Computational Intelligent Design

Human has the remarkable capability to make best decisions in ample environmental information. The research presented here concerns establishing computational models that simulate the human abstraction, reasoning and creation capabilities during architectural design. This is important for two reasons. The first aspect is that the computational models permit to better understand the processes occurring via human mind, so that a deeper understanding of what design is and how it works is gained. The second aspect is that it permits to support a human decision-maker by means of powerful, ‘wise’ assistance during difficult tasks that are beyond human comprehension. In particular decisions in design and engineering are difficult to take due to increasing complexity that generally arises from the following three issues:

  • The softness, which stems from the need to represent many detailed features of an environment by means of a few quantities, so that models involve many non-linear relations among variables.
  • Optimization with the involvement of multiple, and stiff constraints that must be satisfied.
  • Involvement of several independent variables constituting a solution, which implies an excessive amount of possible solutions to be investigated within a limited time.

These issues make it formidably challenging to reach most suitable solutions. It is emphasized that this difficulty is alleviated when advanced computational methods are used to deal with the complexity, which is the subject matter of the computational intelligence-based work presented here. In particular methods from the domain of computational intelligence, such as evolutionary, neural and fuzzy computation, are employed to deal with soft and conflicting objectives, stiff constraints and vast solution domains. As result, solutions are guaranteed to satisfy the objectives at hand, while they satify the constraints at the same time. This quality assurance is highly desirable in the face of depleting resources and increasing demands imposed on engineering and design products, and it will become more and more relevant in the future, in proportion with the increase in complexity of the real-world  design and decision-making problems.

Submitted publications with peer review process

  1. Ciftcioglu, Ö., Bittermann, M.S.: Computational Visual Perception and Perceptual Density: A Probabilistic Theory. Integrated Computer-Aided Engineering
  2. Bittermann, M.S., Ciftcioglu, Ö.,: Ambient Environment Analysis by means of Visual Perception: Probabilistic-Possibilistic Approach. Advanced Engineering Informatics 

Recent publications with peer review process (2006-2012)

Book chapters

  1. Ciftcioglu, Ö., Sariyildiz, I.S.: Data sensor fusion for autonomous robotics. In: Kucuk, S. (ed.) Serial and Parallel Robot Manipulators Kinematics, Dynamics, Control and Optimization. InTech, Vienna (2012)373-400.
  2. Bittermann, M.S., Sariyildiz, I.S., Ciftcioglu, Ö.: A computational intelligence approach to alleviate complexity issues in design. In: Portugali, J. and Meyer, H. (eds.): Complexity Theories of Cities have come of Age - Part Two: Implications to Planning and Urban Design. Springer Verlag, Heidelberg (2012) 347-368
  3. Bittermann, M.S., Sariyildiz, I.S.: Virtual reality and computational design. In: Kim, J.-J. (ed.):Virtual Reality. InTech, Rijeka, Croatia (2010) 547-578
  4. Ciftcioglu, Ö., Bittermann, M.S.: Adaptive formation of Pareto front in evolutionary multi-objective optimization. In: Lazinica, A. (ed.): Evolutionary Computation. In-Tech, Vienna (2009) 417-444
  5. Ciftcioglu Ö., Bittermann M.S.: From perceptual towards cognitive robotics in the framework of evolutionary computation. In: Pennacchio, S. (ed.): Recent advances in Control Systems, Robotics and Automation – Third edition Volume 2. InternationalSAR, Palermo, Italy (2009) 160-175
  6. Ciftcioglu, O.: Multiresolutional filter application for spatial information fusion in robot navigation. Robotics, Automation and Control. InTech, Vienna (2008) 355-372
  7. Ciftcioglu, Ö.: Shaping the perceptual robot vision and multiresolutional Kalman filtering implementation. In: Emerging Technologies, Robotics and Control Systems. International Society for Advanced Research, Palermo (2007) 212-225
  8. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S.: Visual perception theory underlying perceptual navigation. In: Emerging Technologies, Robotics and Control Systems. International Society for Advanced Research, Palermo (2007) 139-153
  9. Sariyildiz, I.S., Bittermann, M.S., and Ciftcioglu, O.: Perception & Architecture. In: H. Bekkering, D. Hauptmann, A. d. Heijer, J. Klatte, U. Knaack, and S. v. Manen (Eds.): The Architecture Annual 2005-2006 Delft University of Technology. 010 Publishers, Rotterdam (2007) 104-109
  10. Ciftcioglu Ö and Sariyildiz I.S Fuzzy logic for stochastic modeling In: J. Lawry, E. Miranda, A. Bugarin, S. Li, M. A. Gil, P. Grzegorzewski, and O. Hryniewicz (Eds.): Soft Methods for Integrated Uncertainty Modelling, Advances in Soft Computing Vol. 37, Springer Verlag (2006) 347-355

Journal papers

  1. Ciftcioglu, Ö., Bittermann, M.S.: From perceptual towards cognitive robotics in the framework of evolutionary computation. Int. J Factory Automation, Robotics and Soft Computing 1 (2009) 165-180
  2. Bittermann M.S., Ciftcioglu Ö.: Visual perception model for architectural design. Journal of Design Research 7 (2008) 35-60
  3. Ciftcioglu, Ö.: Shaping the perceptual robot vision and multiresolutional Kalman filtering implementation. Int. J. Factory Automation, Robotics and Soft Computing 3 (2008) 62-75
  4. Bittermann M.S., Sariyildiz I.S. and Ciftcioglu Ö. Visual perception in design and robotics. J. Integrated Computer-Aided Engineering 14 (2007) 73-91
  5. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S.: Visual perception theory underlying perceptual navigation. Int. J. Factory Automation, Robotics and Soft Comp. (2007) 171-185
  6. Ciftcioglu Ö., Bittermann M.S. and Sariyildiz I.S. Multiresolutional fusion of perceptions applied to robot navigation . J. of Advanced Computational Intelligence and Intelligent Informatics (JACIII) 11, No. 6 (2007) 688-700

Conference papers

  1. Ciftcioglu, O., Bittermann, M.S.:Fusion of perceptions in architectural design. eCAADe 2013 Computation and Performance , Delft, Netherlands, (2013) 335-344
  2. Bittermann, M.S.,Ciftcioglu, O.: Ambient surveillance by probabilistic-possibilistic perception. eCAADe 2013 Computation and Performance, Delft, Netherlands, (2013) 345-353
  3. Bittermann, M.S., Ciftcioglu, Ö., Mehul Bhatt, M., Schultz, C.: Ambient environment analysis by means of perception. 20th Int. Workshop Intelligent Computing in Engineering 2013 – EG-ICE 2013, Vienna, Austria (2013) 1-10
  4. Datta, R., Bittermann, M.S., Deb, K., Ciftcioglu, Ö.: Probabilistic constraint handling in the framework of joint evolutionary-classical optimization with robotics applications. In: Proc. IEEE Congress on Evolutionary Computation – CEC 2012 at World Congress on Computational Intelligence – WCCI 2012, Brisbane, Australia (2012) 757-764
  5. Erbas, I., Bittermann, M.S., Stouffs, R.: Use of a knowledge model for integrated performance evaluation for housing (re) design towards environmental sustainability: A case study. In: Proc. 14th Int. Conf. Computer Aided Architectural Design - CAAD Futures, Liege, Belgium, (2011) 281-296
  6. Bittermann, M.S.: Sustainable conceptual building design using a cognitive system. In: Proc. 14th Int. Conf. Computer Aided Architectural Design - CAAD Futures, Liège, Belgium, (2011), 297-314
  7. Bittermann, M.S., Sariyildiz, I.S.: An adaptive multi-objective evolutionary algorithm with human-like reasoning for enhanced decision-making in building design. In: Proc. IEEE Symp. Computational Intelligence in Multicriteria Decision-Making – MDCM 2011, Paris, (2011), 105-112
  8. Bittermann, M.S.: A computational design system with cognitive features based on multi-objective evolutionary search with fuzzy information processing. In: Proc. Design Computing and Cognition 2010 – DCC’10, Stuttgart, (2011), 505-524
  9. Bittermann, M.S., Ciftcioglu, O.: A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm. In: Proc. IEEE Conference on Evolutionary Computation – CEC 2009, Trondheim, Norway (2009) 1271-1280
  10. Ciftcioglu Ö., Bittermann M.S.: Solution diversity in multi-objective optimization: A study in virtual reality. In: Proc. IEEE Conference on Evolutionary Computation – CEC 2008 at World Congress on Computational Intelligence WCCI 2008, Hong Kong (2008) 1019-1026
  11. Ciftcioglu Ö.: A fuzzy neural tree for possibilistic reliability. In: Proc. Joint 4th Int. Conf. on Soft Computing and Intelligent Systems - SCIS & ISIS, Nagoya, Japan (2008)
  12. Ciftcioglu Ö., Bittermann M.S.: Multi-objective optimization for cognitive design. In: Proc. Joint 4th Int. Conf. on Soft Computing and Intelligent Systems (SCIS & ISIS), Nagoya, Japan (2008) 1518-1524
  13. Sariyildiz I.S., Bittermann M.S., Ciftcioglu Ö.: Multi-objective optimization in the construction industry. In: Proc. 5th Int. Conf. Innovation in Architecture, Engineering and Construction - AEC 2008, Antalya, Turkey (2008) 1-11
  14. Sariyildiz, I.S., Bittermann, M.S., Ciftcioglu, Ö.: Performance-based Pareto optimal design. In: Proc. Int. Symp. Tools and Methods of Competitive Engineering - TMCE 2008, Izmir, Turkey (2008) 1005-1020
  15. Bittermann, M.S., Sariyildiz, I.S., Ciftcioglu, Ö.: Blur in human vision and increased visual realism in virtual environments. In: Proc. Third Int. Symp. ISVC 2007, Lake Tahoe, Nevada, USA - Lecture Notes in Computer Science 4841, Springer Verlag, Heidelberg (2007) 137-148
  16. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S. Building performance analysis supported by GA. In: Proc. 2007 IEEE Congress on Evolutionary Computation - CEC 2007, Singapore (2007) 489-495
  17. Ciftcioglu, Ö. and Sariyildiz, I.S.: Further studies on visual perception for perceptual robotics. In: Proc. Fourth Int. Conf. Informatics in Control, Automation and Robotics - ICINCO2007, Angers, France (2007) 468-744
  18. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S.: Sensor data fusion in autonomous robotics. In: Proc. The 2nd Int. Conf. Innov. Comp., Inf. and Contr. - ICICIC 2007, Kumamoto, Japan (2007) 1-6
  19. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S.: Fuzzy neural tree for knowledge driven design. In: Proc. The 2nd Int. Conf. Innov. Comp., Inf. and Contr. - ICICIC 2007, Kumamoto, Japan (2007) 2132-2137
  20. Ciftcioglu, Ö., Bittermann, M.S., and Sariyildiz, I.S.: A neural fuzzy system for soft computing. In: Proc. 26th Annual Meeting of the North American Fuzzy Information Processing Society - NAFIPS'07, San Diego, USA (2007) 489-495
  21. Ciftcioglu Ö, Bittermann M.S and Sariyildiz I.S Towards computer-based perception by modeling visual perception: a probabilistic theory. In: Proc.IEEE International Conference on Systems, Man and Cybernetics - SMC 2006,Taipei, Taiwan (2006) 5152-5159
  22. Ciftcioglu Ö, Bittermann M.S and Sariyildiz I.S Fusion of perceptions for perceptual robotics. In: Proc. 25th Annual Meeting of the North American Fuzzy Information Processing Society - NAFIPS’06, Montréal, Québec, Canada (2006) 688-700
  23. Ciftcioglu Ö, Bittermann M.S, and Sariyildiz I.S Studies on visual perception for perceptual robotics. In: Proc. 3rd Int. Conf. on Informatics in Control, Automation and Robotics - ICINCO 2006, Setubal, Portugal (2006) 468-477
  24. Bittermann M.S and Ciftcioglu Ö Real-time measurement of perceptual qualities in conceptual design. In: Proc. 6th Int. Symp. on Tools and Methods of Competitive Engineering -TMCE 2006, Ljubljana, Slovenia (2006) 231-239
  25. Bittermann M.S, Sariyildiz I.S, and Ciftcioglu Ö Visual space perception model Identification by evolutionary search. In: Proc. 9th International Design Conference - Design 2006, Dubrovnik, Croatia (2006) 185-192
  26. Ciftcioglu Ö, Bittermann M.S and Sariyildiz I.S Application of a visual perception model in virtual reality (poster). In: Proc. ACM SIGGRAPH Symp. on Applied Perception in Graphics and Visualization - APGV’2006, Boston, USA (2006) 143 (poster)
  27. Bittermann M.S and Ciftcioglu Ö. Validation of a visual perception model. In: Proc. Joint Int. Conf. on Construction Culture, Innovation, and Management - CCIM, Dubai, United Arabian Emirates (2006) 289-299
  28. Ciftcioglu Ö and I. Sevil Sariyildiz Knowlegde model for knowledge managememnt in the construction industry. In: Proc. Joint Int. Conf. on Construction Culture, Innovation, and Management - CCIM, Dubai, United Arabian Emirates (2006)
  29. Ciftcioglu Ö and Sariyildiz S.I On the efficiency of multivariable TS fuzzy modeling. In: Proc. 2006 IEEE International Conference on Fuzzy Systems, Vancouver, BC, Canada (2006)
  30. Ciftcioglu Ö and Sariyildiz S.I On the efficiency of fuzzy logic for stochastic modeling. In: Proc. 25th Annual Meeting of the North American Fuzzy Information Processing Society - NAFIPS’06, Montréal, Québec, Canada (2006)
  31. Ciftcioglu Ö, Bittermann M.S and Sariyildiz I.S Autonomous robotics by perception. In: Proc. ISCIS & ISIS 2006, Joint 3rd Int. Conf. on Soft Computing and Intelligent Systems and 7th Int. Symp. on Advanced Intelligent Systems, Tokyo, Japan (2006) 1963-1970
  32. Ciftcioglu Ö, Bittermann M.S and Sariyildiz I.S Fuzzy ARX modeling of dynamic systems. In: Proc. ISCIS & ISIS 2006, Joint 3rd Int. Conf. on Soft Computing and Intelligent Systems and 7th Int. Symp. on Advanced Intelligent Systems, Tokyo, Japan (2006)

Recent publications without peer review process (2006-2012)

  1. Bittermann, M.S.: Artificial intelligence versus computational intelligence for treatment of complexity in design. In: Proc. Workshop Assessing the Impact of Complexity Science in Design at Design Computing and Cognition '10 – DCC’10, Stuttgart (2011) 1-8
  2. Bandaru, S., Bittermann, M.S.,Deb, K.: Discovering design principles for soft multi-objective decision-making. Technical Report nr. 2011015, Kanpur Genetic Algorithm Laboratory, IITK Kanpur, India (2011) pp. 1-21, presented at 21st Int. Conf. on Multiple Criteria Decision Making - MCDM 2011, Jyväskylä, Finland, (2011)
  3. Bittermann, M.S., Ciftcioglu, Ö.: Systematic measurement of perceptual design qualities. In: Proc. ECCS 2005 Satellite Workshop: Embracing Complexity in Design at Europ. Conf. Complex Systems,Paris, France (2005) 15-22

 

Computational Cradle to Cradle

Ciftcioglu, Ö., Bittermann, M.S., Computational Cradle to Cradle - Generic Approach for Cradle to Cradle. presented on January 30 at C2C Lab TU Delft.

Multi-dimensional performance analysis

Evaluation of the a decision needs consideration of many facts at the same time. A multi-dimensional analysis model is a model to compute the suitability of a decision, where every dimension refers to a certain decision aspect. Using such a model the suitability of a decision is computed with respect to multiple dimensions at the same time. A method to establish such a model is a neuro fuzzy modeling.

Multi-dimensional analysis model using a neuro-fuzzy systemknown as fuzzy neural tree

Nonlinear mapping at an inner node of a fuzzy neural tree

A neural fuzzy system for soft computing. Proc. NAFIPS 2007, San Diego, USA (2007) 489-495

In a neuro fuzzy system the linguistic concepts involved in the decision analysis, such as sustainability, functionality, etc. are represented by means of neurons performing a non-linear mapping from the neuron's input to its output, simulating a reasoning activity in brain.The neuro fuzzy system we developed for decision analysis is different from artificial neural networks in the sense that the latter are established using training data to optimize the model parameters being the weight connections among nodes, whereas the method we developed optimizes the activation function in the neuron while the connections weights are fixed. This way our method is able to model deep knowledge from already existing knowledge, whereas ANN identify knoweldge from data, i.e. ANN are used for data-driven knowedge modelling, while fuzzy neural trees are used for knoweldge-driven knowledge modelling.

Illustration of fuzzy information processing at a neuron to obtain the design performance.

A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm , IEEE Congress on Evolutionary Computation –CEC 2009, Trondheim, Norway, 18-21st May 2009

Computational Intelligence for Enhanced Decision Making in Engineering and Design

In this approach a multi-dimensional performance model is integrated into a computational search process.

Multi-dimensional performance-based design by means of a cognitive system using evolutionary computation & fuzzy logic

A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm, IEEE Congress on Evolutionary Computation –CEC 2009, Trondheim, Norway, 18-21st May 2009

This way design parameters are incorporated into a complex algorithm, namely evolutionary algorithm with fuzzy neural computation, that finds the best set of solutions to meet the objectives set by the design team.

Visual representation of optimal solutions for two objectives in the urban design

The solutions obtained in this way are known as Pareto-optimal front. They provide a variety of outstanding alternatives to a decision maker, since none of these solutions is outperformed by another one. Every solution is equally valid, and a decision maker selects among them with great confidence.

Visual representation of optimal solutions for four objectives in the interior design task

As a computational solution set has been built, alternate designs are explored by varying the parameters. The generative system can handle effectively up to five objectives, and has no restriction regarding the number of variables playing role on the objectives. The amount of variables characterizing a solution is only limited by available computational time and power. For more than four objectives the five-dimensional Pareto front can be represented as well.

Visual representation of optimal solutions for five objectives

The strength of the approach is that solutions can be assessed without any presupposition, and confidence of finding the best solution is increased. Human and computational cognitive system are in an interaction loop: Human decision maker is setting the criteria, computations privide optimal solutions for these, based on these solutions the decision maker modifies criteria and so on, until a Pareto-optimal solution matches the designer's complete preferences as far as possible.

Two Pareto optimal solutions generated by a multi-dimensional performance-based design system

Solution Diversity in Multi-Objective Optimization: A study in Virtual Reality. World Congress on Computational Intelligence WCCI 2008, Hong Kong (2008)

One of the Pareto optimal solutions for an interior design task, where visual perception plays a role in the computational optimisation

A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm, IEEE Congress on Evolutionary Computation –CEC 2009, Trondheim, Norway, 18-21st May 2009

Perception modeling

Architectural design involves perception-based requirements, such as visual openness or visual privacy. Such requirements are challenging to treat, because the human vision process is highly complex, involving brain processes. Therefore the comparison of perceptual properties among scenes is imprecise.

To let perception play a more prominent role in design, a model of human vision is developed. The model is based on probabilistic terms. This way the complexity of the vision process is absorbed.

Unbiased visual attention for a nearby object

Unbiased visual attention for a distant object

The model is implemented by means of an avatar in virtual reality. The avatar experiences the environment in a human-like manner, so that the results are used during the evaluation of design alternatives.

From perceptual towards cognitive robotics in the framework of evolutionary computation. In: Pennacchio, S. (ed.): Emerging Technologies, Robotics and Control Systems. InternationalSAR, Palermo, Italy (2009)

Probability density of perception for objects that are oriented perpendicular to the observer's forward direction

Visual perception theory underlying perceptual navigation. In: Emerging Technologies, Robotics and Control Systems International Society for Advanced Research (2007) 139-153

Perception measurement in virtual reality.

Towards computer-based perception by modeling visual perception: a probabilistic theory. Proc. IEEE International Conference on Systems, Man and Cybernetics, October 8-11, 2006, Taipei, Taiwan.

Perception analysis of an interior space

The authors of the publications are with the Chair of Design Informatics, Delft University of Technology, Faculty of Architecture, Dept. of Architectural Engineering and Technology,Julianalaan 134, 2628 BL Delft , NL | Email:o.ciftcioglu@remove-this.tudelft.nl; m.s.bittermann@remove-this.tudelft.nl;i.s.sariyildiz@remove-this.tudelft.nl | Tel: +31-6 39250915| Tel: +31-6 39250901

Naam auteur: Bittermann
© 2014 TU Delft

Metamenu