Decoding Ethiopian Abodes: Towards Classifying Buildings by Occupancy Type Using Footprint Morphology

Daniel S. Adams, Taylor Hauser, Jessica Moehl

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Building occupancy classification plays a crucial role in urban planning, disaster management, and population modeling. Traditional methods often require extensive field surveys or detailed datasets, which can be time-consuming, expensive, and may yield incomplete or erroneous data. In this paper, we present a novel approach for classifying buildings as residential or non-residential using only building footprint data. By extracting geometric shape derivatives that characterize building morphology, we developed a high-accuracy classification model employing a combination of unsupervised and supervised learning methods. We utilized open-source data from Open Street Map, aggregating it to create binary labels for buildings based on their respective human use type. Our approach demonstrates the potential for scalability without the need for additional data sources other than building footprints and labels, offering a more efficient solution for building occupancy classification.

Original languageEnglish
Title of host publicationProceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
EditorsM. Arif Wani, Mihai Boicu, Moamar Sayed-Mouchaweh, Pedro Henriques Abreu, Joao Gama
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages210-217
Number of pages8
ISBN (Electronic)9798350345346
DOIs
StatePublished - 2023
Event22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023 - Jacksonville, United States
Duration: Dec 15 2023Dec 17 2023

Publication series

NameProceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

Conference

Conference22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
Country/TerritoryUnited States
CityJacksonville
Period12/15/2312/17/23

Keywords

  • Anomaly Detection
  • Building Morphology
  • Occupancy Type
  • VGI
  • XG-Boost

Fingerprint

Dive into the research topics of 'Decoding Ethiopian Abodes: Towards Classifying Buildings by Occupancy Type Using Footprint Morphology'. Together they form a unique fingerprint.

Cite this