Modeling Wood Density of Larch by Near-Infrared Spectrometry and Support Vector Machine

Abstract:

Model for predicting wood density of Larch was established using near-infrared spectroscopy (NIR) combined with support vector machine (SVM). A hundred and seventeen Larch samples were used in the study. Wood density of samples was measured according to standard test methods for physical and mechanical properties of wood. Support vector machines for regression (SVR) was used for model building. Radial basis function (RBF) was used as kernel function to establish a model for predicting wood density. For the train set, the coefficient of determination (R²) and the mean square error (MSE) were 0.8504 and 0.6460×10^-3, while the R² and MSE was 0.8520 and 0.4451×10^-3, respectively, for the test set. Results showed that using SVM in near-infrared spectroscopy calibration could significantly improve the model performance in order to rapidly and accurately predict wood density.

• Periodical: Applied Mechanics and Materials (Volumes 55-57)
• Pages: 433-438
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.55-57.433
• Online since: May 2011
• Authors: Ya Zhao Zhang, Yao Xiang Li, Hong Fu Zhang, Hui Juan Zhang, Pai Li
• Keywords: Larch, Near Infrared Spectroscopy (NIRS), Support Vector Machine (SVM), Wood Density

References

[1] Y. Li, H. Zhang, Y. Zhang, Hui Zhang, and P. Li: Modeling of Dahurian Larch wood density based on NIR and multivariate analysis. Journal of Northeast Forestry University. Vol. 38 (2010), p.27.

DOI: 10.1109/icmtma.2010.328

[2] H.F. Zhang and Y.X. Li: Literature Review on Application of Near-infrared spectroscopy in wood Non-destructive Testing. Forest Engineering Vol. 25 (2009), p.25.

[3] W.Z. Lu: Modern NearInfrared Spectroscopy Analysis Technology (China Petrochemical Press, Beijing 2007).

[4] Z. Yang, Z.H. Jiang, B.H. Fei and J.L. Liu: Application of Near Infrared (NIR) Spectroscopy to Wood Science. Scientia Silvae Sinicae Vol. 41 (2005), p.177.

[5] A.M. Huang, Z.H. Jiang and G.Y. Li: Determination of Holocellulose and Lignin Content in Chinese Fir by Near Infrared Spectroscopy. Spectroscopy and Spectral Analysis Vol. 27 (2007), p.1328.

[6] A.M. Huang, B.H. Fei, Z.H. Jiang and C.Y. Hse: Influence of Sample Surface Roughness on Mathematical Model of NIR Quantitative Analysis of Wood Density. Spectroscopy and Spectral Analysis Vol. 27 (2007), p.1700.

[7] Cortes C and Vapnik V: Support-vector network. Machine Learning Vol. 20 (1995), p.273.

[8] S. Sathiya Keerthi and C.J. Lin: Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Computation Vol. 15 (2003), p.1667.

DOI: 10.1162/089976603321891855

[9] H.M. Hao, X.J. Tang, P. Bai, J.H. Liu and C.C. Zhu: Quantitative Analysis of Multi-Component Gas Mixture Based on KPCA and SVR. Spectroscopy and Spectral Analysis Vol. 28 (2008), p.1286.

[10] X.D. Gao and H. Liu: Combination predication model based on SVR and its application. Computer Engineering and Design  Vol. 30 (2009), p.4506.