EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Fire Detection Method Based on a Mind-Linked Continuous-Coupled Neural Network

Kangrong Liu, Ji Wang, Wei Yang, Shiwei Wang, Jianxiang Wang iD, Jinhai Zhang, Zhaorui Zhang, Xinlei An, Jizhao Liu iD

Biomimetics · 10.06.2026 · 11 (6) · 410

DOI: 10.3390/biomimetics11060410 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 10.06.2026. Verfasst von Kangrong Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation, Gansu Provincial Leading Talents Program, funder name.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of Internet of Things (IoT) technology, fire detection systems based on multi-sensor fusion have become critical infrastructure to ensure public safety. Due to environmental noise and sensor heterogeneity, these systems often suffer from high rates of false alarms and missed detections. Although existing machine learning approaches have partially improved classification accuracy, their overall performance remains limited. Inspired by the cognitive mechanisms of the human brain, we developed an improved mind-linked continuous-coupled neural network (ML-CCNN) based on the existing continuous-coupled neural network (CCNN). We propose a parameter adaptation mechanism that modulates neural activations through a global threshold. We utilized the synthetic minority oversampling technique (SMOTE) to mitigate data imbalance and transformed sample feature vectors into matrices for training. Our model achieved an accuracy of 99.96% on our own dataset and 99.97% on the public Smoke Detection Dataset (SDD), which highlights ML-CCNN’s potential for fire detection.

Schlagwörter

Stichwörter der Autor:innen

ML-CCNNbrain-inspired computingfire detectionsmoke alarm

Autor:innen und Institutionen

  • School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China.
  • National Key Laboratory on Vacuum Technology and Physics, Lanzhou Institute of Physics, Lanzhou 730000, China.
  • School of Mathematics and Physics, Lanzhou Jiaotong University, Lanzhou 730070, China.
  • School of Electronics and Communication Engineering, Lanzhou University of Arts and Sciences, Lanzhou 730010, China.

ORCID-Profile: Jianxiang Wang, Jizhao Liu

Förderung

  • Natural Science Foundation
  • Gansu Provincial Leading Talents Program
  • funder name

Zitieren

APA

Liu, K., Wang, J., Yang, W., Wang, S., Wang, J., Zhang, J., Zhang, Z., An, X., & Liu, J. (2026). A Fire Detection Method Based on a Mind-Linked Continuous-Coupled Neural Network. Biomimetics, 11(6), 410. https://doi.org/10.3390/biomimetics11060410

Vancouver

Liu K, Wang J, Yang W, Wang S, Wang J, Zhang J, et al. A Fire Detection Method Based on a Mind-Linked Continuous-Coupled Neural Network. Biomimetics. 2026;11(6):410. doi:10.3390/biomimetics11060410

BibTeX
@article{Liu2026,
  author = {Liu, Kangrong and Wang, Ji and Yang, Wei and Wang, Shiwei and Wang, Jianxiang and Zhang, Jinhai and Zhang, Zhaorui and An, Xinlei and Liu, Jizhao},
  title = {A Fire Detection Method Based on a Mind-Linked Continuous-Coupled Neural Network},
  journal = {Biomimetics},
  year = {2026},
  volume = {11},
  number = {6},
  pages = {410},
  doi = {10.3390/biomimetics11060410}
}
Kostenlos starten →