Support vector machines in wood identification: the case of three Salix species from Turkey

The aim of this study was to use a support vector machine (SVM) for the first time as a predictive method for differentiating species of Salix wood through the biometric analysis of their anatomy using wood taken from basal disks of 3 species. The purpose of a SVM is to construct optimal decision boundaries among classes in a decision plane. A decision plane separates a set of objects having different class memberships. In this study, the decision plane has 3 different wood species. Timely and accurate identification of tree species can be crucial in forestry. The similarity of structures in wood anatomy across many species, especially in the case of Salix species, means that they cannot be differentiated anatomically using traditional methods. SVM can be an effective tool for identifying similar taxa with a high percentage of accuracy. A SVM was used to differentiate Salix alba, Salix caprea, and Salix elaeagnos growing in Turkey. These Salix species are sufficiently similar that it is not possible to differentiate between them using traditional anatomical methods. However, a SVM was able to differentiate between the 3 species with a high degree of probability using the biometrics of wood anatomy. For the purposes of classification, a SVM with linear kernel function was designed; it attained an 80.6% success rate in the training group and a 95.2% success rate in the testing group. After feature selection, our SVM was able to classify the 3 species with notable success. If the number of samples were increased, the SVM would return more precise classification results.

Anahtar Kelimeler:

Key words: Biometry, classification, Salix alba, Salix caprea, Salix elaeagnos, SVM

Support vector machines in wood identification: the case of three Salix species from Turkey

Keywords:

Key words: Biometry, classification, Salix alba, Salix caprea, Salix elaeagnos, SVM,

PDF

___

Argus GW (1997) Infrageneric classification of Salix L. (Salicaceae) in the New World. Syst Bot Monogr 52: 1–121.
Arıhan O, Güvenç A (2011) Studies on the anatomical structure of stems of willow (Salix L.) species (Salicaceae) growing in Ankara province, Turkey. Turk J Bot 35: 535–551.
Bharathi A, Natarajan AM (2011) Cancer classification using support vector machines and relevance vector machine based on analysis of variance features. J Comput Sci 7: 1393–1399.
Dubey A, Chouhan A (2011) Support vector machine for classification of HIV, plant and animal miRNA’s. Int J Bioinforma Res 3: 202– 20
Esteban LG, Fernández FG, Palacios de Palacios Pde, Romero RM, Cano NN (2009) Artificial neural networks in wood identification: the case of two Juniperus species from the Canary Islands. IAWA J 30: 87–94.
Fang Z, Zhao S, Skvortsov AK (1999) Salicaceae In: Wu Z, Raven PH (eds.) Flora of China. Science Press – Missouri Botanical Garden Press, Beijing – St. Louis.
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann of Eugen 7: 111–132.
Fletcher R (1987) Practical Methods of Optimization. 2nd ed., John Wiley and Sons, New York.
Gu IYH, Andersson H, Vicen R (2009) Automatic classification of wood defects using support vector machines. Comput Vis and Graph Lecture Notes in Comput Sci 5337: 356–367.
Güner A (2000) Salix L. In: Güner A, Özhatay N, Ekim T, Başer KHC (eds.) Flora of Turkey and the East Aegean Islands Vol. 11. Edinburgh University Press, Edinburgh.
Güner A, Zielinski J (1993) Salix rizeensis (Salicaceae): a new willow from NE Turkey. Karaca Arbor 1: 1–5.
Han J, Kamber M (2006) Data Mining: Concepts and Techniques. 2nd ed. Morgan Kaufmann Publishers, New York.
Heywood VH, Brummitt RK, Culham A, Seberg O (2006) Flowering Plant Families of the World. Royal Botanic Gardens, Kew.
IAWA Committee (1989) AWA List of microscopic features for hardwood identification. IAWA Bull 10: 221–332.
Ives E (2001) A Guide to Wood Microtomy. Suffolk Offset, UK.
Jielinski Z, Tomaszewski D (2008) Salix anatolica (Salicaceae), a new species from Turkey. Ann Bot Fenn 45: 386–388.
Khalid M, Lee ELY, Yusof R, Nadaraj M (2008) Design of an intelligent wood species recognition system. Int J Simul Syst Sci Technol 9: 9–19.
Lipkowitz KB, Cundari TR (2007) Reviews in Computational Chemistry. Wiley-VCH, John Wiley & Sons Inc 23: pp. 291–400. Mabberley DJ (2008) Salix L. In: Mabberley’s Plant Book. A Portable Dictionary of Plants, Their Classification and Uses. Cambridge University Press, Cambridge.
Normand D (1972) Manuel D’identification des bois commerciaux, 1. Généralités. Centre Tech. For. Trop Nogent-sur-Marne.
Ohashi H (2001) Salicaceae of Japan. Science Reports of Tohoku University 4th Series 40: 269–396.
Özşahin Ş (2012) The use of Artificial Neural Network for modeling the moisture absorption and thickness swelling properties of oriented standard board. BioResources 7: 1053–1067.
Pham DT, Muhamad Z, Mahmuddin M, Ghanbarzadeh A, Koc E, Otri S (2007) Using the Bees Algorithm to Optimise a Support Vector Machine for wood defect classification. In: Proceedings of Third Virtual International Conference on Innovative Production Machines and Systems, IPROMS 2007, Cardiff UK, pp. 540–545. Skvortsov AK (1999) Willows of Russia and Adjacent Countries: Taxonomical and Geographical Revision (transl. from: Skvortsov AK (1968) Willows of the USSR: Taxonomic and Geographic Revision. Nauka, Moscow). Joensuu University. Joensuu.
Skvortsov AK, Edmondson JD (1970) Salix L. In: Davis PH (ed.) Flora of Turkey and the East Aegean Islands, Edinburgh: Edinburgh University Press Vol. 7: 694–716.
Tian Y, Zhao C, Lu S, Guo X (2011) Multiple classifier combination for recognition of wheat leaf diseases. Intell Autom Soft Co 17: 519–529.
Turhan K, Engin YZ, Kurt B (2011) Data Mining on Laboratory Test Orders: Female Genital Cancer Diagnosis Control by Using Support Vector Machines. In: Proceedings of VIIIth National Turkish Medical Informatics Conference Antalya Turkey, pp. 132–137.
Vapnik V, Lerner A (1963) Pattern recognition using generalized portrait method. Automat Rem Contr 24: 774–780.
Vapnik V, Chervonenkis AY (1974) Teoriya raspoznavaniya obrazov: Statisticheskie problemy obucheniya [Theory of pattern recognition: Statistical problems of learning]. Nauka, Moscow, Russia.
Vapnik V (1979) Estimation of Dependences Based on Empirical Data. Nauka, Moscow, Russia.
Vapnik V (1995) The Nature of Statistical Learning Theory. Springer, New York.
Vapnik V (1998) Statistical Learning Theory. Wiley-Interscience, New York.