Application of Genetic Algorithm-Least Squares Support Vector Regression with Near Infrared Spectroscopy for Prediction of Nicotine Content in Tobacco

2012 ◽  
Vol 49 (2) ◽  
pp. 021201
Author(s):  
郭志明 Guo Zhiming ◽  
陈立平 Chen Liping ◽  
黄文倩 Huang Wenqian ◽  
张驰 Zhang Chi
Keyword(s):  
Genetic Algorithm ◽  
Infrared Spectroscopy ◽  
Least Squares ◽  
Support Vector Regression ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Support Vector ◽  
Nicotine Content

scholarly journals Moisture Content Quantization of Masson Pine Seedling Leaf Based on Stacked Autoencoder with Near-Infrared Spectroscopy

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Chao Ni ◽  
Yun Zhang ◽  
Dongyi Wang
Keyword(s):  
Infrared Spectroscopy ◽  
Moisture Content ◽  
Support Vector Regression ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Support Vector ◽  
Spectroscopy Analysis ◽  
Support Vector Regression Model ◽  
Masson Pine ◽  
Stacked Autoencoder

Masson pine is widely planted in southern China, and moisture content of the pine seedling leaves is an important index for evaluating the vigor of seedlings. For precisely predicting leaf moisture content, near-infrared spectroscopy analysis is applied in the experiment, which is a cost-effective, high-speed, and noninvasive material content prediction tool. To further improve the spectroscopy analysis accuracy, in this study, a new analysis model is proposed which integrates a stacked autoencoder for extracting hierarchical output-related features layer by layer and a support vector regression model to leverage these features for precisely predicting moisture contents. Compared with traditional spectroscopy analysis method like partial least squares regression and basic support vector regression, the proposed model shows great superiority for leaf moisture content prediction, with R2 value 0.9946 and root-mean squared error (RMSE) value 0.1636 in calibration set and R2 value 0.9621 and RMSE 0.4249 in prediction set.

Sign in / Sign up

Export Citation Format

Share Document