Comparison of machine learning methods for classification of Bandar Kong windcatchers
محورهای موضوعی : Space Ontology International JournalMona Mohtaj 1 , Mansoureh Tahbaz 2 , Atefeh Dehghan Touranposhti 3
1 - Department of Architecture College of Art and architecture, West Tehran Branch, Islamic Azad University, Tehran, Iran
2 - Faculty of Architecture and Urbanism, Shahid Beheshti University, Tehran , Iran.
3 - Department of Architecture College of Art and architecture, West Tehran Branch, Islamic Azad University, Tehran, Iran.
کلید واژه: Machine Learning, Similarity, Clustering, Anaconda,
چکیده مقاله :
Hot and humid region of Iran is one of the hardest climates in the world. Due to its proximity to the sea and in order to use of coastal winds, windcatcher is one of the architectural elements of these areas, including Bandar Kong. Classification of architectural types is the first step in understanding the features governing architecture. This research aims to classify the catchers of Bandar Kong using machine learning methods. For this purpose, the plans of Bandar Kong have been categorized in two General ways, based on shape and characteristics of plans and the results have been compared. In the first method, the similarity of 35 windcatchers is calculated using the Cosine Distance method in Anaconda3.9 .each plans is compared 34 times with other plans. In second step plans are are clustered using using Clustmap from Seaborn Library. In the next method, the characteristics of windcatchers such as length, width and location of windcatcher have been extracted from each plan and classified in Anaconda using complete linkage and average linkage methods from Numpy library. Windcatcher plans had been divided to 6, 5 and 4 clusters using different methods. The clusters show that clustering based on images, had placed more similar plans in one cluster.
Hot and humid region of Iran is one of the hardest climates in the world. Due to its proximity to the sea and in order to use of coastal winds, windcatcher is one of the architectural elements of these areas, including Bandar Kong. Classification of architectural types is the first step in understanding the features governing architecture. This research aims to classify the catchers of Bandar Kong using machine learning methods. For this purpose, the plans of Bandar Kong have been categorized in two General ways, based on shape and characteristics of plans and the results have been compared. In the first method, the similarity of 35 windcatchers is calculated using the Cosine Distance method in Anaconda3.9 .each plans is compared 34 times with other plans. In second step plans are are clustered using using Clustmap from Seaborn Library. In the next method, the characteristics of windcatchers such as length, width and location of windcatcher have been extracted from each plan and classified in Anaconda using complete linkage and average linkage methods from Numpy library. Windcatcher plans had been divided to 6, 5 and 4 clusters using different methods. The clusters show that clustering based on images, had placed more similar plans in one cluster.
Araldi, A., Emsellem, D., Fusco, G., Tettamanzi, A., & Overal, D. (2021). Exploring building typologies through fast iterative Bayesian clustering. In SAGEO’2021 (pp. 113-124).
Arkin, E. M., Chew, L. P., Huttenlocher, D. P., Kedem, K., & Mitchell, J. S. (1989). An efficiently computable metric for comparing polygonal shapes. Cornell University Operations Research and Industrial Engineering.
Babakhani, R., & Keifari, A. (2021). Explaining the evolution of Iranian traditional house spaces based on distance measurement method of plan similarity vector. Space Ontology International Journal, 10(4), 97-103.
Carter, D. J., & Whitehead, B. (1975). The use of cluster analysis in multi-storey layout planning. Building Science, 10(4), 287-296.
Chang, C. C., Hwang, S. M., & Buehrer, D. J. (1991). A shape recognition scheme based on relative distances of feature points from the centroid. Pattern recognition, 24(11), 1053-1063.
Collins, J., & Okada, K. (2012, September). A Comparative Study of Similarity Measures for Content-Based Medical Image Retrieval. In CLEF (Online Working Notes/Labs/Workshop) (pp. 2-7).
Ezavan, Amin, Babakhani, Reza (1400). Analysis of the structure of the opening form of the bridges of the Safavid period. Environmental science and technology (105)
Farhadi, Marzieh, Jamzadeh, Mansour (2017) Examining similarity criteria in content-based image retrieval. Computer Science, (21), 13-27.
Feist, S., Sanhudo, L., Esteves, V., Pires, M., & Costa, A. A. (2022). Semi-supervised clustering for architectural modularisation. Buildings, 12(3), 303.
Grosswendt, A., & Roeglin, H. (2017). Improved analysis of complete-linkage clustering. Algorithmica, 78, 1131-1150.
Hu, R., Huang, Z., Tang, Y., Van Kaick, O., Zhang, H., & Huang, H. (2020). Graph2plan: Learning floorplan generation from layout graphs. ACM Transactions on Graphics (TOG), 39(4), 118-1.
Jarman, A. M. (2020). Hierarchical cluster analysis: Comparison of single linkage, complete linkage, average linkage and centroid linkage method. Georgia Southern University, 29.
Mousavi, M., & Afzalian, K. (2019). Morphological Analysis of Modern Residential Architecture in Turkey and Iran (Case Study: Chankaya Palace and Sa'ad Abad Palace). Journal of Iranian Architecture & Urbanism (JIAU), 10(1), 113-126.
Nabi Lo, Maryam, Daneshpour, Negin, 2014, a new hybrid clustering algorithm in category data approach
RahmatNia, A., & Hayati, H. The role of traditional medicine and human physiology in Iranian bath architecture: A case study of Kahyar Dehdasht bath, Ali Gholi Agha public bath in Isfahan, Vakil bath in Shiraz, and Bokan bath in Behbahan.
Rodrigues, E., Sousa-Rodrigues, D., de Sampayo, M. T., Gaspar, A. R., Gomes, Á., & Antunes, C. H. (2017). Clustering of architectural floor plans: A comparison of shape representations. Automation in Construction, 80, 48-65.
Ryan P.Adams, 2019, Hierarchical clusterin, Cos 324-Element of Machine Learning, Prinston University.
Sajjanhar, A., & Lu, G. (1997). A grid-based shape indexing and retrieval method. Australian Computer Journal, 29(4), 131-140.
Saxena, A., Prasad, M., Gupta, A., Bharill, N., Patel, O. P., Tiwari, A., ... & Lin, C. T. (2017). A review of clustering techniques and developments. Neurocomputing, 267, 664-681.
Seawright, J., & Gerring, J. (2008). Case selection techniques in case study research: A menu of qualitative and quantitative options. Political research quarterly, 61(2), 294-308.
Serafrazi, Abbas, 2017, half a century after clustering: review and evaluation of clustering approaches and methods with multi-criteria decision analysis, Research Quarterly in Engineering Sciences and Technology, Volume 4, Number 2, Taistan 2017, 65-84
Shah Hosseini, Habib, Khandani, Nadia, Korepaz, Rana (1401) Systematic evaluation of architectural articles in Iranian scientific-research journals and Elsevier publications (q1). Bagh Nazar (115), 5-20
Shah Mohammadi, Nima, Babakhani, Reza (1400). Analysis of the writing pattern of Nasir al-Molk mosque sashes based on the effects of environmental psychology on the psychological perceptions of users. Environmental Science and Technology, Journal 23(8): 37-46
Shih, C. Y., & Peng, C. H. (2022). Floor Plan Exploration Framework Based on Similarity Distances. arXiv preprint arXiv:2211.07331.
Son, K., & Hyun, K. H. (2021). A framework for multivariate data based floor plan retrieval and generation. In 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections. The Association for Computer-Aided Architectural Design Research in Asia, Hong Kong (Vol. 29, No. 03, pp. 2021-01).
Son, K., & Hyun, K. H. (2022). Designer-centric spatial design support. Automation in Construction, 137, 104195.
Strauss, Anselm, Corbin, Juliet, (2017) Fundamentals of qualitative research - techniques and stages of producing grounded theory. Translated by Ebrahim Afshar, Tehran: Nei Publishing House, 7th edition.
Vakilinejad, Roza, Mofidi, Majid, Mahdizadeh Siraj, Fatemeh (2012), The combined effect of building envelope and ventilation patterns on energy consumption in residential buildings.
Varzan, Milad (1400), Machine Learning and General Data: Basics, Concepts, Algorithms and Tools, Tehran: Miyad Andisheh.
Xiao, R. (2021). Comparing and clustering residential layouts using a novel measure of grating difference. Nexus Network Journal, 23(1), 187-208.
Yousif, S., & Yan, W. (2019). Shape clustering using k-medoids in architectural form finding. In Computer-Aided Architectural Design." Hello, Culture" 18th International Conference, CAAD Futures (2019), Daejeon, Republic of Korea, June 26–28, 2019, Selected Papers 18 (pp. 459-473). Springer Singapore.
