Michael S. Bittermann
From Design Informatics
Dr.ir. Michael S. Bittermann
Postdoctoral Researcher
Michael Bittermann studied architecture from 1997-2003 and graduated cum laude as Master of Science in Architecture from Delft University of Technology, in Delft, The Netherlands. Mr. Bittermann carried out his PhD during the period 2005-2009 at the chair of Design Informatics, at the Faculty of Architecture of Delft University of Technology.
Bittermann received his PhD title cum laude in 2009.
Following his PhD Bittermann received the Young Researcher Fellowship of Delft University of Technology for outstanding research and academic achievements (120k€, source: TU Delft) in 2009 as one of the five best researchers among the PhD students of all faculties of TU Delft who graduated in 2009.
During his Fellowship, for two years he has been collaborating with Professor Kalyanmoy Deb, director of the Kanpur Genetic Algorithm Laboratory KanGAL [1] at Indian Institute of Technology Kanpur (IITK) in Kanpur, India. KanGAL is a center of excellence in the field of evolutionary computation, fuzzy logic controllers, bioinformatics and neural networks. Bittermann visited KanGAL in 2011 for the collaboration, and vice versa at different periods during 2010 and 2011. The collaboration led to advanced problems handling by evolutionary optimization methods, and applications in the framework of joint evolutionary-classical search [2]. Later these methods are extended by Bittermann at the Chair of Design Informatics in Delft by integrating a new probability dimension into evolutionary optimization, e.g. see [3] [4].
Bittermann has published more than thirty papers in the areas of computational design, evolutionary computation, fuzzy computation, robotics and computer vision, including six chapters in international peer-reviewed books, and five papers in international peer-reviewed journals. The publications can be dowloaded here: [5].
His research interests are computational cognition and consciousness, computational intelligence, and machine perception.
Contact
Mailto: m.s.bittermann@tudelft.nl
Tel:+31-639250915
Tel priv:+31-645728249
Office:01.west.rm.010
Address:Faculty of Architecture, Department of Architectural Engineering & Tehcnology, Delft University of Technology, Julianalaan 134, 2628 BL Delft, The Netherlands
Brief summary of research
 | Design is complex. This is because it involves conflicting goals that are often vague. Also, prior to the design it is generally not clear how important goals are relative to each other. And finally the amount of possible solutions is large in general. These bottlenecks are addressed in this thesis.
A novel approach for design is proposed, where computation is used to reach most suitable solutions. The approach is based on a novel concept of the objects forming a design. This concept is termed intelligent design objects. Such objects exhibit intelligent behavior in the sense that they approach most desirable solutions for conflicting, vague goals put forward by a designer. That is, the objects know ‘themselves’ what to do to satisfy the designer’s goals. This is accomplished using methods from the domain of computational intelligence, as these are uniquely able to deal with the complexity of design mentioned above.
The result from the approach is that designers and decision makers have great certainty about the satisfaction of their goals and are able to concentrate on second order aspects they were not aware of prior to the execution. The approach is implemented for two applications from the domain of architecture demonstrating its effectiveness.
The thesis addresses to students, researchers and executives in the field of architecture, and other areas of design. It may be also interesting for researchers in the domain of computational intelligence, as it provides a formalism of intelligent design, and it exemplifies the use of these modern technologies in the design domain. |
