Please use this identifier to cite or link to this item:
https://doi.org/10.1145/3486611.3491120
DC Field | Value | |
---|---|---|
dc.title | Fifty shades of black: Uncovering physical models from symbolic regressions for scalable building heat dynamics identification | |
dc.contributor.author | Leprince, J | |
dc.contributor.author | Miller, C | |
dc.contributor.author | Frei, M | |
dc.contributor.author | Madsen, H | |
dc.contributor.author | Zeiler, W | |
dc.date.accessioned | 2022-07-28T05:09:39Z | |
dc.date.available | 2022-07-28T05:09:39Z | |
dc.date.issued | 2021-11-17 | |
dc.identifier.citation | Leprince, J, Miller, C, Frei, M, Madsen, H, Zeiler, W (2021-11-17). Fifty shades of black: Uncovering physical models from symbolic regressions for scalable building heat dynamics identification. BuildSys '21: The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation : 345-348. ScholarBank@NUS Repository. https://doi.org/10.1145/3486611.3491120 | |
dc.identifier.isbn | 9781450391146 | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/229340 | |
dc.description.abstract | The rapid growth of machine learning (black-box) techniques and computing capacity has started to transform many research domains, including building performance analysis. However, physical interpretation of these models remains a challenge due to their opaque nature. This paper outlines an experiment to unveil analytical expressions from an open-source machine-learning-based algorithm, i.e., symbolic regression. From 241 residential buildings in the Netherlands, 50 unique analytical expressions were produced demonstrating overall better characterization accuracies than an XGBoost baseline, while providing a powerful mean of interpretability from model structures and coefficients. These insights present a starting point for further work towards highly scalable models yielding new characterizations of residential buildings. | |
dc.publisher | ACM | |
dc.source | Elements | |
dc.type | Conference Paper | |
dc.date.updated | 2022-07-19T00:44:54Z | |
dc.contributor.department | THE BUILT ENVIRONMENT | |
dc.description.doi | 10.1145/3486611.3491120 | |
dc.description.sourcetitle | BuildSys '21: The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation | |
dc.description.page | 345-348 | |
dc.published.state | Published | |
Appears in Collections: | Staff Publications Elements |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
3486611.3491120.pdf | Published version | 1.56 MB | Adobe PDF | OPEN | Published | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.