Explain the theoretical model of the arrangement of facade elements using distance measuring vector in automatic facade design intelligence

Subject Areas : Architecture and urbanism

Mahsa Safarnezhad Samarin ¹ , azadeh Shahcheraghi ² , hossein zabihi ³

1 - PhD of Architecture, Researcher, Department of Architecture, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - PhD of Architecture, Associate Professor, Department of Architecture, Science and Research Branch, Islamic Azad University, Tehran, Iran. *(Corresponding Author)
3 - , PhD of Architecture, Associate Professor of Urban Planning, Department of Art and Architecture, Science and Research Branch, Islamic Azad University, Tehran, Iran

Received: 2021-01-13 Accepted : 2021-09-01 Published : 2024-08-22

Keywords: Computational design, Automated design intelligence, Facade layout, Residential buildings. ,

Abstract :

Background and Objectives: Machine learning is one of the emerging issues in architectural research that seeks to design and draw architectural plans such as plans and facades with the help of machine learning algorithms. In fact, researchers in the field of computational design of building facades have long been looking for approaches that can enable the artificial intelligence factor to participate in the creation of architectural designs. Therefore, the purpose of this study is to find the answer to the question of what theoretical model can ultimately be fruitful for the arrangement of building elements through machine learning so that the computational process required to implement these elements by automated facade design intelligence with Make machine learning algorithms possible   

Material and Methodology: The research method is a combination of library studies and mathematical calculations as well as the use of books on national building regulations in relation to the facade.

Finding: The research findings show that using Euclidean and Manhattan mathematical relations with the conversion of facade data into unique vectors as well as the conversion of national regulation data and facade design standards to numerical vectors, with the help of Python programming language And KNN's nearest neighbor classification algorithms achieved good results.

Discussion and conclusion: And finally, the results show that the arrangement of the main elements of the facade can be drawn from architectural plans with the help of artificial intelligence algorithm, reading and facade of residential buildings based on architectural plans.

References:

1. Raza Khan, Mustakeem,. Gupta, S.K,& Kumar, Rakesh. (2018). Role of Computer’s Tech nology: Architectural Design. International Journal for Research in Applied Science & Engineering Technology (IJRASET). pp 2936-2942. ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 6.887. http://doi.org/10.22214/ijraset.2018.5479.
2. Alexander, C. (1967). Notes on the Synthesis of Form, Cambridge: Harvard University Press.
3. Russell, S. J. and P. Norvig. (2016). Artificial Intelligence: A Modern Approach. 3rd ed. Boston: Pearson Education.
4. Newton, David. (2019). Generative Deep Learning in Architectural Design. Technology|Architecture + Design, 3:2, 176-189, DOI: 10.1080/24751448.2019.1640536.
5. Goodfellow, I. J., J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville, and Y. Bengio. 2014. “Generative Adversarial Nets.” In Proceedings of the Twenty-Seventh International Conference on Neural Information Processing Systems (NIPS), 2:2672–2680. Montreal, Canada, December 8–13.
6. Reddy TE, et al. (2007) Positional clustering improves computational binding site detection and identifies novel cis-regulatory sites in mammalian GABAA receptor subunit genes. Nucleic Acids Res 35(3): e20.
7. Thompson, D.B. and Miner, R.G. (2007) Building Information Modeling - BIM: Contractual Risks are Changing with Technology, online at http://www.aepronet.org/ge/no35.html .
8. Cudzik, Jan, & Radziszewski, Kacper . (2018). Artificial Intelligence Aided Architectural Design. AI FOR DESIGN AND BUILT ENVIRONMENT. 77-84. https://www.researchgate.net/publication/328018944.
9. Goertzel, B 2006, The Hidden Pattern, Brown Walker Press, Florida.
10. Isaev, lya and Smetannikov, Ivan. (2016). Optimization of filter ensemble algorithm withparallel computing. InIFIP International Conference on Artificial Intelligence Applica-tions and Innovations, pages 341–347.
11. Moore, GE 2006, ’Cramming more components onto integrated circuits’, IEEE Solid-State Circuits Society Newsletter, 11(3), pp. 33-35.
12. Jordan, M. I. and Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. sciencemag.org. ISSUE 6245. 260-255.
13. Mohri, M, Rostamizadeh, A and Talwalkar, A (2012), Foundations of Machine Learning, MIT Press, New York.
14. Garcia Belém, Catarina,. Santos, Luis, & Menezes Leitão, António (2019). On the Impact of Machine Learning Architecture without Architects?. Conference: CAAD Futures 2019, At: Daejon, South Korea. https://www.researchgate.net/publication/335175592.
15. Deo, R. C. (2015). Machine Learning in Medicine.Architectural Education in the 21st Century. First International Conference on Critical Digital. Design Studies. https://www.academia.edu/25884262/The_impact_of_information_technology_on_design_methods_products_and_practices.
16. Ferreira, D. R. (2018) Applications of Deep Learning to Nuclear Fusion Research.
17. Bolton, R. J., & Hand, D. J.(2015). Statistical Fraud Detection: A review. Statistical Science, 17(3), 235–255.
18. Behera, R. N., & Das, K. (2017). A Survey on Machine Learning: Concept, Algorithm and Applications. International Journal of Innovative Research in Computer and Communication Engineering, 5(2).
19. Khean, N., Fabbri, A., & Haeusler, M. H. (2018). Learning Machine Learning as an Architect, How to?.
20. Steinfeld, K. (2017). Dreams May Come. In Acadia 2017, 590–599.
21. Claus L. Cramer-Petersen, Bo T. Christensen, Saeema Ahmed-Kristensen. (2019). Empirically analysing design reasoning patterns: Abductive-deductive reasoning patterns dominate design idea generation, Design Studies, 60, 39-70.
22. Samalavicius, Almantas. (2019). Architecture, City and Mathematics: The Lost Connection, Mathematics Interdisciplinary Research, 1-10. to the Future, Volume I: Antiquity to the 1500s, Birkhäuser Basel.
23. Zappulla, Carmelo. (2013). Connections Between Architectural Design and Mathematical Patterns. Materials Architecture Design Environment. https://www.academia.edu/5309062/Connections_Between_Architectural_Design_and_Mathematical_Patterns.
24. K. Terzidis,(2006). Algorithmic Architecture (Oxford: Architectural Press), p. xii.
25. Williams.k and. Ostwald. M. J. (2015). Architecture and Mathematics from Antiquity.
26. EA, Botchway,. SA, Abanyie, & SO, Afram (2015). The Impact of Computer Aided Architectural Design Tools on Architectural Design Education. The Case of KNUST. Architectural Engineering Technology, 1-6. http://dx.doi.org/10.4172/2168-9717.1000145.
27. E. Kalay, Yehuda. (2006). The Impact of Information Technology on design methods, products and practices, Design Studies, 27(3): 357-380, https://doi.org/10.1016/j.destud.2005.11.001
28. Sariyildiz, S. & S. Ozsariyildiz. S. (1998). The future of Architectural Design Practice within ICT developments. omputerised Craftsmanship, eCAADe Conference Proceedings, Paris, September 24-26, http://resolver.tudelft.nl/uuid:87601877-406e-487a-9122-64d91798d4f8.
29. Malaeb, Jamal,& Ma, Wejung. (2019). Artificial Intelligence in Architecture, GENERAL UNDERSTANDING AND PROSPECTIVE STUDIES, i-14.
30. Likai, WEI. (2018). AI Concepts in Architectural Design. IOP Conf. Series: Materials Science and Engineering 392, doi:10.1088/1757-899X/392/6/062016.
31. As, Imdat,. Pal, Siddharth, & Basu, Prithwish (2018). Artificial intelligence in architecture: Generating conceptual design via deep learning. International Journal of Architectural Computing 306– 327. DOI: 10.1177/1478077118800982.
32. Mathias, Markus, Martinovic, Andelo, Weissenberg, Julien, & Van Gool, Luc. (2012). Automatic architectural style recognition. • ISPRS - International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences XXXVIII-5/W16(5):171-176. DOI: 10.5194/isprsarchives-XXXVIII-5-W16-171-2011.
33. Dolnicar, Sara., Grün, Bettina, & Leisch, Friedrich (2018). Step 5: Extracting Segments. Market Segmentation Analysis pp 75-181.https://doi.org/10.1007/978-981-10-8818-6_7.