DOI QR코드

DOI QR Code

딥 러닝을 활용한 한국 아파트 단위평면 진화과정 분석

An Analysis on the Evolution of Korean Apartment Unit Plans using Deep Learning

  • Ahn, Euisoon (Department of Architecture and Architectural Engineering, Seoul National University)
  • 투고 : 2020.05.13
  • 심사 : 2021.09.17
  • 발행 : 2021.10.30

초록

Deep learning methods have shown outstanding performance in image recognition on a big data scale, which has been the bottleneck in research on Korean apartments. Several studies have applied deep learning to architectural images, but analyzing Korean apartments required a deep learning model trained on a Korean apartment dataset. We developed an architectural research methodology for floor plan images, which utilizes deep learning, biclustering, and activation mapping methods. The method performs an inductive classification based on the similarity between floor plan images, guided by but not limited to accompanied class labels. We constructed a 50K unit plan image dataset of Korean apartments by collecting and normalizing floor plan images and analyzed the dataset using the developed method. The biclusters of unit plan types, extracted from the learned representation of the model, also showed a closely grouped temporal arrangement. Further examination on the unit plan types using bicluster activation mapping (BAM) showed that the deep learning model could discover areas where new design trend of the era emerged, without any prior knowledge on Korean apartments or architectural design in general.

키워드

참고문헌

  1. Ahn, E. (2021). Deep Learning Based Spatial Analysis Method for Korean Apartment Unit Plans [Doctoral dissertation, Seoul National University]. http://www.riss.kr/link?id=T15828388
  2. Choi, J. (1990). From Courtyard to Living Room. Housing City, 51, 52-64.
  3. Choi, J., Cho, H.-K., Park, I.-S., & Park, Y.-S. (2004). A Spatial Analysis of the Apartment Unit Plans from 1966 to 2002 in Seoul. Journal of the Architectural Institute of Korea Planning & Design, 20(6), 153-162.
  4. Dhillon, I. S. (2001). Co-clustering documents and words using bipartite spectral graph partitioning. Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 269-274.
  5. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org/
  6. Jeon, B., & Kwon, Y. (2012). Hanok and the history of the Korean house. Dongnyok Publishers. 197-200.
  7. Kim, S., & Kim, S. (1997). Time series analysis of unit plan of private sector apartment housing in Korea. Housing Studies, 5(1), 103-127. http://www.riss.kr/link?id=A76459241
  8. Kluger, Y., Basri, R., Chang, J. T., & Gerstein, M. (2003). Spectral biclustering of microarray data: Coclustering genes and conditions. Genome Research, 13(4), 703-716. https://doi.org/10.1101/gr.648603
  9. Kwon, H., Chun, W., & Park, J. (2006). A study on the efficient utilization plan of balcony space in apartment. Journal of the Architectural Institute of Korea Planning & Design, 26(1), 81-84.
  10. Merrell, P., Schkufza, E., & Koltun, V. (2010). Computer-generated residential building layouts. ACM Transactions on Graphics, 29(6), 1. https://doi.org/10.1145/1882261.1866203
  11. NAVER Corp. (2020). Naver Real Estate. https://land.naver.com/
  12. Park, I.-S., Park, N.-H., & Chun, H.-S. (2014). Changes in Apartment Unit Plan Caused by the Revision of Regulations for Area Calculating Criteria and Balcony Use: Focused on Changes of Size of Rooms in 60 m2 and 85 m2 Sized Unit. Journal of the Korean housing association, 25(2), 27-36. https://doi.org/10.6107/JKHA.2014.25.2.027
  13. Rodrigues, E., Gaspar, A. R., & Gomes, A. (2013). An approach to the multi-level space allocation problem in architecture using a hybrid evolutionary technique. Automation in Construction, 35, 482-498. https://doi.org/10.1016/j.autcon.2013.06.005
  14. Rodrigues, E., Sousa-Rodrigues, D., Teixeira de Sampayo, M., Gaspar, A. R., Gomes, A., & Henggeler Antunes, C. (2017). Clustering of architectural floor plans: A comparison of shape representations. Automation in Construction, 80, 48-65. https://doi.org/10.1016/j.autcon.2017.03.017
  15. scikit-learn developers. (2020). Biclustering. https://scikit-learn.org/stable/modules/biclustering.html
  16. Seo, K. W. (2007). Space puzzle in a concrete box: finding design competence that generates the modern apartment houses in Seoul. Environment and Planning B: Planning and Design, 34(6), 1071-1084. https://doi.org/10.1068/b32134
  17. Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., & Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484-489. https://doi.org/10.1038/nature16961
  18. Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. http://arxiv.org/abs/1409.1556
  19. Turner, A., Doxa, M., O'Sullivan, D., & Penn, A. (2001). From Isovists to Visibility Graphs: A Methodology for the Analysis of Architectural Space. Environment and Planning B: Planning and Design, 28(1), 103-121. https://doi.org/10.1068/b2684
  20. Yoshimura, Y., Cai, B., Wang, Z., & Ratti, C. (2019, July). Deep learning architect: classification for architectural design through the eye of artificial intelligence. In International Conference on Computers in Urban Planning and Urban Management (pp. 249-265). Springer, Cham.
  21. Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. European Conference on Computer Vision, 818-833.
  22. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2015). Learning Deep Features for Discriminative Localization. http://arxiv.org/abs/1512.04150