Overcoming Data Scarcity through Transfer Learning in CO2-Based Building Occupancy Detection

Manuel Weber, Farzan Banihashemi, Peter Mandl, Hans Arno Jacobsen, Ruben Mayer

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

2 Scopus citations

Abstract

Knowing indoor occupancy states is crucial for energy optimization in buildings. While neural networks can effectively be used to detect occupancy based on carbon dioxide measurements, their application is impeded by the need for sufficient labeled training data. In this study, we analyze the prediction performance of three different transfer learning (TL) methods leveraging target room data jointly with data from other rooms. The methods include (1) pretraining and fine-tuning, (2) layer freezing, and (3) domain-adversarial learning. Using data from five real-world rooms and one simulated room, including multiple room types, we provide the most extensive evaluation of TL in the field of occupancy prediction from environmental variables to date. This work's contribution further includes the architecture and hyperparameters of a deep CNN-LSTM model for CO2-based occupancy detection. Our results indicate that TL effectively reduces the required amount of target room data. Moreover, while previous literature was focused on pretraining with related real-world data, we show that similar performance can be achieved by the more practical approach of leveraging simulated data.

Original languageEnglish
Title of host publicationBuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
PublisherAssociation for Computing Machinery, Inc
Pages1-10
Number of pages10
ISBN (Electronic)9798400702303
DOIs
StatePublished - 15 Nov 2023
Externally publishedYes
Event10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023 - Istanbul, Turkey
Duration: 15 Nov 202316 Nov 2023

Publication series

NameBuildSys 2023 - Proceedings of the10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Conference

Conference10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2023
Country/TerritoryTurkey
CityIstanbul
Period15/11/2316/11/23

Keywords

  • Building Occupancy Detection
  • CNN-LSTM
  • Deep Learning
  • Indoor Carbon Dioxide
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Overcoming Data Scarcity through Transfer Learning in CO2-Based Building Occupancy Detection'. Together they form a unique fingerprint.

Cite this