Towards a Fire Alarm Model Based on Variable Learning Rate Algorithm with Weight Factor

Wei Wang, Liping Yang, Lei XuAdvances 2014 · DOI

Abstract

Fire alarm with Neural Network (NN) can learn knowledge from multiple sensor data fusion. By adjusting network weight, more stable fire alarm can be achieved. Classic BP NN is likely to fall into local minimum. To address this problem, a Variable Learning Rate Algorithm with Weight Factor (VLRA-BP) was proposed and introduced into automatic intelligent decision in fire alarm. The model with VLRA-BP algorithm uses temperature and smoke sensors to perform intelligent information transformation, so as to achieve target of timely alarming and decrease system false alarm rate. Simulation experiment result shows that system accuracy and average error can effectively monitor simulated fire scene and forecast fire.
BibTeX
@inproceedings{wang2014towards,
  author = {Wei Wang and Liping Yang and Lei Xu},
  title = {{Towards a Fire Alarm Model Based on Variable Learning Rate Algorithm with Weight Factor}},
  booktitle = {Advances},
  year = {2014},
  doi = {10.2991/mce-14.2014.22},
}
Figure