Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Human Preference for Architectural Shape using CNN

CNN을 이용한 건축적 형상에 대한 선호 추정

  • Received : 2012.08.02
  • Accepted : 2022.03.28
  • Published : 2022.04.30
⟨ Previous Next ⟩

Abstract

This study aims to explore the possibility that artificial intelligence can identify human preferences through images using the convolutional neural network (CNN). To determine if people had a consistent preference for form, experiment participants were asked to select the preferred images among 200 images twice, which were automatically generated in dynamo. In the two consecutive image selection processes, ten participants repeatedly selected the same images at a rate of 79 percent. These results confirmed that there is a consistent preference for form. Next, the possibility of identifying the preference for form using CNN was investigated. Data for each experiment participant was divided into two sets. The preferred and non-preferred images were included in each set at a certain percentage. A classification model was produced by conducting supervised learning using CNN with one of the two sets. The classification accuracy was measured by applying this classification model to the other set. As a result of these tests, the classification model created by CNN could classify the preferred and non-preferred images with 82.7 percent accuracy. In random selection, the probability of correctly classifying the preferred and non-preferred images with more than 82.7 percent accuracy was 6.5 × 10-12 percent. Therefore, 82.7 percent reflects a fairly high classification accuracy. Based on this high accuracy, it was possible to identify human preferences for form using CNN

Keywords

Acknowledgement

이 연구는 정부(과학기술정보통신부)의 제원으로 한국연구재단의 지원을 받아 수행된 연구임(No.2019R1F1A105857413)

References

  1. Byun, J. (2017). Design and Implementation of Image Recommender Ssystem Using Personal Preference Image Based on Deep Learning, Thesis, Sangmyung University.
  2. Gill, D., Jeon, K., & Lee, G. (2017). Classification of images from construction sites using a deep-learning algorithm - preliminary study, Journal of the Architectural Institute of Korea, Planning and Design, 37(2), 785-786.
  3. Han, Y., & Lee, H. (2019). An analysis on consistency of brand identity with ai-based image classification, Journal of the Architectural Institute of Korea, Planning and Design Section, 28(6), 138-145.
  4. Jang, J., An, H., Lee, J., & Shin, S. (2019). Construction of faster R-CNN deep learning model for surface damage detection of blade system, Journal of the Korea institute for Structural Maintenance and Inspection, 23(7), 80-86. https://doi.org/10.11112/JKSMI.2019.23.7.80
  5. Jeong, I., Shin, H., Kim, E., & Jang, S. (2020). Design guidelines for rest area in high school based on MBTI characteristic, Journal of the Architectural Institute of Korea, Planning and Design, 22(2), 338-341.
  6. Kang, E., Kim, M., Ji, S., & Jun, H. (2019). A study on the method for visual perception of hanok components form through artificial intelligence - focusing on the hanok bracket system, Journal of the Architectural Institute of Korea, Planning and Design Section, 39(1), 100-101.
  7. Kim, W., Kim, S., & Moon, H. (2019). A study on thermal comfort prediction with thermographic camera using convolutional neural network, Journal of the Architectural Institute of Korea, 39(2), 357-358.
  8. Lee, S., & Lu, N. (2020). A methodology of enhancing the accuracy of image classification with CNN, Journal of the Architectural Institute of Korea, 36(9), 15-22. https://doi.org/10.5659/JAIK.2020.36.9.15
  9. Myung, J., & Jung, H. (2020). Emotion classification DNN model for virtual reality based 3D space, Journal of the Architectural Institute of Korea, Planning and Design, 36(4), 41-49. https://doi.org/10.5659/JAIK_PD.2020.36.4.41
  10. Seol, D., Oh, J., & Kim, H. (2020). Comparison of deep learning-based CNN models for crack detection, Journal of the Architectural Institute of Korea Structure & Construction, 36(3), 113-120.
  11. Sim, H., & Lee, Y. (2018). Analysis on the preference for each emotional component in elementary school space, Journal of the Architectural Institute of Korea, Planning and Design Section, 34(3), 3-10.