Research on PM2.5 concentration prediction based on HHO-LMBP neural network

Hai-jun Wang; Zhi-gang Wang; Tao Jin; Zhi-li Qiao; Xiao-jiao Zhang

doi:10.1117/12.2652782

20 October 2022 Research on PM2.5 concentration prediction based on HHO-LMBP neural network

Hai-jun Wang, Zhi-gang Wang, Tao Jin, Zhi-li Qiao, Xiao-jiao Zhang

Proceedings Volume 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022); 1235019 (2022) https://doi.org/10.1117/12.2652782
Event: 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 2022, Qingdao, China

Abstract

Aiming at the PM2.5 concentration in the air, which is affected by meteorological factors and atmospheric pollutants, and has the characteristics of nonlinearity and uncertainty, a prediction method of LMBP neural network based on Harris Hawk optimization algorithm is proposed. In the process of LMBP neural network weight threshold optimization process, Harris Hawk optimization algorithm (HHO) is introduced, and a LMBP initial weights and thresholds optimization method based on HHO algorithm is designed. This method utilizes the global optimization ability of HHO algorithm and effectively avoids the LMBP neural network is trapped in a local minimum worth of possibilities. The simulation results show that the prediction model based on the HHO-LMBP algorithm has higher accuracy and better stability than the DELMBP and LMBP algorithms.

Citation Download Citation

Hai-jun Wang, Zhi-gang Wang, Tao Jin, Zhi-li Qiao, and Xiao-jiao Zhang "Research on PM2.5 concentration prediction based on HHO-LMBP neural network", Proc. SPIE 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235019 (20 October 2022); https://doi.org/10.1117/12.2652782

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