Visual Universitätsmedizin Mainz
Apeldoorn
Daan Apeldoorn
Funktionen: Wissenschaftlicher Mitarbeiter
Qualifikationen: Master of Science in Informatik

06131 17-5062
daan.apeldoorn@uni-mainz.de
Weitere Informationen

Personal Details

  • Since 2019: Staff member at the Institute of Medical Biostatistics, Epidemiology and Informatics (IMBEI) at the University Medical Center of the Johannes Gutenberg University Mainz
  • Since 2018: Staff member at the Z Quadrat GmbH
  • 2017: Award Forum Young Top Researchers 2nd place
  • 2015-2018: Scientific staff member at the TU Dortmund University
  • 2014-2015: Scientific staff member at the University of Koblenz-Landau
  • Since 2014: Jury member of the German competition for young researchers Jugend forscht/Schüler experimentieren
  • 2014: MSc in Computer Science from the University of Hagen
  • 2014: Helmholtz-Teacher-Award
  • 2009-2014: Extracurricular staff member/teacher at the Otto-Schott-Gymnasium (secondary school) in Mainz
  • 2007-2009: Systems Engineer at the IMAGIN (Schweiz) AG
  • 2006: BSc in Computer Science from the University of Mainz (minor subject: Musicology)
  • 2005-2013: Co-founder of the music project Acoustique Parfum; several releases on different record labels (e.g., Mole Listening Pearls)
  • 2002: Hasso-Plattner-Award for Software Systems Technology
  • 1999-2002: Developer at a Children Cancer Database at the University Hospital of Mainz

Research Interests

  • Multi-agent systems and simulations (e.g., with application in logistics)
  • Incorporation of symbolic and subsymbolic approaches with a focus on agent-based learning with knowledge extraction/integration
  • Methods of Artificial Intelligence and their application in the context of autonomous agents (e.g., in games)

In the past, I was also working on a project in the field of Software Engineering.

Projects

  • AbstractSwarm Multi-Agent Modeling and Simulation System: A multi-agent modeling and simulation system for optimizing logistics and related scenarios like hospital processes. (WIMS)
  • InteKRator Toolbox: A toolbox for integrating machine learning and knowledge representation aspects (e.g., for finding structural dependencies in data and for reasoning tasks) with applications, e.g., in the automated creation of expert systems from data.(WIMS)

Teaching

IMBEI: 

  • 2020: Course on Knowledge Base Extraction at IMBEI Summer School in Bioinformatics and High-Dimensional Statistics

Z Quadrat:

  • 2019/2020 (selection): Workshops/courses in Artificial Intelligence, Robotics (with LEGO® Mindstorms), Games/Apps Programming (with EduGine C++), and others
  • 2018/2019 (selection): Workshops/courses in Artificial Intelligence, Robotics (with LEGO® Mindstorms), Games Programming (with EduGine Java), and others

TU Dortmund University:

  • Winter 2017/2018: Tutorial Darstellung, Verarbeitung und Erwerb von Wissen (Bachelor)
  • Summer 2017: Tutorial Commonsense Reasoning (Master)
  • Winter 2016/2017: Tutorial Darstellung, Verarbeitung und Erwerb von Wissen (Bachelor)
  • Summer 2016: Tutorial Commonsense Reasoning (Master)
  • Winter 2015/2016: Tutorial Darstellung, Verarbeitung und Erwerb von Wissen (Bachelor)
  • Summer 2015: Tutorial Commonsense Reasoning (Master)

University of Koblenz-Landau:

  • Winter 2014/2015: Tutorial Introduction to Web Science (Master, in English)

University of Hagen:

  • Winter 2018/2019: Corrector for Wissensbasierte Systeme (Bachelor/Master)
  • Summer 2018: Corrector for Wissensbasierte Systeme (Bachelor/Master)
  • Summer 2011: Corrector for Entscheidungsmethoden in unternehmensweiten Softwaresystemen (Bachelor/Master)
  • Winter 2010/2011: Corrector for Entscheidungsmethoden in unternehmensweiten Softwaresystemen (Bachelor/Master)

Co-Supervised Theses

  • Integration zweier unterschiedlicher Agentenmodelle für Multi-Agenten-Szenarien mit Anwendung in der Logistik (together with Prof. Dr. Kern-Isberner, Master, finished)
  • Erlernen von Wissensbasen mittels Reinforcement Learning und Neuronalen Netzen (together with Prof. Dr. Kern-Isberner, Master, finished)
  • Lernen von Bayes-Netz-Strukturen als Grundlage für Agentenverhalten (together with Prof. Dr. Kern-Isberner, Bachelor, finished)
  • Statistische Evaluation unterschiedlicher Repräsentationsformen für die Wissensextraktion aus Reinforcement Learning (together with Prof. Dr. Kern-Isberner, Bachelor, finished)

In the past, I was also supervising more than 20 projects for the German young researchers competition Jugend Forscht/Schüler Experimentieren.

Publications

  • Apeldoorn, D., Hadidi, L., Panholzer, T.: Learning Behavioral Rules from Multi-Agent Simulations for Optimizing Hospital Processes. In: Chomphuwiset, P., Kim, J., Pawara, P. (eds.) Multi-disciplinary Trends in Artificial Intelligence – 14th International Conference, MIWAI 2021, Virtual Event, July 2–3, 2021, Proceedings, pp. 14–26. Springer, Cham, 2021. (url)
  • Apeldoorn, D.: KI in der Schule – Teil 1: Einführung in die künstliche Intelligenz. LOG IN – Informatische Bildung und Computer in der Schule, 195/196:126–131, 2021.
  • Apeldoorn, D., Dockhorn, A.: Exception-Tolerant Hierarchical Knowledge Bases for Forward Model Learning. IEEE Transactions on Games (Early Access), DOI: 10.1109/TG.2020.3008002, 2020. (url)
  • Dockhorn, A., Apeldoorn, D.: Forward Model Approximation for General Video Game Learning. In: Browne, C., Winands, M. H. M., Liu, J., Preuss, M. (eds.) Proceedings of the 2018 IEEE Conference on Computational Intelligence and Games (CIG’18), pp. 425–432. IEEE, Piscataway, 2018. (url) (bibtex)
  • Apeldoorn, D., Kern-Isberner, G.: An Agent-Based Learning Approach for Finding and Exploiting Heuristics in Unknown Environments. In: Gordon, A. S., Miller, R., Turán, G. (eds.) Proceedings of the Thirteenth International Symposium on Commonsense Reasoning, London, UK, November 6-8, 2017. CEUR Workshop Proceedings, vol. 2052, paper 1. CEUR-WS.org, Aachen, 2018. (url) (bibtex)
  • Apeldoorn, D., Volz, V.: Measuring Strategic Depth in Games Using Hierarchical Knowledge Bases. In: 2017 IEEE Conference on Computational Intelligence and Games (CIG), pp. 9–16. IEEE, Piscataway, 2017. (url) (bibtex)
  • Krüger, C., Apeldoorn, D., Kern-Isberner, G.: Comparing Answer Set Programming and Hierarchical Knowledge Bases Regarding Comprehensibility and Reasoning Efficiency in the Context of Agents. In: Proceedings of the 30th International Workshop on Qualitative Reasoning (QR 2017) at International Joint Conference on Artificial Intelligence (IJCAI 2017) in Melbourne, Australia. Northwestern University, Evanston, Illinois, 2017. (url) (bibtex)
  • Apeldoorn, D., Kern-Isberner, G.: Towards an Understanding of What is Learned: Extracting Multi-Abstraction-Level Knowledge from Learning Agents. In: Rus, V., Markov, Z. (eds.) Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference, pp. 764–767. AAAI Press, Palo Alto, California, 2017. (url) (bibtex)
  • Apeldoorn, D., Kern-Isberner, G.: When Should Learning Agents Switch to Explicit Knowledge? In: Benzmüller, C., Sutcliffe, G., Rojas, R. (eds.) GCAI 2016. 2nd Global Conference on Artificial Intelligence. EPiC Series in Computing, vol. 41, pp. 174–186. EasyChair Publications, 2016. (url) (bibtex)
  • Apeldoorn, D.: A Spatio-Temporal Multiagent Simulation Framework for Reusing Agents in Different Kinds of Scenarios. In: Müller, J. P., Ketter, W., Kaminka, G., Wagner, G., Bulling, N. (eds.) Multiagent System Technologies. LNAI, vol. 9433, pp. 79–97. Springer International Publishing, Switzerland, 2015. (url) (bibtex)
  • Apeldoorn, D.: Learning Rules for Cooperative Solving of Spatio-Temporal Problems. In: Beierle, C., Kern-Isberner, G., Ragni, M., Stolzenburg, F. (eds.) Proceedings of the 5th Workshop on Dynamics of Knowledge and Belief (DKB-2015) and the 4th Workshop KI & Kognition (KIK-2015) co-located with the 38th German Conference on Artificial Intelligence (KI-2015), Dresden, Germany, September 22, 2015. CEUR Workshop Proceedings, vol. 1444, pp. 5–15. CEUR-WS.org, Aachen, 2015. (url) (bibtex)
  • Apeldoorn, D.: AbstractSwarm – A Generic Graphical Modeling Language for Multi-Agent Systems. In: Klusch, M., Thimm, M., Paprzycki, M. (eds.) Multiagent System Technologies. LNCS, vol. 8076, pp. 180–192. Springer, Berlin Heidelberg, 2013. (url) (bibtex)
  • Apeldoorn, D.: Statistical Relational Learning in Dynamic Environments – An Agent-Based Approach to Dynamic Pathfinding Using Bayesian Logic Networks and ProbCog. In: Beierle, C., Kern-Isberner, G. (eds.) Informatik Berichte 361–09/2011: Evolving Knowledge in Theory and Applications – Proceedings of the 3rd Workshop on Dynamics of Knowledge and Belief (DKB 2011) at the 34th Annual Conference on Artificial Intelligence (KI-2011) in Berlin, pp. 61–71. FernUniversität in Hagen, Hagen, 2011. (url) (bibtex)
  • Apeldoorn, D., Heimbürger, H.: Method-oriented software development (MOSD) with the programming language C-mol – a new concept for improved Human Computer Interaction regarding the transfer of an idea to its realization. TESI 2005 Conference Proceedings, AIS II.2, Highbury Business, Kent, 2005. (bibtex)
  • Apeldoorn, D., Heimbürger, H.: Method-oriented software development (MOSD) with the programming language C-mol – A new concept for more efficient development and implementation of software systems. In: Gesellschaft für Informatik e.V. (ed.) Informatiktage 2003: Fachwissenschaftlicher Informatik-Kongress, pp. 103–106. Konradin Verlagsgruppe, Grasbrunn, 2004. (bibtex)