Presenting a Predictive Model of Residential Facade Preferences Using Machine Learning Case Study: Tehran

Document Type : Original Article

Authors

1 MA in Urban Design, Faculty of Architecture and Urban Planning, University of Art, Tehran, Iran

2 Associate Professor, Department of Urban Design, Faculty of Architecture and Urban Planning, University of Art, Tehran, Iran

Abstract

The issue of urban facade preferences for users is one of the most important issues in the field of urban design. The answer to this question has been considered by researchers in the form of various objective and subjective methods. This study intends to use machine learning method as a predictable approach to evaluate the preferences and also desirability of urban facades for users. Therefore, the aim of the research is to design a predictive model that its output is the level of user preferences of residential facades in Tehran. According to the expected output, the data provided to the model consists of residential facade image. Due to the necessity of standard data in the machine learning process, residential facade images submitted to the Tehran City Facade and Landscape Commission in the years 2016 to 2019 have been used. Out of the original 800 images, 278 images were chosen in selection process. The input of this predictive model is images along with features. The features considered in this research have been obtained using the approach of visual preferences and image processing. The issue of whether the physical characteristics related to the visual preferences approach and the statistical characteristics obtained with the image processing technique both have an effect on the level of visual preference was tested with machine learning and the results showed that the use of both the feature provide better results. Since the supervised machine learning method has been used, it was necessary to present the labels to the machine. Therefore the number of preferences were carried out through an online questionnaire by users (218) in four categories of low preferences (0-25%), medium (50-26%), good (51-75%) and very good (100-76%). By selecting the models and determining the amount of 80 to 20 as the training to test data volume, the learning process was carried out and then using the confusion matrix, the validity of the models used in machine learning was tested. Also, to ensure the predictability of the machine, at the end, some new facades which were neither training nor test data were presented to the machine and the degree of predictability of their visual preference was checked by the machine and with the result of the survey. Based on the results, three algorithms of support vector machine, decision tree and random forest with 100% accuracy and X-G-Boost method with 97% accuracy have performed best. Based on the results, the importance of the influence of elements on users' preferences, includes the minimum distance between windows, the ratio of transparent to opaque surface in the facade, the presence of gardens in the balcony, the variety of materials, the maximum distance between windows, the number of openings, the length of the balcony, the number of balconies, the number of floors, the variety of colors, the decorations used on the roof, the type of roof lines (continuous, discontinuous), the number of entrances, and the ratio of the height to the length of the building.

Keywords

Main Subjects

References

پاکزاد، جهانشاه، و بزرگ، حمیده (1395). الفبای روان‌شناسی محیط برای طراحان، چاپ چهارم. تهران: انتشارات آرمان‌شهر.
رنجبر، هادی، حق‌دوست، علی‌اکبر، صلصالی، مهوش، خوشدل، علیرضا، سلیمانی، محمدعلی، و بهرامی، نسیم (1391). نمونه‌گیری در پژوهش‌های کیفی: راهنمایی برای شروع. مجله علمی ‌پژوهشی دانشگاه علوم پزشکی ارتش جمهوری اسلامی ایران، 10(3)، 238- 250.
رشید قلم، پریچهر (1395). سنجش تأثیرگذاری مطلوبیت بصری بر حضورپذیری استفاده‌کنندگان از فضا مبتنی بر تکنیک پردازش تصویر، نمونه موردی خیابان سی تیر، منطقه 12 شهرداری تهران. پایان‌نامه برای دریافت درجه کارشناسی شهرسازی، دانشگاه هنر.
شاهین راد، بهنوش، رفیعیان، مجتبی، و پورجعفر، محمدرضا (1394). ارزیابی ترجیحات بصری زنان از فضاهای شهری تهران. فصلنامه تازه‌های علوم‌شناختی، 17(1)، 24-10.
گونزالز، رافائل، و وودز، ریچارد یوجین (1333). پردازش دیجیتالی تصاویر، (مترجمان: مجتبی لطفی‌زاده، امیر‌‌مسعود عموئی، حمید‌رضا محمد‌شیرازی، سعید میرقاسمی). چاپ پنجم، تهران: انتشارات نیاز دانش.
کیم، فیل (1399). یادگیری عمیق با متلب، (مترجمان: جواد وحیدی و محمد رحیمی). بابل: انتشارات فناوری نوین.
مقسمی، حمیدرضا، و علیزاده سواره، بهروز (1397). شبکه‌های عصبی با متلب و سی پلاس. تهران: نیاز دانش.
Abdi, A. (2016). Three types of Machine Learning Algorithms, Netherlands, Enschede: University of Twente, 1-50.
Anurag, V. Xiaodai, D. (2016). Detection of Ventricular Fibrillation Using Random Forest Classifier. Journal of Biomedical Science and Engineering, 9(5), 1-33.
Batarseh, F. & Yang, R. (2020). Data Democracy: At the Nexus of Artificial Intelligence, Software Development, and Knowledge Engineering. Durham City: Academic Pess.
Bin, I. (1984). Visual Preferences in Enclosed Urban An Exploration of a Scientific Approach to Environmental Design. Environment and Behavior Journal, 16 (2), 235-262.
Chen, T. & Guestrin, C. (2016). Xgboost: A Scalable Tree Boosting Syste. 22nd acm sigkdd international conference on knowledge discovery and data mining, New York.
Cohen, L. (1996). Observing Responses, Visual Preferences and Habituation to Visual Stimuli in Infants. Journal of Experimental Child Psychology, 7, 419-433.
Dacci, L. (2019). Aesthetical cognitive perceptions of urban street form, Pedestrian  preferences towards straight or curvy route shapes.  Journal of Urban Design, 24( 6), 896–912.
Gupta, R. & Gola, K. (2020). Analysis of Machine Learning for Processing Big Data in High Performance Computing. EAI Endorsed Transactions on Cloud Systems, 6(19), 1-12.
Glukhova, D. Katilova, J. Krupina, A. (2018). Graphic-Analytical Method in Architectural Assessment Urban Visual Environment, MATEC Web of Conferences 245.
Hernandez, J. & Marcotegui, B. (2013). Morphological Segmentation of Building Facade Images. 16 th IEEEI nternational Conference on Image Processing, Le Caire.
Khastou, M. & Najafi charmini, H. (2015). Organizing The Urban landscape with Emphasis on legibility, Using Visual Preference Technique (V.P.T) (case study: Khayyam Street of Qazvin). International journal of architecture and urban development, 5(2), 43-56.
Kang, K. Bakar, A. (2013). A Nightscape Preference Study Using Eye Movement Analysis. Journal Universiti Putra Malaysia, 6(2), 85-99.
Kozlova, N. (2018). Architectural  Organization Of Facades According to The Principle of Variability: Videoecological Aspect. Journal of Architecture and Urbanism, 42(1), 52-62.
Kozlova, N. (2016). Contemporary Facades Of Multistorey Residential Building In Kiev:Videoecological Aspect. Journal of Spaium,1(36) , 24-33.
Krstinic, D., Braovic, M., Seric, L., & Bozic-Stulic, D. (2020). Multi-Label Classifer Performance Evaluation with Confusion Matrix. AIRCC Publishing Corporation, 10(18), 1-14.
Krosl, K., Bauer, D., Schwarzler, M., Fuchs, H.,  Suter, G., & Wimmer, M. (2018). A VR-Based User Study On The Effects Of Vision Impairments On Recognition Distances Of Escape-route Signs In Buildings. The Visual Computer Journal, 34(6), 911-923.
Kukhta, M., & Pelvin, Y. (2014).The Specifics Of Creating Emotional Comfort By Means Of Modern Design. Social and Behavioral Sciences Journal, 166, 199 – 203.
Leopord, H.,  Kipruto Cheruiyot, W., &  Kimani, S. (2016). A Survey and Analysis on Classification and Regression Data Mining Techniques for Diseases Outbreak Prediction in Datasets. The International Journal Of Engineering And Science, 5(9), 1-11.
Liu, C., & Gagalowicz, A. (2010). Image-based Modeling of Haussmannian Facades. The International Journal of Virtual Reality, 9(1), 13-18.
Liu, l. Silva, E. Wu, Ch. Wamg, H. (2017). A machine learning-based method for the large-scale evaluation of the qualities of the urban environment, Computers. Environment and Urban Systems Journal, 65, 113-125.
Liu, H. Zhang, J. Zhu, J. C.H. Hoi, S. (2012). DeepFacade: A Deep Learning Approach to Facade Parsing. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne.
Laupheimer, D.,  Tutzauer, P.,  Haala, N. & Spicker, M. (2018). Neral Networks For the Classification of Building Use From Srteet: View Imagery, ISPRS Annals of the Photogrammetry. Remote Sensing and Spatial Information Sciences, 2, 177-184.
Luchinin, N., Asylgaraeva, M., Startsev, S., & Samosudova, N. (2018). Characterization Of The New Dormitory Towns Visual Environments And Its Perceptual Influence On Their Residents. MATEC Web of Conferences,
Malhotra, V., & Semwal, M. (2019). Comparison of 3 Supervised Machine Learning Models. Phd Thesis, University of Windsor.
Mishra, S., & Kolay, S. (2019). Visual Perception of the Street Facade of a Historic Town, Case Study of the Walled City of Jaipur, India. Springer Nature Singapore, 2, 377-389.
Mechelli, A., & Vieira, S. (2020). Machine Learning Methods and Applications to Brain Disorders. Durham City: Academic Press.
Natalya, Z., Lyudmila, S., Lyudmila, M., Svetlana, L., & Anna, Ch. (2014). Eye Tracking and Autonomic Nervous System Reactivity During Perception of Visual Environments of Different Comfort. European Scientific Journal, 3, 1857 –7881.
Nelessen, A., & Constantine, J. (1993). Understanding & Making Use of People's Visual Preferences. Planning cimmissioners journal , 9, 12-14.
Noland, R., Weiner, M., Gao, D., Cook, M., & Nelessen, A. (2016). Eye-Tracking Technology, Visual Preference Surveys, and Urban Design:Preliminary Evidence of an Effective Methodology. Journal of Urbanism: International Research on Placemaking and Urban Sustainability, 10(1), 1-11.
Novack, T., Vorbeck, L., Lorei, H., & Zipf, A. (2020). Towards Detecting Building Facades with Graffiti Artwork Based on Street View Images. International Journal of Geo-Information, 9(2), 1-17.
Pourjafar, M. & Baba Abbasi, M. (2015). Improving the Quality of Urban Spaces Through Image Processing, Case Study: 17th-Shahrivar Street of Tehran. Journal of Armanshahr Architecture & Urban Development, 8(14), 119-130.
Pourdehghan, H., Shahcheraghi, A., Mokhtabad, M., & Majedi, H. (2017). Evaluating Visual Preferences of Architects and People Toward Housing Facades, Using Multidimensional Scaling Analysis. Space Ontology International Journal, 6(4), 7585.
Quercia, D, Aiello, L.(2017). Good City Life: Crowdsourcing Satellite Data and Emotions to Map Our Urban Landscape, Retrieved, 2017 from https://www.eurisy.eu/stories/good-city-life-crowdsourcing-satellite-data-and-emotions-to-map-our-urban-landscape_241. Pdf.
Prashantha, D., Mehta, V., & Sharma, N. (2019). Classification of Handwritten Devanagari Number – An analysis of Pattern Recognition Tool using Neural Network and CNN. International Conference on Computational Intelligence and Data Science, India, 1672445-2457.
Rahn, S. (2014). Visualizing Living Streets in North St. Paul, A Visual Preference Survey in the Casey Lake Neighborhood, Minneapolis City, Hubert H. Humphrey School of Public Affairs.
Ray, S. (2018). A Comparative Analysis and Testing of Supervised Machine Learning Algorithms. International Journal of Advanced Computer Science and Applications, 10(12) , 1-8.
Ridzuan, F., Nazmee, W., & Zainon, W. (2019). A Review on Data Cleansing Methods for Big Data. The Fifth Information Systems International Conference 2019, Penang, 731–738.
          Safavian, R., & Landgrebe, D. (1991). A Survey Of Decision Tree Classifier Methodolog. Reprinted From IEEE Transactions On Systems, Man, and Cybernetics, 21(3), 660-674.
Santosa, H., Kobayashi, Sh., & Kobayashi, T. (2012). Study of visual preferences on the  growth of urban commercial  streetscape through building owners assessment. 11 International Conference on Design & Decision Support Systems 2012 in Architecture and Urban Planning,  Eindhoven.
Shahhoseini, H., Bin, M.K., & Bin Maulan, S. (2015). Visual Preferences of Small Urban Parks Based on Spatial Configuration of Place. International Journal of Architectural Engineering & Urban Planning, 25(2), 84-91.
Stamps, A. (1999). Sex, Complexity, And Preferences For Residential Facades. Institute of Environmental Quality, SAGE Journal, 88(3),1301-1312.
Tucker, C., Ostwald, M., & Marshall, J. (2004). A Method For The Visual analysis of The Streetscape. 38th Annual Conference of the Architectural Science Association ANZAScA and the International Building Performance Simulation Association, Australia.
Tsvetkov, O., Simankina, T., & Karmokova, K. (2019). Video-Ecological Coefficient Of Real Estate Objects. E3S Web of Conferences , Moscow.
Upadhyay, D., Manero, J., Zaman, M., & Sampalli, S. (2017). Gradient Boosting Feature Selection with Machine Learning Classifiers for Intrusion Detection on Power Grids. IEEE transactions on network and service management, 18(1), 1-14.
Wang, S., Liu, H., & Tang, J. (2016). Encyclopedia of Machine Learning and Data Mining. New York City: Springer New York, NY publisher.
Xie, X., Murphy, C.,  Kaiserc, G., Xue, B., & Yueh Chena, T. (2011). Testing and Validating Machine learning Classifiers by Metamorphic Testing. The Journal of Systems and Software, 84(4), 544-558.
Zou, H., Zhu, J., Hastie, T., & Rosset, S. (2009). Multi-Class Adaboost. Statistics and its Interface Journal, (2)1, 349-360.
Zhou, Z. Liu, J. (2022). A Review of Ensemble Learning Algorithms Used in Remote Sensing Applications. MDPI Journals, (12)7, 270-281.
Zhou, Z., & Hooker, G. (2020). Unbiased Measurement of Feature Importance in Tree-Based Methods. Journal of ACM Transactions on Knowledge Discovery from Data, (15)2, 1-21.
Zyagina, N., Taleeva, A., & Kuznetsova, D. (2019). Physiological Markers Of Visual Environment Comfort In  The North. Earth and Environmental Science, 263, 1-7.
 
 
Journal of Architecture and Urban Planning
Volume 16, Issue 41
December 2023
Pages 23-44

Files

Share

How to cite

Statistics