Jeroen Janssens

Jeroen Janssens is a Ph.D. researcher at the Tilburg center for Cognition and Communication, Tilburg University. His supervisors are Eric Postma and Jaap van den Herik.

• International Workshop on Maritime Anomaly Detection (MAD 2011)

  • April 2011 to June 2011
  Team Members: Jeroen Janssens, Eric Postma, Joke Hellemons

  Organised the first international workshop on detecting maritime anomalies automatically, which was attended by 30 participants from 10 different countries. We received 20 contributions which resulted in 11 oral and 7 poster presentations.

• Presto: A Poseidon Research Tool

  • July 2008 to March 2009
  Team Members: Jeroen Janssens, Hans Hiemstra, Bob Eskes, Maurice Glandrup

  Developed, in collaboration with engineers from Thales Naval, open-source software that allows maritime domain experts to create and simulate anomalous vessel trajectories. The anomalous trajectories are merged with real data in order to evaluate machine learning algorithms in the maritime domain.

• Puncta

  • October 2006 to February 2007
  Team Members: Jeroen Janssens, Jeroen Donkers, Marius Nap

  Designed and programmed an application that visualises healthcare consumption. The application was used successfully by medical students as part of their research internship.
  

• An integrated approach for visual analysis of a multi-source moving objects knowledge base

  • International Journal of Geographical Information Science
  • October 2010
  Authors: Jeroen Janssens, Niels Willems, Willem van Hage, Gerben de Vries, Veronique Malaise

  We present an integrated and multi-disciplinary approach for analyzing behavior of moving objects. The results originate from ongoing research of four different partners from the Dutch Poseidon project (Embedded Systems Institute (2007)), which aims to develop new methods for Maritime Safety and Security (MSS) systems to monitor vessel traffic in coastal areas. Our architecture enables an operator to visually test hypotheses about vessels with time-dependent sensor data and on-demand external knowledge. The system includes the following components: abstraction and simulation of trajectory sensor data, fusion of multiple heterogeneous data sources, reasoning, and visual analysis of the combined data sources. We start by extracting segments of consistent movement from simulated or real-world trajectory data, which we store as instances of the Simple Event Model (SEM), an event ontology represented in the Resource Description Framework (RDF). Next, we add data from the web about vessels and geography to enrich the sensor data. This additional information is integrated with the representation of the vessels (actors) and places in SEM. The enriched trajectory data is stored in a knowledge base, which can be further annotated by reasoning and is queried by a visual analytics tool to search for spatio-temporal patterns. Although our approach is dedicated to MSS systems, we expect it to be useful in other domains.

• Creating artificial vessel trajectories with Presto

  • Proceedings of the 22nd Benelux Conference on Artificial Intelligence
  • October 2010
  Authors: Jeroen Janssens, Hans Hiemstra, Eric Postma

  The automatic detection of anomalies in the maritime domain requires representative anomalous instances. We developed Presto, an application that enables maritime-domain experts to create artificial anomalous vessel trajectories that may be characteristic of traffic violations, illegal fishing activities, drug smuggling, or piracy. When merged with existing real-world data, the artificial trajectories make possible the usage and evaluation of machine learning algorithms for the automatic detection of anomalies.

• Outlier detection with one-class classifiers from ML and KDD

  • Proceedings of the Eighth International Conference on Machine Learning and Applications
  • December 2009
  Authors: Jeroen Janssens, Ildiko Flesch, Eric Postma

  The problem of outlier detection is well studied in the fields of Machine Learning (ML) and Knowledge Discovery in Databases (KDD). Both fields have their own methods and evaluation procedures. In ML, Support Vector Machines and Parzen Windows are well-known methods that can be used for outlier detection. In KDD, the heuristic local-density estimation methods LOF and LOCI are generally considered to be superior outlier-detection methods. Hitherto, the performances of these ML and KDD methods have not been compared. This paper formalizes LOF and LOCI in the ML framework of one-class classification and performs a comparative evaluation of the ML and KDD outlier-detection methods on real-world datasets. Experimental results show that LOF and SVDD are the two best-performing methods. It is concluded that both fields offer outlier-detection methods that are competitive in performance and that bridging the gap between both fields may facilitate the development of outlier-detection methods.

• One-class classification with LOF and LOCI: An empirical comparison

  • Proceedings of the 18th Annual Belgian-Dutch Conference on Machine Learning
  • May 2009
  Authors: Jeroen Janssens, Eric Postma

  LOF and LOCI are two widely used density-based outlier-detection methods. Generally, LOCI is assumed to be superior to LOF, because LOCI constitutes a multi-granular method. A review of the literature reveals that this assumption is not based on quantitative comparative evaluation of both methods. In this paper we investigate outlier detection with LOF and LOCI within the framework of one-class classification. This framework allows us to perform an empirical comparison using the AUC performance measure. Our experimental results show that LOCI does not outperform LOF. We discuss possible reasons for the results obtained and argue that the multi-granularity of LOCI in some cases may hamper rather than help the detection of outliers. It is concluded that LOCI does not outperform LOF and that the choice for either method depends on the nature of the task at hand. Future work will address the evaluation of both methods with existing one-class classifiers.

• Ranking images on semantic attributes using human computation

  • NIPS Workshop on Computational Social Science and the Wisdom of Crowds
  • December 2010
  Authors: Jeroen Janssens

  We investigate to what extent a large group of human workers is able to produce collaboratively a global ranking of images, based on a single semantic attribute. To this end, we have developed CollaboRank, which is a method that formulates and distributes tasks to human workers, and aggregates their personal rankings into a global ranking. Our results show that human workers can achieve a relatively high consensus, depending on the type of the semantic attribute.

1. Collaborating with and presenting to academic and engineering audiences
2. Setting up large-scale experiments to evaluate machine learning algorithms
3. Visualising data with TikZ and Adobe Illustrator
4. Implementing (new) machine learning algorithms in MATLAB
5. Typesetting beautiful documents and presentations with LaTeX
6. Programming in Java, C, C++, Python, PHP, and JavaScript
7. Working with Linux on a daily basis

Websites:

• Short curriculum vitae (PDF)

Groups and Associations:

• 
  Alumni Maastricht University
• 
  Carolus Borromeus College
• 
  Data Mining, Statistics, and Data Visualization
• 
  Data Scientists
• 
  Dutch Artificial Intelligence
• 
  Embedded Systems Institute Alumni
• 
  Linux Users
• 
  MATLAB Users
• 
  Maastricht University
• 
  Machine Learning Connection
• 
  PADI Scuba Divers
• 
  SIKS-Community, members and alumni of the School for Information and Knowledge Systems
• 
  Visual Analytics

Honors and Awards:

Best Presentation Award, TiCC Ph.D. Day 2010