Towards the Detection of Building Occupancy with Synthetic Environmental Data

2020/10/08 by Manuel Weber, Weber, Manuel, Christoph Doblander +3
Engineering · Environmental Science · #Air Quality Monitoring and Forecasting #Building Energy and Comfort Optimization #C.3 #FOS: Computer and information sciences #I.2.6 #Machine Learning (cs.LG) #Urban Heat Island Mitigation

paper · pdf · doi:10.48550/arxiv.2010.04209

openalex publication_date 2020/10/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03

Abstract

Information about room-level occupancy is crucial to many building-related tasks, such as building automation or energy performance simulation. Current occupancy detection literature focuses on data-driven methods, but is mostly based on small case studies with few rooms. The necessity to collect room-specific data for each room of interest impedes applicability of machine learning, especially data-intensive deep learning approaches, in practice. To derive accurate predictions from less data, we suggest knowledge transfer from synthetic data. In this paper, we conduct an experiment with data from a CO₂ sensor in an office room, and additional synthetic data obtained from a simulation. Our contribution includes (a) a simulation method for CO₂ dynamics under randomized occupant behavior, (b) a proof of concept for knowledge transfer from simulated CO₂ data, and (c) an outline of future research implications. From our results, we can conclude that the transfer approach can effectively reduce the required amount of data for model training.

Related

• Physics-Informed Building Occupancy Detection: a Switching Process with Markov Regime
• Room Occupancy Prediction: Exploring the Power of Machine Learning and Temporal Insights
• Occupancy Detection in Room Using Sensor Data
• Indoor occupancy estimation from carbon dioxide concentration
• Using Statistical Models to Detect Occupancy in Buildings through Monitoring VOC, CO₂, and other Environmental Factors