Advertisement

Journal of Thermal Analysis and Calorimetry

, Volume 104, Issue 1, pp 87–100 | Cite as

Functional nonparametric classification of wood species from thermal data

  • Javier Tarrío-SaavedraEmail author
  • Salvador Naya
  • Mario Francisco-Fernández
  • Jorge López-Beceiro
  • Ramón Artiaga
Article

Abstract

In this study, thermogravimetric (TG) and differential scanning calorimetry (DSC) curves, obtained by means of a simultaneous TG/DSC analyzer, and statistical functional nonparametric methods are used to classify different wood species. The temperature ranges, where the highest probability of correct classification is reached, are also computed. As each observation is a curve, a nonparametric functional discriminant technique based on the Bayes rule and the Nadaraya–Watson regression estimator is used. It assigns a future observation to the highest probability predefined class (supervised classification). The smoothing parameter needed in this nonparametric method is selected according to the cross-validation technique. The method proposed is applied to a sample of 49 wood items (7 per wood class) and also to classify between hardwoods and softwoods. In all the cases, the samples have been successfully classified, obtaining better results with the TG curves. The results are compared with those obtained with other nonparametric methods based on boosting algorithm. A discussion about the relation of the obtained results with the referenced wood component degradation temperature ranks is presented.

Keywords

Wood Nonparametric classification Functional data analysis Thermal analysis 

Notes

Acknowledgements

This study was supported by the Ministry of Education and Science MTM2008-00166 (ERDF included), and by Xunta de Galicia, under Grant No.PGIDIT07PXIB105259PR. The authors wish to express special thanks to Manuel Febrero Bande for his valuable comments.

References

  1. 1.
    Guindeo Casasús A, García Esteban L, Peraza Sánchez F, Arriaga Martitegui F. Especies de maderas. Madrid: Asociación de investigación técnica de las industrias de la madera ycorcho (AITIM); 1997.Google Scholar
  2. 2.
    Lewis IR, Daniel NW, Chaffin NC, Griffiths PR. Raman spectrometry and neural networks for the classification of wood types-1. Spectrochim Acta A-Mole Biomole Spectrosc. 1994;50:1943–58.Google Scholar
  3. 3.
    Miller RB. Structure of wood. In: Wood handbook: Wood as an engineering material. Madison, WI: Woodhead Publishing Limited, Department of Agriculture, Forest Service, Forest Products Laboratory; 1999.Google Scholar
  4. 4.
    Cavalin P, Oliveira LS, Koerich AL, Britto AS. Wood defect detection using grayscale images and an optimized feature set. In: Proceedings IEEE Ind. Electron (IECON). Singapore: World Scientific; 2006. pp. 3408–12.Google Scholar
  5. 5.
    Fuentealba C, Simon C, Choffel D, Chawentier P, Massons D. Wood products identification by internal characteristics readings. In: Proceedings IEEE-ICIT. Hammamet: IEEE; 2004.Google Scholar
  6. 6.
    Gu IY, Andersson H, Vicen R. Automatic classification of wood defects using support vector machines. In: Bole L, Kulikowski JL, Wojciechoswski K, editors. ICCVG 2008, Lecture Notes in Computer Science. Berlin Heilderberg: Springer-Verlag; 2009. pp. 356–67.Google Scholar
  7. 7.
    Lampinen J, Smolander S, Korhonen M. Wood surface inspection system based on generic visual features. In: Fogelman F, Gallinari SP, editors. Industrial applications of neural networks. Paris: World Scientic; 1995. pp. 35–42.Google Scholar
  8. 8.
    Watanabe K, Hart JF, Mansfield SD, Avramidis S. Near-infrared technology applications for quality control in wood processing. In: Ridley-Ellis DJ, Moore JR, editors. Proceedings of the final conference of COST Action E53, quality control for wood & wood products. Edinburgh, UK: Forest Products Research Institute/Centre for Timber Engineering, Edinburgh Napier University; 2010.Google Scholar
  9. 9.
    Khalid M, Lee ELY, Yusof R, Nadaraj M. Design of an intelligent wood species recognition system. Int J Simul Syst Sci Technol. 2008;9:9–19.Google Scholar
  10. 10.
    Lavine BK, Davidson CE, Moores AJ, Griffiths PR. Raman spectroscopy and genetic algorithms for the classification of wood types. Appl Spectrosc. 2001;55:960–66.CrossRefGoogle Scholar
  11. 11.
    Nuopponen MH, Birch GM, Sykes RJ, Lee SJ, Stewart DJ. Estimation of wood density and chemical composition by means of diffuse reflectance mid-infrared fourier transform (DRIFT-MIR) spectroscopy. J Agric Food Chem. 2006;54:34–40.CrossRefGoogle Scholar
  12. 12.
    Piuri V, Scotti F. Design of an automatic wood types classification system by using fluorescence spectra. IEEE Trans Syst Man Cybern C-Appl Rev. 2010;40:358–66.CrossRefGoogle Scholar
  13. 13.
    Yang H, Lewis IR, Griffiths PR. Raman spectrometry and neural networks for the classification of wood types. 2. Kohonen self-organizing maps. Spectrochim Acta A-Mole Biomol Spectrosc. 1999;55:2783–91.CrossRefGoogle Scholar
  14. 14.
    Ferraty F, Vieu P (2006) Nonparametric functional data analysis. Berlin: Springer-Verlag.Google Scholar
  15. 15.
    Ramsay JO, Silverman BW. Functional data analysis 2nd ed. New York, Springer-Verlag; 2005.Google Scholar
  16. 16.
    Ramsay JO, Silverman BW. Applied functional data analysis. New York: Springer-Verlag; 2002.CrossRefGoogle Scholar
  17. 17.
    Alén R, Kuoppala E, Pia O. Formation of the main degradation compound groups from wood and its components during pyrolysis. J Anal Appl Pyrolysis. 1996;36:137–48.CrossRefGoogle Scholar
  18. 18.
    Gašparovič L, Koreňová Z, Jelemenský L. Kinetic study of wood chips decomposition by TGA. Chem Pap. 2009;64:174–81.Google Scholar
  19. 19.
    Grønli MG, Várhegyi G, Blasi C. Thermogravimetric analysis and devolatilization kinetics of wood. Ind Eng Chem Res. 2002;41:4201–08.CrossRefGoogle Scholar
  20. 20.
    Müller-Hagedorn M, Bockhorn H, Krebs L, Müller U. A comparative kinetic study on the pyrolysis of three different wood species. J Anal Appl Pyrolysis. 2003;68–69:231–49.CrossRefGoogle Scholar
  21. 21.
    Raveendran K, Ganesh A, Khilar KC. Pyrolysis characteristics of biomass and biomass components. Fuel. 1996;75:987–98.CrossRefGoogle Scholar
  22. 22.
    Roberts AF. A review of kinetics data for the pyrolysis of wood and related substances. Combust Flame. 1970;14:261–72.CrossRefGoogle Scholar
  23. 23.
    Wang S, Wang K, Liu Q, Gu Y, Luo Z, Cen K, Fransson T. Comparison of the pyrolysis behavior of lignins from different tree species. Biotechnol Adv. 2009;27:562–7.CrossRefGoogle Scholar
  24. 24.
    Korošec RC, Lavrič B, Rep G, Pohleven F, Bukovec P. Thermogravimetry as a possible tool for determining modification degree of thermally treated Norway spruce wood. J Therm Anal Calorim. 2009;98:189–95.CrossRefGoogle Scholar
  25. 25.
    Mohan D, Pittman JCU, Steele PH. Pyrolysis of wood/biomass for bio-oil: a critical review. Energy Fuel 2006;20:848–89.CrossRefGoogle Scholar
  26. 26.
    Bühlmannand P, Hothorn T. Boosting algorithms: regularization, prediction and model fitting. Stat Sci. 2007;22:477–505.CrossRefGoogle Scholar
  27. 27.
    Prime RB, Bair HE, Gallagher PK, Riga A. Thermogravimetric analysis (TGA). In: Menczel JD, Prime RB, editors. Thermal analysis of polymers Fundamentals and applications. San José, CA: Wiley; 2009. pp. 7–240.Google Scholar
  28. 28.
    López-Granados F, Peña Barragán JM, Jurado-Expósito M, Francisco-Fernández M, Cao R, Alonso-Betanzos A, Fontenla-Romero O. Multispectral classification of grass weeds and wheat (Triticum durum) using linear and nonparametric functional discriminant analysis and neural networks. Weed Res. 2008;48:28–37.CrossRefGoogle Scholar
  29. 29.
    Naya S, Cao R, Artiaga R, García A. New method for material classification from TGA data by nonparametric regression. Mater Sci Forum. 2006;514–516:1452–6.CrossRefGoogle Scholar
  30. 30.
    R Development Core Team. R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. 2008. http://www.R-project.org. Accesed 1 Sep 2010.
  31. 31.
    Fraiman R, Muniz G. Trimmed means for functional data. Test. 2001;10:419–40.CrossRefGoogle Scholar

Copyright information

© Akadémiai Kiadó, Budapest, Hungary 2010

Authors and Affiliations

  • Javier Tarrío-Saavedra
    • 1
    Email author
  • Salvador Naya
    • 2
  • Mario Francisco-Fernández
    • 1
  • Jorge López-Beceiro
    • 3
  • Ramón Artiaga
    • 3
  1. 1.Departamento de Matemáticas. Facultad de InformáticaUniversidade da CoruñaCorunnaSpain
  2. 2.Departamento de Matemáticas. Escuela Politécnica SuperiorUniversidade da CoruñaCorunnaSpain
  3. 3.Departamento de Ingeniería Industrial II. Escuela Politécnica SuperiorUniversidade da CoruñaCorunnaSpain

Personalised recommendations