Prediction Using Different Classification Methods of Tree Species Depending on Contact Angle Values

Abstract

Nowadays, in various studies, the tree type can be determined according to the different properties of a tree material such as mechanical, chemical, physical properties, anatomy, but these studies are both long-lasting and require cost. Especially knowing the wettability of wooden materials used in outdoor weather conditions gives information about the usability of the material (pool edge, sauna, siding) in these weather conditions. In this study, the determination of the type of wood material was done by artificial neural networks (ANN), support vector machines (DVM), K-nearest neighbor (K-EYK) and Naive Bayes (NB) method according to the wettability feature. Contact angles of heat treated and unheat treated cedar (Cedrus Libani), Iroko (Chlorophora excelsa), Ash (Fraxinus excelsior) and Spruce (Picea abies) samples were determined. Later, artificial neural networks (ANN), support vector machines, K-nearest neighbor and Naive bayes classification methods have been estimated. It will be fast, practical and economical with this method used in the study to determine which wood species belongs to, depending on the wettability property measured by an easy method. Determination of the tree type with dropping method easily will contribute to the restoration and strengthening works.

Keywords

• Wettability
• Contact angle
• Wood Type
• Prediction
• Classification methods
• Machine learning

Temas Açısı Değerlerine Bağlı Ağaç Türlerinin Farklı Sınıflandırma Yöntemleri İle Tahmini

Öz

Günümüzde çeşitli çalışmalarda bir ağaç malzemenin mekanik, kimyasal, fiziksel özellikleri, anatomisi gibi farklı özelliklerine göre ağaç türü tespit edilebilmekle birlikte bu çalışmalar hem uzun sürmekte hem de maliyet gerektirmektedir. Özellikle dış hava koşullarında kullanılan ısıl işlem görmüş ahşap malzemelerin ıslanabilirlik özelliğinin bilinmesi malzemenin bu hava şartlarında hangi alanda (havuz kenarı, sauna, dış cephe kaplaması vb.) kullanılabilirliği hususunda bilgi vermektedir. Bu çalışmada ıslanabilirlik özelliğine göre yapay sinir ağları (YSA), destek vektör makineleri (DVM), K-en yakın komşu (K-EYK) ve Naive Bayes (NB) yöntemi ile ağaç malzemenin türünün tespiti işlemi yapılmıştır. Isıl işlem görmüş ve ısıl işlem görmemiş Sedir (Cedrus Libani), Iroko (Chlorophora excelsa), Dişbudak (Fraxinus excelsior) ve Ladin (Picea abies) numunelerin damla metodu ile temas açıları belirlenmiştir. Daha sonra yapay sinir ağları (YSA), destek vektör makineleri, K-en yakın komşu ve Naive bayes sınıflandırma metotları ile ağaç türlerinin tahmini yapılmıştır. Ahşap malzemenin kolay bir metot ile ölçülen ıslanabilirlik özelliğine bağlı olarak hangi ağaç türüne ait olduğunun belirlenmesi çalışmada kullanılan bu yöntem ile hızlı, pratik ve ekonomik olacaktır. Damlatma metodu ile ağaç türünün kolaylıkla belirlenmesi, restorasyon ve güçlendirme çalışmalarına katkı sağlayacaktır.

Anahtar Kelimeler

• Islanabilirlik
• Temas açısı
• Ağaç türü
• Tahmin
• Sınıflandırma metodları
• Makine öğrenmesi

References

1. Antipov, G., Berrani, S. A., Dugelay, J. L. (2016). Minimalistic CNN-based ensemble model for gender prediction from face images. Pattern recognition letters, 70, 59-65.
2. Chai, T., Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)–Arguments against avoiding RMSE in the literature. Geoscientific model development, 7(3), 1247-1250.
3. Clinton, N., Holt, A., Scarborough, J., Yan, L. I., & Gong, P. (2010). Accuracy assessment measures for object-based image segmentation goodness. Photogramm. Eng. Remote Sens, 76(3), 289-299.
4. Cruz, J. A., Wishart, D. S. (2006). Applications of machine learning in cancer prediction and prognosis. Cancer informatics, 2, 117693510600200030.
5. De Marsico, M., Petrosino, A., & Ricciardi, S. (2016). Iris recognition through machine learning techniques: A survey. Pattern Recognition Letters, 82, 106-115.
6. Furey, T. S., Cristianini, N., Duffy, N., Bednarski, D. W., Schummer, M., Haussler, D. (2000). Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics, 16(10), 906-914.
7. Gerardin, P., Petric, M., Petrissans, M., Lambert, J., Ehrhrardt, J.J. (2007). Evolution of Wood Surface Free Energy after Heat Treatment. Polym Degrad Stabil 92:653–657.
8. Gulpen, S. F. J. (2014). Using Country-level Forest Coverage to Analyze the Existence of an Environmental Kuznets Curve, Master's Thesis, Oregon State University, Corvallis, OR, USA.

9. Hakkou M, Petrissans M, Zoulalian A, Gerardin P (2005). Investigation of Wood Wettability Changes During Heat Treatment on the Basis of Chemical Analysis. Polym Degrad Stabil 89:1–5.
10. Haralick, R. M., Shanmugam, K., & Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6), 610-621.
11. Jain, A. K., Mao, J., Mohiuddin, K. M. (1996). Artificial neural networks: A tutorial. Computer, 29(3), 31-44.
12. Juang, B. H., Hou, W., Lee, C. H. (1997). Minimum classification error rate methods for speech recognition. IEEE Transactions on Speech and Audio processing, 5(3), 257-265.
13. Kamdem, D.P., Pizzi, A., Jermannaud, A., (2002). Durability of heat-treated wood. Holz als Roh-und Werkstoff 60, 1–6.
14. Kılınçarslan, Ş., Şimşek Türker, Y. (2019). Determination of Contact Angle Values of Heat-treated Spruce (Picea abies) Wood with Image Analysis Program. Biomed J Sci & Tech Res 18(4), DOI: 10.26717/BJSTR.2019.18.003183.
15. Kılınçarslan, Ş., Şimşek Türker, Y. (2020a). Investigation of Wooden Beam Behaviors Reinforced with Fiber Rein-forced Polymers. Organic Polymer Material Research, 02 (01), 1-7.
16. Kılınçarslan, Ş., Şimşek Türker, Y. (2020b). Ahşap Malzemelerin FRP ile Güçlendirilmesinin Sürdürülebilirlik Açısından Değerlendirilmesi. Teknik Bilimler Dergisi, 10(1), 23-30.
17. Kılınçarslan, Ş., Şimşek Türker, Y.(2020c). Physical-Mechanical Properties Variation with Strengthening Polymers. Acta Physica Polonica, A., 137.
18. Kılınçarslan, Ş., Şimşek Türker, Y. (2020d). Ahşap Malzemelerin Islanabilirlik Özelliği Üzerine Isıl İşlem Uygulamasının Etkisi. Mühendislik Bilimleri ve Tasarım Dergisi, 8(2), 460-466.
19. Kocaefe, D., Poncsak, S., Doré, G., & Younsi, R. (2008). Effect of heat treatment on the wettability of white ash and soft maple by water. Holz als Roh-und Werkstoff, 66(5), 355-361.
20. Kotsiantis, S. B., Zaharakis, I., Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160, 3-24.
21. Kvålseth, T. O. (1985). Cautionary note about R 2. The American Statistician, 39(4), 279-285.
22. Langdon, W. B., Dolado, J., Sarro, F., & Harman, M. (2016). Exact mean absolute error of baseline predictor, MARP0. Information and Software Technology, 73, 16-18.
23. Ma, Z., & Redmond, R. L. (1995). Tau coefficients for accuracy assessment of classification of remote sensing data. Photogrammetric Engineering and Remote Sensing, 61(4), 435-439.
24. Manevitz, L. M., Yousef, M. (2001). One-class SVMs for document classification. Journal of machine Learning research, 2(Dec), 139-154.
25. Mathur, A., Foody, G. M. (2008). Multiclass and binary SVM classification: Implications for training and classification users. IEEE Geoscience and remote sensing letters, 5(2), 241-245.
26. Mayes, D., Oksanen, O. (2002). Thermowood Handbook. By: Thermowood, Finnforest, Stora, 5-15.
27. Mazela, B., Zakrzewski, R., Grzes’ kowiak, W., Cofta, G., Bartkowiak,M., (2004). Resistance of thermally modified wood to basidiomycetes.Wood Technology 7 (1), 253–262.
28. Militz, H. (2002). Thermal Treatment of Wood: European Processes And Their Background. IRG/WP 02-40241: 18 str., 33rd Annual Meeting . 12–17 May 2002.
29. Neumann, A.W., Spelt, J.K. (eds). (1996). Applied Surface Thermodynamics (Surfactant series v. 63). Marcel Dekker Inc, New York.
30. Nguyen, T. T., Ji, X., Nguyen, T. H. V., and Guo, M. (2017). Wettability modification of heat-treated wood (HTW) via cold atmospheric-pressure nitrogen plasma jet (APPJ) Holzforschung 72(1), 37-43. DOI: 10.1515/hf-2017-0004.
31. Petrissans, M., Gerardin, P., El Bakali, I., Serraj, M. (2003). Wettability of Heat-Treated Wood. Holzforschung 57:301–307.
32. Ramírez-Gallego, S., Krawczyk, B., García, S., Woźniak, M., Benítez, J. M., & Herrera, F. (2017). Nearest neighbor classification for high-speed big data streams using spark. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47(10), 2727-2739.
33. Rasjid, Z. E., & Setiawan, R. (2017). Performance comparison and optimization of text document classification using k-NN and naïve bayes classification techniques. Procedia computer science, 116, 107-112.
34. Sahin, C.K., Onay, B. (2020). Alternative wood species for playgrounds wood from fruit trees, Wood Research, 65(1):149-160.
35. Sahin, H.T., Arslan, M.B., Korkut, S. Sahin, C. (2011). Colour changes of heat‐treated woods of redbud maple. European hophornbeam and oak. Color Research & Application. 36(6),462-466.
36. Sahin, C.K., Topay, M. Var, A.A. 2020. A study on suitability of some wood species for landscape applications: surface color, hardness and roughness changes at outdoor conditions, Wood Research, 65(3),395-404.
37. Sanderman, W., Augustin, H., (1963). Chemical investigation on thethermal decomposition of wood-Part III: chemical investigation on thecourse of decomposition. Holz als Roh-und Werkstoff 22 (10), 377–386.
38. Saritas, M. M., Yasar, A. (2019). Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification. International Journal of Intelligent Systems and Applications in Engineering, 7(2), 88-91.
39. Shi, Q., Gardner, D.J., Wang, J.Z. (1997). Surface Properties of Polymeric Automobile Fluff Particles Characterized by Inverse Gas Chromatography and Contact Angle Analysis. In: Int. Conf. Of Woodfiber-Plast. Compos. 4th Forest Product Society, Madison, USA, pp 245–256.
40. Viitaniemi, P., Jamsa, S., Ek, P., Viitanen, H. (2001). Method for Increasing the Resistance of Cellulosic Products against Mould and Decay. in: European Patent Spesification, (Ed.) V.T.R.C.o. Finland, Vol. EP695408B1.
41. Walinder, MEP., Johansson, I. (2001). Measurement of Wood Wettability by the Wilhelmy Method. Holzforschung 1(55):21–32.
42. Walinder, MEP., Strom, G. (2001). Measurement of Wood Wettability by the Wilhelmy Method. Holzforschung 2(55):33–41.
43. Zhang, M. L., Peña, J. M., & Robles, V. (2009). Feature selection for multi-label naive Bayes classification. Information Sciences, 179(19), 3218-3229.