Research on fire detection based on improved random forest algorithm

Shuo Lin; Qi Zhang; Hongshan Xie

doi:10.1117/12.2627645

11 March 2022 Research on fire detection based on improved random forest algorithm

Shuo Lin, Qi Zhang, Hongshan Xie

Proceedings Volume 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021); 121601S (2022) https://doi.org/10.1117/12.2627645
Event: International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 2021, Sanya, China

Abstract

Aiming at the problems of low detection accuracy and poor generalization ability in multi-information fire detection, a fire detection method based on improved random forest algorithm was proposed. The method was considered comprehensively from the data, characteristics and model. Firstly, an improved random forest algorithm was designed to build a fire detection model. Secondly,feature selection was carried out through Pearson correlation coefficient feature extraction rule, and then the fire factor data were balanced. Finally, through the simulation experiment, the comparison with the results of the standard Random Forest algorithm showed that the overall accuracy of the improved random forest algorithm was 93.33%, 4.44% higher than the standard random forest algorithm.

Citation Download Citation

Shuo Lin, Qi Zhang, and Hongshan Xie "Research on fire detection based on improved random forest algorithm", Proc. SPIE 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 121601S (11 March 2022); https://doi.org/10.1117/12.2627645

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available