Application of Interval Random Frog Combined with Sucessive Projections Algorithm to Detecting Nitrogen Content in Rubber Tree Leaves

Journal Title: 河南科技大学学报(自然科学版) - Year 2019, Vol 40, Issue 5

Abstract

The non-destructive detection method of nitrogen content in rubber tree leaves based on visible/near infrared spectroscopy was studied.A total of 176 rubber tree leaf samples were collected, and the visible/near infrared data from 350 ~ 2 500 nm was used as experimental data.Firstly, a novel interval random frog (iRF) algorithm was used to select the wavelength interval combination with smallest root mean square error of crossvalidation (RMSECV) . Secondly, the successive projections algorithm (SPA) was used to further select the characteristic wavelength. Thirdly, the selected characteristic wavelength was taken as the input variable to establish a partial least squares (PLS) model.The results show that the wavelength selection is carried out by two-step strategy.The 714 variables from full-spectrum 2 151 are selected by rough selection of iRF algorithm.Then the 20 optimal variables further was selected from the 714 variables refined selection by SPA algorithm, which reduces the information redundancy, and significantly reduces the number of variables of 99. 07%. The root mean square error of calibration (RMSEC) , correlation coefficient of correlation (Rc) , root mean square error of prediction (RMSEP) and correlation coefficient of prediction (Rp) are respectively 0.091 3%, 0.956 5, 0.123 8%, and 0.901 8 which have lower root mean square errors and higher correlation coefficients than PLS, iPLS, iRF, and SPA. Therefore, iRF-SPA can be used as the strategy for wavelength selection to detect the nitrogen content of rubber tree leaves.

Authors and Affiliations

Wei CHEN, Chuang LI, Rongnian TANG

Keywords

Related Articles

Effect of Electronic Thermostat on Fuel Consumption with Fuzzy PID

Aiming at the problem that the traditional internal combustion engine water temperature control system could not accurately, quickly and steadily adjust the engine water temperature, a fuzzy controller was designed in Si...

Effect of Arc on Tribological Characteristics of C/C Composites Under Electric Current

The friction and wear tests were carried out on an HST-100 high-speed friction and wear testing machine with a pin-on-disc configuration,and the arc images were recorded by a high-speed camera. The effect of arc on the t...

Atomic Simulation of Interaction of Shear-Coupled Grain Boundary Motion with Crack in α-Iron

The interaction of shear coupled migration (SCM) with crack of tilt grain boundary (GB) Σ 9[110] (221) in α-iron was studied by using molecular dynamics simulation method.The effect of temperature and the Cr addition on...

Ultrasonic Phased Array Testing and Probability of Detection Quantitative Analysis of Polyethylene Pipe Butt Fusion Joints

The customized polyethylene test block was designed with transverse hole defects at depths of 10 mm, 15 mm, 20 mm, 25 mm, 30 mm, 35 mm, 40 mm, whose diameters were 1 mm and 2 mm respectively. Then probability of detectio...

Download PDF file
  • EP ID EP594626
  • DOI 10.15926/j.cnki.issn1672-6871.2019.05.009
  • Views 65
  • Downloads 0

How To Cite

Wei CHEN, Chuang LI, Rongnian TANG (2019). Application of Interval Random Frog Combined with Sucessive Projections Algorithm to Detecting Nitrogen Content in Rubber Tree Leaves. 河南科技大学学报(自然科学版), 40(5), 51-56. https://europub.co.uk/articles/-A-594626