Near infrared reflectance spectroscopy analysis of compost products using nonlinear support vector machine with RBF nucleus

被引：0

作者：

Huang, Guangqun ^{[1
]}

Han, Lujia ^{[1
]}

机构：

[1] College of Engineering, China Agricultural University

来源：

Guangxue Xuebao/Acta Optica Sinica | 2009年 / 29卷 / 12期

关键词：

Compost quality analysis; Near-infrared reflectance spectroscopy; Spectroscopy; Support vector machine;

D O I：

10.3788/AOS20092912.3556

中图分类号：

学科分类号：

摘要：

This study explored a new method to choose optimal parameters for support vector machine regression with RBF nucleus (RBF-SVR) and its application on the estimation of moisture content, volatile solid (VS) and the ratio of carbon to nitrogen (C/N) in animal manure compost products using near-infrared reflectance spectroscopy (NIRS). The efficiency of RBF-SVR method was compared with partial least-squares regression (PLSR) mainly using the determination coefficient of prediction (r2) of the standard error of prediction (SEP) and ratio of porformance to standard deviation [RPD (SD/SEP)]. In this study, 120 commercial animal manure compost samples were collected from 22 provinces in China. Spectra of the orient samples were scanned with a SPECTRUM ONE NTS from 4000~10000 cm-1, respectively. Results showed stepwise search for optimal parameters was a feasible method for RBF-SVR. The efficiency of RBF-SVR method for moisture content, VS and C/N were all better than PLSR. Robust models using RBF-SVR were developed for moisture content and VS (r2>0.90, RPD>4.0) and for C/N (r2>0.85, RPD>2.5), respectively. Results showed the potential of NIRS with RBF-SVR to evaluate the products quality of animal manure compost, but further research would be needed for the higher precision.

引用

页码：3556 / 3560

页数：4

共 14 条

[1]

Haug R.T., The Practical Handbook of Compost Engineering, pp. 1-10, (1993)

[2]

Malley D.F., McClure C., Martin P.D., Et al., Compositional analysis of cattle manure during composting using a field-portable near-infrared spectrometer, Communication in Soil Science and Plant Analysis, 36, 4, pp. 455-475, (2005)

[3]

Huang G.Q., Han L.J., Liu X., Rapid estimation of the composition of animal manure compost by near infrared reflectance spectroscopy, J. Near Infrared Spectroscopy, 2, 1, pp. 79-84, (2007)

[4]

Albrechta R., Joffreb R., Grosa R., Et al., Efficiency of near-infrared reflectance spectroscopy to assess and predict the stage of transformation of organic matter in the composting process, Bioresource Technology, 99, 2, pp. 448-455, (2008)

[5]

Deng N., Tian Y., New Method in Data Mining: Support Vector Machine, (2004)

[6]

Taloy A., McCabe R.W., Removal of hydrogen bonding interferences in the near infrared spectroscopic determination of dicarboxylic acids in diols, J. Near Infrared Spectroscopy, 12, 2, pp. 101-104, (2004)

[7]

Zhang R., Zeng S., Xia Y., Et al., Application of support vector regression for reconstruction of non-uniform strain profile along the fiber grating, Acta Optica Sinica, 28, 8, pp. 1513-1517, (2008)

[8]

Zhang L., Su S., Wang L., Et al., Study on application of Fourier transformation near-infrared spectroscopy analysis with support vector machine, Spectroscopy and Spectral Analysis, 25, 1, pp. 33-35, (2005)

[9]

Agricultural criterion of people's republic of China-microbial organic fertilizer

[10]

Thompson W.H., Leege P.B., Millner P.D., Et al., Test methods for the examination of composting and compost, (2002)

← 1 2 →