Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.95 MB
Add to list
  1. Search results
  2. Predicting the state of a house using...

Predicting the state of a house using Google Street View : an analysis of deep binary classification models for the assessment of the quality of Flemish houses

Margot Geerts, Kiran Shaikh, Jochen De Weerdt and Seppe vanden Broucke (UGent)
(2022) Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings. In Lecture notes in business information processing 446. p.703-710
Author
Organization
Abstract
Currently, the state of a house is typically assessed by an expert, which is time and resource intensive. Therefore, an automatic assessment could have economic, social and ecological benefits. Hence, this study presents a binary classification model using transfer learning to classify Google Street View images of houses. For this purpose, a three-by-three analysis is conducted that allows to compare three different network architectures and three differently-sized data sets, using properties located in Leuven, Belgium. A DenseNet201 architecture was found to work best, as illustrated quantitatively as well as by means of state-of-the-art explainability methods.
Keywords
Google Street View, Real estate, Deep learning, Convolutional neural networks, Transfer learning

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.95 MB

Citation

Please use this url to cite or link to this publication:

MLA
Geerts, Margot, et al. “Predicting the State of a House Using Google Street View : An Analysis of Deep Binary Classification Models for the Assessment of the Quality of Flemish Houses.” Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings, edited by Renata Guizzardi et al., vol. 446, Springer, 2022, pp. 703–10, doi:10.1007/978-3-031-05760-1_46.
APA
Geerts, M., Shaikh, K., De Weerdt, J., & vanden Broucke, S. (2022). Predicting the state of a house using Google Street View : an analysis of deep binary classification models for the assessment of the quality of Flemish houses. In R. Guizzardi, J. Ralyté, & X. Franch (Eds.), Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings (Vol. 446, pp. 703–710). https://doi.org/10.1007/978-3-031-05760-1_46
Chicago author-date
Geerts, Margot, Kiran Shaikh, Jochen De Weerdt, and Seppe vanden Broucke. 2022. “Predicting the State of a House Using Google Street View : An Analysis of Deep Binary Classification Models for the Assessment of the Quality of Flemish Houses.” In Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings, edited by Renata Guizzardi, Jolita Ralyté, and Xavier Franch, 446:703–10. Cham: Springer. https://doi.org/10.1007/978-3-031-05760-1_46.
Chicago author-date (all authors)
Geerts, Margot, Kiran Shaikh, Jochen De Weerdt, and Seppe vanden Broucke. 2022. “Predicting the State of a House Using Google Street View : An Analysis of Deep Binary Classification Models for the Assessment of the Quality of Flemish Houses.” In Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings, ed by. Renata Guizzardi, Jolita Ralyté, and Xavier Franch, 446:703–710. Cham: Springer. doi:10.1007/978-3-031-05760-1_46.
Vancouver
1.
Geerts M, Shaikh K, De Weerdt J, vanden Broucke S. Predicting the state of a house using Google Street View : an analysis of deep binary classification models for the assessment of the quality of Flemish houses. In: Guizzardi R, Ralyté J, Franch X, editors. Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings. Cham: Springer; 2022. p. 703–10.
IEEE
[1]
M. Geerts, K. Shaikh, J. De Weerdt, and S. vanden Broucke, “Predicting the state of a house using Google Street View : an analysis of deep binary classification models for the assessment of the quality of Flemish houses,” in Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings, Barcelona, Spain, 2022, vol. 446, pp. 703–710.
@inproceedings{8754074,
  abstract     = {{Currently, the state of a house is typically assessed by an expert, which is time and resource intensive. Therefore, an automatic assessment could have economic, social and ecological benefits. Hence, this study presents a binary classification model using transfer learning to classify Google Street View images of houses. For this purpose, a three-by-three analysis is conducted that allows to compare three different network architectures and three differently-sized data sets, using properties located in Leuven, Belgium. A DenseNet201 architecture was found to work best, as illustrated quantitatively as well as by means of state-of-the-art explainability methods.}},
  author       = {{Geerts, Margot and Shaikh, Kiran and De Weerdt, Jochen and vanden Broucke, Seppe}},
  booktitle    = {{Research Challenges in Information Science, 16th International Conference, RCIS 2022, Proceedings}},
  editor       = {{Guizzardi, Renata and Ralyté, Jolita and Franch, Xavier}},
  isbn         = {{9783031057595}},
  issn         = {{1865-1348}},
  keywords     = {{Google Street View,Real estate,Deep learning,Convolutional neural networks,Transfer learning}},
  language     = {{eng}},
  location     = {{Barcelona, Spain}},
  pages        = {{703--710}},
  publisher    = {{Springer}},
  title        = {{Predicting the state of a house using Google Street View : an analysis of deep binary classification models for the assessment of the quality of Flemish houses}},
  url          = {{http://doi.org/10.1007/978-3-031-05760-1_46}},
  volume       = {{446}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: