摘要
相比传统方法,光谱法进行土壤分析具有低成本、高效、无损的优点。提出了基于粒子群优化卷积神经网络的土壤光谱分析模型,以达到快速、高效、准确的土壤元素分析。选用粒子群算法对卷积神经网络的结构进行优化,进一步提升CNN的预测准确率。结果表明,相比传统的CNN,PLS,LSSVM等建模方法,所提出的模型具有更高的预测准确率。
Compared with traditional methods,soil analysis by spectroscopy has the advantages of low cost,high efficiency and non-destructive.This paper proposes a soil spectral analysis model based on particle swarm optimization convolutional neural network to achieve the purpose of fast,efficient and accurate detection.The particle swarm optimization algorithm is used to optimize the structure of the convolutional neural network to further improve the prediction accuracy of the model.The results show that the model proposed in this paper has higher prediction accuracy than traditional CNN,PLS,RBF,LSSVM and other modeling methods.
作者
刘兰军
翟永庆
郑俊俊
范萍萍
邓莉
LIU Lan-jun;ZHAI Yong-qing;ZHENG Jun-jun;FAN Ping-ping;DENG Li(College of Engineering,Ocean University of China,Qingdao 266100,China;Institute of Oceanographic Instrumentation,Shandong Academy of Sciences,Qilu University of Technology,Qingdao266100,China)
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2020年第S01期71-72,共2页
Spectroscopy and Spectral Analysis
基金
国家重点研发计划项目(2017YFC0307701)
山东省自然科学基金项目(ZR2018LD007)资助
关键词
土壤元素分析
可见/近红外光谱
卷积神经网络
粒子群算法
Soil elemental analysis
Visible-Near infrared spectroscopy
Convolutional Neural Networks
Particle swarm optimization
