8 March 2017 Identification chemical agent simulants by remote infrared spectra with improved artificial neural network
Author Affiliations +
Proceedings Volume 10255, Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016; 102553V (2017) https://doi.org/10.1117/12.2268044
Event: Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016, 2016, Jinhua, Suzhou, Chengdu, Xi'an, Wuxi, China
Abstract
Remote infrared sensing is a good approach to detect Chemical agents which can prevent operator being poisoned. The pattern recognition algorithms such as artificial neural network are the core of the chemical agent spectra identification subsystem. This paper presents a modified artificial neural network that can effectively train and identify chemical agent remote sensing spectra. The C++ language was used to program the identification software. Then many remote sensing spectra DMMP as chemical agent simulants were used to train the artificial neural network. The results show that the adaptive momentum and adaptive learning rate accelerate the artificial neural network convergence, cross-examination avoids neural network over-fitting, and the modified artificial neural network can be used to identify chemical agents remote sensing spectra perfectly.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiao-qiang Dong, Xiao-qiang Dong, Teng-xiao Guo, Teng-xiao Guo, Yu-Ting Yan, Yu-Ting Yan, Ji Wang, Ji Wang, Xu Zhang, Xu Zhang, Jun-ming Li, Jun-ming Li, } "Identification chemical agent simulants by remote infrared spectra with improved artificial neural network", Proc. SPIE 10255, Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016, 102553V (8 March 2017); doi: 10.1117/12.2268044; https://doi.org/10.1117/12.2268044
PROCEEDINGS
5 PAGES


SHARE
Back to Top