Recent Publications

@article{wicker2017best,
title = {The Best Privacy Defense is a Good Privacy Offense: Obfuscating a Search Engine User's Profile},
author = {Jörg Wicker and Stefan Kramer},
editor = {Kurt Driessens and Dragi Kocev and Marko Robnik-Šikonja and Myra Spiliopoulou},
url = {http://rdcu.be/tL0U},
doi = {10.1007/s10618-017-0524-z},
issn = {1573-756X},
year = {2017},
date = {2017-09-01},
journal = {Data Mining and Knowledge Discovery},
volume = {31},
number = {5},
pages = {1419-1443},
abstract = {User privacy on the internet is an important and unsolved problem. So far, no sufficient and comprehensive solution has been proposed that helps a user to protect his or her privacy while using the internet. Data are collected and assembled by numerous service providers. Solutions so far focused on the side of the service providers to store encrypted or transformed data that can be still used for analysis. This has a major flaw, as it relies on the service providers to do this. The user has no chance of actively protecting his or her privacy. In this work, we suggest a new approach, empowering the user to take advantage of the same tool the other side has, namely data mining to produce data which obfuscates the user’s profile. We apply this approach to search engine queries and use feedback of the search engines in terms of personalized advertisements in an algorithm similar to reinforcement learning to generate new queries potentially confusing the search engine. We evaluated the approach using a real-world data set. While evaluation is hard, we achieve results that indicate that it is possible to influence the user’s profile that the search engine generates. This shows that it is feasible to defend a user’s privacy from a new and more practical perspective.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{latino2017eawag,
title = {Eawag-Soil in enviPath: a new resource for exploring regulatory pesticide soil biodegradation pathways and half-life data},
author = {Diogo Latino and Jörg Wicker and Martin Gütlein and Emanuel Schmid and Stefan Kramer and Kathrin Fenner},
doi = {10.1039/C6EM00697C},
year = {2017},
date = {2017-01-01},
journal = {Environmental Science: Process & Impact},
publisher = {The Royal Society of Chemistry},
abstract = {Developing models for the prediction of microbial biotransformation pathways and half-lives of trace organic contaminants in different environments requires as training data easily accessible and sufficiently large collections of respective biotransformation data that are annotated with metadata on study conditions. Here, we present the Eawag-Soil package, a public database that has been developed to contain all freely accessible regulatory data on pesticide degradation in laboratory soil simulation studies
for pesticides registered in the EU (282 degradation pathways, 1535 reactions, 1619 compounds and 4716 biotransformation half-life values with corresponding metadata on study conditions). We provide a thorough description of this novel data resource, and discuss important features of the pesticide soil degradation data that are relevant for model development. Most notably, the variability of half-life values for individual compounds is large and only about one order of magnitude lower than the entire range of median half-life values spanned by all compounds, demonstrating the need to consider study conditions in the development of more accurate models for biotransformation prediction. We further show how the data can be used to find missing rules relevant for predicting soil biotransformation pathways. From this analysis, eight examples of reaction types were presented that should trigger the formulation of new biotransformation rules, e.g., Ar-OH methylation, or the extension of existing rules e.g., hydroxylation in aliphatic rings. The data were also used to exemplarily explore the dependence of half-lives of different amide pesticides on chemical class and experimental parameters. This analysis highlighted the value of considering initial transformation reactions for the development of meaningful quantitative-structure biotransformation relationships (QSBR), which is a novel opportunity of f ered by the simultaneous encoding of transformation reactions and corresponding half-lives in Eawag-Soil. Overall, Eawag-Soil provides an unprecedentedly rich collection of manually extracted and curated biotransformation data, which should be useful in a great variety of applications.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{wicker2016envipath,
title = {enviPath - The Environmental Contaminant Biotransformation Pathway Resource},
author = {Jörg Wicker and Tim Lorsbach and Martin Gütlein and Emanuel Schmid and Diogo Latino and Stefan Kramer and Kathrin Fenner},
editor = {Michael Galperin},
url = {http://nar.oxfordjournals.org/content/44/D1/D502.abstract},
doi = {10.1093/nar/gkv1229},
year = {2016},
date = {2016-01-01},
journal = {Nucleic Acid Research},
volume = {44},
number = {D1},
pages = {D502-D508},
abstract = {The University of Minnesota Biocatalysis/Biodegradation Database and Pathway Prediction System (UM-BBD/PPS) has been a unique resource covering microbial biotransformation pathways of primarily xenobiotic chemicals for over 15 years. This paper introduces the successor system, enviPath (The Environmental Contaminant Biotransformation Pathway Resource), which is a complete redesign and reimplementation of UM-BBD/PPS. enviPath uses the database from the UM-BBD/PPS as a basis, extends the use of this database, and allows users to include their own data to support multiple use cases. Relative reasoning is supported for the refinement of predictions and to allow its extensions in terms of previously published, but not implemented machine learning models. User access is simplified by providing a REST API that simplifies the inclusion of enviPath into existing workflows. An RDF database is used to enable simple integration with other databases. enviPath is publicly available at https://envipath.org with free and open access to its core data.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{williams2015element,
title = {Cinema audiences reproducibly vary the chemical composition of air during films, by broadcasting scene specific emissions on breath},
author = {Jonathan Williams and Christof Stönner and Jörg Wicker and Nicolas Krauter and Bettina Derstorff and Efstratios Bourtsoukidis and Thomas Klüpfel and Stefan Kramer},
url = {http://www.nature.com/articles/srep25464},
doi = {10.1038/srep25464},
year = {2016},
date = {2016-01-01},
journal = {Scientific Reports},
volume = {6},
publisher = {Nature Publishing Group},
abstract = {Human beings continuously emit chemicals into the air by breath and through the skin. In order to determine whether these emissions vary predictably in response to audiovisual stimuli, we have continuously monitored carbon dioxide and over one hundred volatile organic compounds in a cinema. It was found that many airborne chemicals in cinema air varied distinctively and reproducibly with time for a particular film, even in different screenings to different audiences. Application of scene labels and advanced data mining methods revealed that specific film events, namely "suspense" or "comedy" caused audiences to change their emission of specific chemicals. These event-type synchronous, broadcasted human chemosignals open the possibility for objective and non-invasive assessment of a human group response to stimuli by continuous measurement of chemicals in air. Such methods can be applied to research fields such as psychology and biology, and be valuable to industries such as film making and advertising.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@incollection{wicker2016ahybrid,
title = {A Hybrid Machine Learning and Knowledge Based Approach to Limit Combinatorial Explosion in Biodegradation Prediction},
author = {Jörg Wicker and Kathrin Fenner and Stefan Kramer},
editor = {Jörg Lässig and Kristian Kersting and Katharina Morik},
url = {http://dx.doi.org/10.1007/978-3-319-31858-5_5},
doi = {10.1007/978-3-319-31858-5_5},
isbn = {978-3-319-31858-5},
year = {2016},
date = {2016-04-21},
booktitle = {Computational Sustainability},
pages = {75-97},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {One of the main tasks in chemical industry regarding the sustainability of a product is the prediction of its environmental fate, i.e., its degradation products and pathways. Current methods for the prediction of biodegradation products and pathways of organic environmental pollutants either do not take into account domain knowledge or do not provide probability estimates. In this chapter, we propose a hybrid knowledge-based and machine learning-based approach to overcome these limitations in the context of the University of Minnesota Pathway Prediction System (UM-PPS). The proposed solution performs relative reasoning in a machine learning framework, and obtains one probability estimate for each biotransformation rule of the system. Since the application of a rule then depends on a threshold for the probability estimate, the trade-off between recall (sensitivity) and precision (selectivity) can be addressed and leveraged in practice. Results from leave-one-out cross-validation show that a recall and precision of approximately 0.8 can be achieved for a subset of 13 transformation rules. The set of used rules is further extended using multi-label classification, where dependencies among the transformation rules are exploited to improve the predictions. While the results regarding recall and precision vary, the area under the ROC curve can be improved using multi-label classification. Therefore, it is possible to optimize precision without compromising recall. Recently, we integrated the presented approach into enviPath, a complete redesign and re-implementation of UM-PPS.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}

@inproceedings{wicker2016nonlinear,
title = {A Nonlinear Label Compression and Transformation Method for Multi-Label Classification using Autoencoders},
author = {Jörg Wicker and Andrey Tyukin and Stefan Kramer},
editor = {James Bailey and Latifur Khan and Takashi Washio and Gill Dobbie and Zhexue Joshua Huang and Ruili Wang},
url = {http://dx.doi.org/10.1007/978-3-319-31753-3_27},
doi = {10.1007/978-3-319-31753-3_27},
isbn = {978-3-319-31753-3},
year = {2016},
date = {2016-04-16},
booktitle = {The 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},
volume = {9651},
pages = {328-340},
publisher = {Springer International Publishing},
address = {Switzerland},
series = {Lecture Notes in Computer Science},
abstract = {Multi-label classification targets the prediction of multiple interdependent and non-exclusive binary target variables. Transformation-based algorithms transform the data set such that regular single-label algorithms can be applied to the problem. A special type of transformation-based classifiers are label compression methods, that compress the labels and then mostly use single label classifiers to predict the compressed labels. So far, there are no compression-based algorithms follow a problem transformation approach and address non-linear dependencies in the labels. In this paper, we propose a new algorithm, called Maniac (Multi-lAbel classificatioN usIng AutoenCoders), which extracts the non-linear dependencies by compressing the labels using autoencoders. We adapt the training process of autoencoders in a way to make them more suitable for a parameter optimization in the context of this algorithm. The method is evaluated on eight standard multi-label data sets. Experiments show that despite not producing a good ranking, Maniac generates a particularly good bipartition of the labels into positives and negatives. This is caused by rather strong predictions with either really high or low probability. Additionally, the algorithm seems to perform better given more labels and a higher label cardinality in the data set.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{raza2016trading,
title = {Trading Off Accuracy for Efficiency by Randomized Greedy Warping},
author = {Atif Raza and Jörg Wicker and Stefan Kramer},
url = {https://wicker.nz/nwp-acm/authorize.php?id=N10030
http://doi.acm.org/10.1145/2851613.2851651},
doi = {10.1145/2851613.2851651},
isbn = {978-1-4503-3739-7},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the 31st Annual ACM Symposium on Applied Computing},
pages = {883-890},
publisher = {ACM},
address = {New York, NY, USA},
series = {SAC '16},
abstract = {Dynamic Time Warping (DTW) is a widely used distance measure for time series data mining. Its quadratic complexity requires the application of various techniques (e.g. warping constraints, lower-bounds) for deployment in real-time scenarios. In this paper we propose a randomized greedy warping algorithm for f i nding similarity between time series instances.We show that the proposed algorithm outperforms the simple greedy approach and also provides very good time series similarity approximation consistently, as compared to DTW. We show that the Randomized Time Warping (RTW) can be used in place of DTW as a fast similarity approximation technique by trading some classification accuracy for very fast classification.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}