A Computational Design System with Cognitive Features Based on Multi-objective Evolutionary Search with Fuzzy Information Processing
A system for architectural design is presented, which is based on combining a multi-objective evolutionary algorithm with a fuzzy information processing system. The aim of the system is to identify optimal solutions for multiple criteria that involve linguistic concepts, and to systematically identify a most suitable solution among the alternatives. The system possesses cognitive features, where cognition is defined as final decision-making based not exclusively on optimization outcomes, but also on some higher-order aspects, which do not play role in the pure optimization process. That is, the machine is able to distinguish among the equivalently valid solution alternatives it generated, where the distinction is based on second order preferences that were not pin-pointed by the designer prior to the computational design process. This is accomplished through integrating fuzzy information processing into the multi-objective evolutionary search, so that second-order information can be inductively obtained from the search process. The machine cognition is exemplified by means of a design example, where a number of objects are optimally placed according to a number of architectural criteria.
KeywordsPareto Front Multiobjective Optimization Pareto Optimal Solution Cognitive Feature Priority Vector
Unable to display preview. Download preview PDF.
- 3.Koile, K.: An intelligent assistant for conceptual design. In: Gero, J.S. (ed.) Design Computing and Cognition 2004, pp. 3–22. Kluwer Academic Publishers, Massachusetts Institute of Technology, Boston, USA (2004)Google Scholar
- 4.Jang, J.S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing. Prentice Hall, Englewood Cliffs (1997)Google Scholar
- 6.Damsky, J., Gero, J.: An evolutionary approach to generating constraint-based space layout topologies. In: Junge, R. (ed.) CAAD Futures 1997, pp. 855–874. Kluwer Academic Publishing, Dordrecht (1997)Google Scholar
- 10.Coello, C.A.C., Veldhuizen, D.A., Lamont, G.B.: Evolutionary Algorithms for Solving Multiobjective Problems. Kluwer Academic Publishers, Boston (2003)Google Scholar
- 11.Bittermann, M.S., Ciftcioglu, O.: A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm. In: IEEE Conference on Evolutionary Computation. IEEE, Trondheim (2009)Google Scholar
- 13.Ciftcioglu, O., Bittermann, M.S., Sariyildiz, I.S.: Building performance analysis supported by GA. In: Tan, K.C., Xu, J.X. (eds.) 2007 IEEE Congress on Evolutionary Computation, pp. 489–495. IEEE, Singapore (2007)Google Scholar
- 14.Deb, K.: Multiobjective Optimization using Evolutionary Algorithms. John Wiley & Sons, Chichester (2001)Google Scholar
- 15.Tan, K.C., Xu, J.-X. (eds.): Proc. 2007 IEEE Congress on Evolutionary Computation. IEEE Cong., Singapore (2007)Google Scholar
- 17.Horn, J., Nafploitis, N., Goldberg, D.E.: A niched Pareto genetic algorithm for multiobjective optimization. In: Michaelwicz, Z. (ed.) First IEEE Conf. on Evolutionary Computation, pp. 82–87. IEEE Press, Los Alamitos (1994)Google Scholar
- 18.Ciftcioglu, Ö., Bittermann, M.S.: Adaptive formation of Pareto front in evolutionary multi-objective optimization. In: Santos, W.P.d. (ed.), Evolutionary Computation. In-Tech, Vienna, pp. 417–444 (2009)Google Scholar
- 19.Bittermann, M.S., Sariyildiz, I.S., Ciftcioglu, Ö.: Visual perception in design and robotics. Integrated Computer-Aided Engineering 14, 73–91 (2007)Google Scholar