@inproceedings{b4de4995c0ac47f68579f451da958544,
title = "Coddora : CO2-Based Occupancy Detection Model Trained via Domain Randomization",
abstract = "Information about human presence in indoor spaces is crucial for building energy optimization. While there has been a considerable amount of research on using neural networks to automatically detect occupancy from CO2 sensors, their application in practice is limited due to the scarcity of labeled training data. In this paper, we propose Coddora, an off-the-shelf deep learning model pretrained on data from randomized room simulations. Coddora enables quick adaptation to real-world rooms, requiring only minimal data collection. Our contribution includes two model variants for application via fine-tuning or zero-shot classifying, as well as the synthetic dataset providing data from simulations with 100,000 room models.",
keywords = "building occupancy detection, deep learning, domain randomization, neural networks, off-the-shelf model",
author = "Manuel Weber and Farzan Banihashemi and Davor Stjelja and Peter Mandl and Ruben Mayer and Jacobsen, {Hans Arno}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; International Joint Conference on Neural Networks, IJCNN ; Conference date: 30-06-2024 Through 05-07-2024",
year = "2024",
doi = "10.1109/IJCNN60899.2024.10650820",
language = "English",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",
booktitle = "2024 International Joint Conference on Neural Networks, IJCNN 2024 - Proceedings",
address = "United States",
}