| id |
ecaade2023_204 |
| authors |
Lacroix, Igor, Güzelci, Orkan Zeynel and Sousa, José Pedro |
| year |
2023 |
| title |
Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning |
| source |
Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 629–638 |
| doi |
https://doi.org/10.52842/conf.ecaade.2023.2.629
|
| summary |
Establishing an evolutive dataset for architectural rationalization of social housing is technically achievable through artificial intelligence based on deep learning (DL). However, concerning the sensitive quality of social housing, the application of such technology needs to preserve the human factor and relate ethically to architectural design. A reference on this subject is historic Portuguese research from the 1960s and the 1970s. By then, pioneering research at the National Laboratory of Civil Engineering (LNEC), based in Lisbon, explored early computing methods to aid the design process by considering deontological concerns. The authors studied these works to refactor those goals and concerns of technological application and sociological interaction with current digital technologies. When digitizing their processes of creating architectural design instruments for social housing a problem emerged with parsing a dataset of floor plans and using it to generate building information models. Thus, a DL process was explored to achieve an evolutive dataset in the most automated way at the architectural level. The paper presents the implementation of a DL process that recognizes floor plans of social housing and consequently enables the development of an instrument for direct architectural rationalization. |
| keywords |
Artificial Intelligence, Machine Learning, Deep Learning, BIM, Social Housing, Evolutive Dataset |
| series |
eCAADe |
| email |
|
| full text |
 file.pdf (992,866 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2023/12/10 10:49 |
|
