Intelligent Systems Laboratory - ISL


Intelligent Systems Laboratory was established in 2000. This laboratory primarily supports research on various aspects of intelligent systems, including semantic-web systems, multimedia databases, knowledge engineering, knowledge-based systems, automated reasoning, natural language processing, text mining, web service composition, artificial life, intelligent collaborative systems for technology-enhanced learning, neural networks, genetic algorithms, and robotics. The research groups currently work on various projects about semantic web technologies and ontology-based question answering systems.


  • Assoc. Prof. Dr. F. Nur Alpaslan
  • Assoc. Prof. Dr. N. Kesim Çiçekli
  • Dr. Ayşenur Birtürk
  • Özgür Alan (PhD.St)
  • Samet Akpınar (MSc.St)
  • Gencay Evirgen (MSc.St)
  • Orkunt Sabuncu (PhD.St)
  • Barış Tanrıkulu (BSc.St.)

Current Projects


Today's information and communication systems hold a huge amount of multimedia data. In addition to professionally produced multimedia content, user generated volume of multimedia content has been increasing dramatically with the advent of widely available sources such as mobile phones, digital cameras and recorders. The aim of this project is to develop architectures and technologies for intelligent ways of storing, searching, retrieving, managing, and consuming this enormous amount of data.

Metadata is necessary to understand and reason the multimedia content. This project will fully utilize widely accepted standards for describing multimedia data semantically. Existing multimedia data without sufficient metadata needs technologies like image processing, text mining and information extraction for generating semantic information.

Personalisation plays a key role in this project. The system will learn user profiles and continuously update them by considering usage histories. It can then find new multimedia content from TV broadcasts or Internet in accordance with the user profiles.


The main activities of the system involve the use of pedagogical approaches and the exploitation of interactivity and context-awareness. The interactivity will be provided by ontology-based question answering systems integrated into technology-enhanced learning systems. This way, users will be able to ask questions to the system in natural language and get appropriate answers from the system. Moreover, the system will be able to learn users' behaviour and configure itself accordingly. This framework provides faster and more effective ways of knowledge acquisition, and also increases user competences, and skills.

This framework also aims to develop standards for machine understandable content representation and for easy integration of question answering systems into technology-enhanced learning. The content generation phase has to be done by using special tools that help users create content in the norms of the standards.

Other Projects

  • The Virtual International Collaborative University, METU-University of North Texas Joint Research Project, Funded by National Science Foundation (USA) and TUBITAK (Turkey), NSF-TUBITAK-100E049, 2000 - 2002
  • Realistic Applications of Action Languages for Workflow Management, METU-University of Texas at Austin Joint Research Project, Funded by National Science Foundation (USA) and TUBITAK (Turkey), NSF-TUBITAK-101E024, 2001 - 2003
  • Distributed and Cooperative Information Systems, METU-Université de Bourgogne Joint Research Project, Funded by French Embassy in Turkey, 1999 - 2001
  • Mobile Commerce with Location-based Mobile Software Agents, Funded by METU, BAP-2002-07-04-01, 2002
  • Behavior-based Robotics Applications, Funded by METU, BAP-2002-03-12-01, 2002
  • Behavior-based Robotics Applications, Funded by TÜBİTAK, 102E003, 2002 - 2004
  • An Ontology-Based Turkish Question-Answering System, Funded by METU, BAP-2007-03-12-02, 2007 - 2009
  • A Personal Multimedia Knowledge Management System System, Funded by METU, BAP- 2007-03-12-01, 2007 - 2009

Selected Publications

  • Buyukbingol E., A. Sisman, M. Akyildiz, F.N. Alparslan, and A. Adejare, Adaptive neuro-fuzzy inference system (ANFIS): A new approach to predictive modeling in QSAR applications: A study of neuro-fuzzy modeling of PCP-based NMDA receptor antagonists, Accepted to be published in Bioorganic & Medicinal Chemistry, 2007.
  • Adiloğlu, K. and F. N. Alpaslan. A Machine Learning Approach to Two-Voice Counterpoint Composition. Knowledge-Based Systems Journal, 20 (2007) 300309.
  • Cicekli, N.K., I. Cicekli, Formalizing the specification and execution of workflows using the event calculus, Information Sciences, vol. 176, no. 15, 2006, pp. 2227-2267.
  • Cicekli, I., N.K. Cicekli, Generalizing predicates with string arguments, Applied Intelligence, vol. 25., No 1, 2006, pp.23-36.
  • Cicekli N.K., A. Cosar, A. Dogac, F. Polat, P. Senkul, I.H. Toroslu and A. Yazici, Data Management Research at the Middle East Technical University, ACM Sigmod Record, Volume 34, Number 3, September 2005.
  • Apolloni, B.; Ghosh, A.; Alpaslan, F.; Jain, L.C.; Patnaik, S. (Eds.) Machine Learning and Robot Perception, Series: Studies in Computational Intelligence, Vol. 7 , 2005. ISBN: 3-540-26549-X
  • Koprulu, M., N.K. Cicekli, A. Yazici, Spatio-temporal Querying in Video Databases, Information Sciences, 160, pp. 131-152, 2004.
  • Swigger K., F. Alpaslan, R. Brazile, and M. Monticino. Effects of Culture on Computer-Supported Collaborations. International Journal of Human-Computer Studies, Vol. 60, March 2004, pages 365-380.
  • Sisman-Yilmaz, N.A., F.N. Alpaslan, and L. Jain. ANFIS-unfolded-in-time for multivariate timeseries forcatsing, Neurocomputing, October 2004, Vol. 61, pages 139-168.

research/intelligent/index.txt · Last modified: 2011/02/17 11:24 by Erdal SIVRI