  title = {Awareness and Learning in Participatory Noise Sensing},
  volume = 8,
  year = 2013
}

Tag Recommendations for SensorFolkSonomies. Mueller, Juergen; Doerfel, Stephan; Becker, Martin; Hotho, Andreas; Stumme, Gerd. In Recommender Systems and the Social Web Workshop at 7th ACM Conference on Recommender Systems, RecSys 2013, Hong Kong, China -- October 12-16, 2013. Proceedings, Vol. 1066. CEUR-WS, Aachen, Germany, 2013.

[ Abstract ]
[ BibTeX ]
[ URL ]
[ Download ]

With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.

@inproceedings{mueller2013recommendations,
  abstract = {With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.},
  address = {Aachen, Germany},
  author = {Mueller, Juergen and Doerfel, Stephan and Becker, Martin and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Recommender Systems and the Social Web Workshop at 7th ACM Conference on Recommender Systems, RecSys 2013, Hong Kong, China – October 12-16, 2013. Proceedings},
  keywords = {from:hotho},
  publisher = {CEUR-WS},
  title = {Tag Recommendations for SensorFolkSonomies},
  volume = 1066,
  year = 2013
}

A Generic Platform for Ubiquitous and Subjective Data. Becker, Martin; Mueller, Juergen; Hotho, Andreas; Stumme, Gerd. In 1st International Workshop on Pervasive Urban Crowdsensing Architecture and Applications, PUCAA 2013, Zurich, Switzerland -- September 9, 2013. Proceedings, p. New York, NY, USA. ACM, 2013.

[ Abstract ]
[ BibTeX ]
[ Download ]

An increasing number of platforms like Xively or ThingSpeak are available to manage ubiquitous sensor data enabling the Internet of Things. Strict data formats allow interoperability and informative visualizations, supporting the development of custom user applications. Yet, these strict data formats as well as the common feed-centric approach limit the flexibility of these platforms. We aim at providing a concept that supports data ranging from text-based formats like JSON to images and video footage. Furthermore, we introduce the concept of extensions, which allows to enrich existing data points with additional information, thus, taking a data point centric approach. This enables us to gain semantic and user specific context by attaching subjective data to objective values. This paper provides an overview of our architecture including concept, implementation details and present applications. We distinguish our approach from several other systems and describe two sensing applications namely AirProbe and WideNoise that were implemented for our platform.

@inproceedings{mueller-2013a,
  abstract = {An increasing number of platforms like Xively or ThingSpeak are available to manage ubiquitous sensor data enabling the Internet of Things. Strict data formats allow interoperability and informative visualizations, supporting the development of custom user applications. Yet, these strict data formats as well as the common feed-centric approach limit the flexibility of these platforms. We aim at providing a concept that supports data ranging from text-based formats like JSON to images and video footage. Furthermore, we introduce the concept of extensions, which allows to enrich existing data points with additional information, thus, taking a data point centric approach. This enables us to gain semantic and user specific context by attaching subjective data to objective values. This paper provides an overview of our architecture including concept, implementation details and present applications. We distinguish our approach from several other systems and describe two sensing applications namely AirProbe and WideNoise that were implemented for our platform.},
  author = {Becker, Martin and Mueller, Juergen and Hotho, Andreas and Stumme, Gerd},
  booktitle = {1st International Workshop on Pervasive Urban Crowdsensing Architecture and Applications, PUCAA 2013, Zurich, Switzerland – September 9, 2013. Proceedings},
  keywords = {platform},
  note = {Accepted for publication},
  pages = {New York, NY, USA},
  publisher = {ACM},
  title = {A Generic Platform for Ubiquitous and Subjective Data},
  year = 2013
}

Modeling and Mining Ubiquitous Social Media. Atzmueller, Martin; Chin, Alvin; Helic, Denis; Hotho, Andreas. In Vol. 7472 of Lecture Notes in Computer Science. Springer Verlag, Heidelberg, Germany, 2012.

[ BibTeX ]
[ URL ]

@book{ACHH:12,
  address = {Heidelberg, Germany},
  editor = {Atzmueller, Martin and Chin, Alvin and Helic, Denis and Hotho, Andreas},
  keywords = {from:hotho},
  publisher = {Springer Verlag},
  series = {Lecture Notes in Computer Science},
  title = {Modeling and Mining Ubiquitous Social Media},
  volume = 7472,
  year = 2012
}

Ubicon: Observing Social and Physical Activities. Atzmueller, Martin; Becker, Martin; Doerfel, Stephan; Kibanov, Mark; Hotho, Andreas; Macek, Björn-Elmar; Mitzlaff, Folke; Mueller, Juergen; Scholz, Christoph; Stumme, Gerd. In IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2012, Besançon, France, 20-23 November, 2012. IEEE, Washington, DC, USA, 2012.

[ Abstract ]
[ BibTeX ]
[ Download ]

The connection of ubiquitous and social computing is an emerging research area which is combining two prominent areas of computer science. In this paper, we tackle this topic from different angles: We describe data mining methods for ubiquitous and social data, specifically focusing on physical and social activities, and provide exemplary analysis results. Furthermore, we give an overview on the Ubicon platform which provides a framework for the creation and hosting of ubiquitous and social applications for diverse tasks and projects. Ubicon features the collection and analysis of both physical and social activities of users for enabling inter-connected applications in ubiquitous and social contexts. We summarize three real-world systems built on top of Ubicon, and exemplarily discuss the according mining and analysis aspects.

@inproceedings{mueller-2012,
  abstract = {The connection of ubiquitous and social computing is an emerging research area which is combining two prominent areas of computer science. In this paper, we tackle this topic from different angles: We describe data mining methods for ubiquitous and social data, specifically focusing on physical and social activities, and provide exemplary analysis results. Furthermore, we give an overview on the Ubicon platform which provides a framework for the creation and hosting of ubiquitous and social applications for diverse tasks and projects. Ubicon features the collection and analysis of both physical and social activities of users for enabling inter-connected applications in ubiquitous and social contexts. We summarize three real-world systems built on top of Ubicon, and exemplarily discuss the according mining and analysis aspects.},
  address = {Washington, DC, USA},
  author = {Atzmueller, Martin and Becker, Martin and Doerfel, Stephan and Kibanov, Mark and Hotho, Andreas and Macek, Björn-Elmar and Mitzlaff, Folke and Mueller, Juergen and Scholz, Christoph and Stumme, Gerd},
  booktitle = {IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2012, Besançon, France, 20-23 November, 2012},
  keywords = {from:hotho},
  publisher = {IEEE},
  title = {Ubicon: Observing Social and Physical Activities},
  year = 2012
}

{Generic Pattern Trees for Exhaustive Exceptional Model Mining}. Lemmerich, Florian; Becker, Martin; Atzmueller, Martin. In Proc. ECML/PKDD 2012: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Springer Verlag, Heidelberg, Germany, 2012.

[ BibTeX ]
[ Download ]

@inproceedings{LBA:12,
  address = {Heidelberg, Germany},
  author = {Lemmerich, Florian and Becker, Martin and Atzmueller, Martin},
  booktitle = {Proc. ECML/PKDD 2012: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.},
  keywords = {model},
  publisher = {Springer Verlag},
  title = {{Generic Pattern Trees for Exhaustive Exceptional Model Mining}},
  year = 2012
}

Machine Learning for Ecosystems and Climate Modeling

Projects

BigData@Geo 2.0

BigData@Geo

BeeConnected

we4bee

Concluded Projects

Publications

Data privacy protection

Data privacy protection

Picture credits