EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Classification in Early Fire Detection Using Multi-Sensor Nodes—A Transfer Learning Approach

Pascal Vorwerk iD, Jörg Kelleter, Steffen Müller, Ulrich Krause iD

Sensors · 22.02.2024 · 24 (5) · 1428

DOI: 10.3390/s24051428 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.02.2024. Verfasst von Pascal Vorwerk und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Process- and Systems Engineering, Institute of Apparatus and Environmental Technology, Otto von Guericke University of Magdeburg, Universi…. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Education and Research as part of the "Research for Civil Security" program, German Federal Ministry of Education and Research as part of the “Research for Civil Security” program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effective early fire detection is crucial for preventing damage to people and buildings, especially in fire-prone historic structures. However, due to the infrequent occurrence of fire events throughout a building’s lifespan, real-world data for training models are often sparse. In this study, we applied feature representation transfer and instance transfer in the context of early fire detection using multi-sensor nodes. The goal was to investigate whether training data from a small-scale setup (source domain) can be used to identify various incipient fire scenarios in their early stages within a full-scale test room (target domain). In a first step, we employed Linear Discriminant Analysis (LDA) to create a new feature space solely based on the source domain data and predicted four different fire types (smoldering wood, smoldering cotton, smoldering cable and candle fire) in the target domain with a classification rate up to 69% and a Cohen’s Kappa of 0.58. Notably, lower classification performance was observed for sensor node positions close to the wall in the full-scale test room. In a second experiment, we applied the TrAdaBoost algorithm as a common instance transfer technique to adapt the model to the target domain, assuming that sparse information from the target domain is available. Boosting the data from 1% to 30% was utilized for individual sensor node positions in the target domain to adapt the model to the target domain. We found that additional boosting improved the classification performance (average classification rate of 73% and an average Cohen’s Kappa of 0.63). However, it was noted that excessively boosting the data could lead to overfitting to a specific sensor node position in the target domain, resulting in a reduction in the overall classification performance.

Schlagwörter

Stichwörter der Autor:innen

classificationearly fire detectionelectronic nosefeature fusiongas sensorslinear discriminant analysis (LDA)multi-sensor nodestransfer learning

Autor:innen und Institutionen

  • Faculty of Process- and Systems Engineering, Institute of Apparatus and Environmental Technology, Otto von Guericke University of Magdeburg, Universitätsplatz 2, 39106 Magdeburg, Germany.
  • GTE Industrieelektronik GmbH, Helmholtzstr. 21, 38-40, 41747 Viersen, Germany.

ORCID-Profile: Pascal Vorwerk, Ulrich Krause

Förderung

  • German Federal Ministry of Education and Research as part of the "Research for Civil Security" program
  • German Federal Ministry of Education and Research as part of the “Research for Civil Security” program

Zitieren

APA

Vorwerk, P., Kelleter, J., Müller, S., & Krause, U. (2024). Classification in Early Fire Detection Using Multi-Sensor Nodes—A Transfer Learning Approach. Sensors, 24(5), 1428. https://doi.org/10.3390/s24051428

Vancouver

Vorwerk P, Kelleter J, Müller S, Krause U. Classification in Early Fire Detection Using Multi-Sensor Nodes—A Transfer Learning Approach. Sensors. 2024;24(5):1428. doi:10.3390/s24051428

BibTeX
@article{Vorwerk2024,
  author = {Vorwerk, Pascal and Kelleter, Jörg and Müller, Steffen and Krause, Ulrich},
  title = {Classification in Early Fire Detection Using Multi-Sensor Nodes—A Transfer Learning Approach},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {5},
  pages = {1428},
  doi = {10.3390/s24051428}
}
Kostenlos starten →