Support vector regression for determination of component of compound oxytetracycline powder on near-infrared spectroscopy

2006 ◽  
Vol 355 (1) ◽  
pp. 1-7 ◽  
Author(s):  
Tingting Zou ◽  
Ying Dou ◽  
Hong Mi ◽  
Jiying Zou ◽  
Yulin Ren
Keyword(s):  
Infrared Spectroscopy ◽  
Support Vector Regression ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Support Vector

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.

scholarly journals Quantitative Determination of Germinability ofPuccinia striiformisf. sp.triticiUrediospores Using Near Infrared Spectroscopy Technology

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Yaqiong Zhao ◽  
Feng Qin ◽  
Pei Cheng ◽  
Xiaolong Li ◽  
Zhanhong Ma ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Quantitative Determination ◽  
Near Infrared Spectroscopy ◽  
Spectral Region ◽  
Near Infrared ◽  
Puccinia Striiformis ◽  
Support Vector ◽  
Near Infrared Reflectance ◽  
Preprocessing Method

Stripe rust caused byPuccinia striiformisf. sp.tritici(Pst) is an important disease on wheat. In this study, quantitative determination of germinability ofPsturediospores was investigated by using near infrared reflectance spectroscopy (NIRS) combined with quantitative partial least squares (QPLS) and support vector regression (SVR). The near infrared spectra of the urediospore samples were acquired using FT-NIR MPA spectrometer and the germination rate of each sample was measured using traditional spore germination method. The best QPLS model was obtained with vector correction as the preprocessing method of the original spectra and 4000–12000 cm−1as the modeling spectral region while the modeling ratio of the training set to the testing set was 4 : 1. The best SVR model was built when vector normalization was used as the preprocessing method, the modeling ratio was 5 : 1 and the modeling spectral region was 8000–11000 cm−1. The results showed that the effect of the best model built using QPLS or SVR was satisfactory. This indicated that quantitative determination of germinability ofPsturediospores using near infrared spectroscopy technology is feasible. A new method based on NIRS was provided for rapid, automatic, and nondestructive determination of germinability ofPsturediospores.

Sign in / Sign up

Export Citation Format

Share Document