Data Mining and Pixel Distribution Approach for Wood Density Prediction

Key Findings & Data:The designed artificial neural network model and random forest algorithm allowed the prediction of density with an accuracy of 95.19% and 96.36%, respectively for the testing phase.

💡

Conclusion & Impact:As a result, this study showed that pixel density and data mining have the potential to be used as an instrument for predicting the density of wood.

🔬Design:Modeling & Simulation

📍Scope:Comprehensive Sample

⚙️Variables:Data mining · artificial neural networks · random forest

Abstract

Wood has a strategic importance in economic development. Innovations are the basic premise of commercial success in the wood industry, as in all industries. The density of wood provides valuable information about the physical and mechanical properties of the wood, and it is also directly related to the productivity in the forest industry. Many non-destructive test studies have been conducted to evaluate the physical properties of wood structures. This study was conducted to predict the density of wood in oak (Quercus robur) and beech (Fagus orientalis L.) using the number of pixels in grayscale image and data mining. To this purpose, pixel density of data were saved from wood images. This data was used as descriptor variables in artificial neural networks and random forest algorithm. The designed artificial neural network model and random forest algorithm allowed the prediction of density with an accuracy of 95.19% and 96.36%, respectively for the testing phase. As a result, this study showed that pixel density and data mining have the potential to be used as an instrument for predicting the density of wood.

Özet

Ahşap ekonomik kalkınmada stratejik bir öneme sahiptir. Yenilikler, tüm endüstrilerde olduğu gibi ahşap endüstrisinde de ticari başarının temelini oluşturur. Ahşabın yoğunluğu, ahşabın fiziksel ve mekanik özellikleri hakkında değerli bilgiler sağlar ve ayrıca orman endüstrisindeki verim ile de doğrudan ilgilidir. Ahşap yapıların fiziksel özelliklerini değerlendirmek için birçok tahribatsız test çalışmaları yapılmıştır. Bu çalışma, gri tonlamalı görüntüdeki piksel sayısı ve veri madenciliğini kullanarak meşe (Quercus robur) ve kayın (Fagus orientalis L.) ağacının yoğunluğunu tahmin etmek için yapıldı. Bu amaçla, ahşap görüntülerden elde edilen piksel yoğunluğu verileri kaydedildi. Bu veriler yapay sinir ağları ve rastgele orman algoritmalarında tanımlayıcı değişkenler olarak kullanılmıştır. Tasarlanan yapay sinir ağı ve rastgele orman algoritmaları, test aşamasında sırasıyla % 95,19 ve % 96,36 doğrulukla yoğunluk tahmini sağladı. Sonuç olarak, bu çalışma piksel yoğunluğunun ve veri madenciliğinin ahşabın yoğunluğunu öngörmede bir araç olarak kullanılma potansiyeline sahip olduğunu göstermiştir.

Keywords

Data mining artificial neural networks random forest digital images wood

🔖

Cite This Article

BARDAK, T., BARDAK, S., SÖZEN, E. (2019). Data Mining and Pixel Distribution Approach for Wood Density Prediction. Bartın Orman Fakültesi Dergisi, Cilt: 21 - Sayı: 2, 386–396. https://ajindex.com/articles/108780

📄 Full Text PDF Viewer

Open in New Tab ↗

↗New Tab

📄

PDF görüntüleyici hazırlanıyor...

References (9)

Ao Y, Li H, Zhu L, Ali S, Yang Z. (2019). Identifying channel sand-body from multiple seismic attributes with an improved random forest algorithm. Journal of Petroleum Science and Engineering, Elsevier, 173, 781–792.
Chuchala D, Orlowski KA, Sandak A, Sandak J, Pauliny D, Barański J. (2014). The Effect of Wood Provenance and Density on Cutting Forces While Sawing Scots Pine (Pinus sylvestris L.). BioResources, 9(3), 5349–5361.
Diaconu D, Wassenberg M, Spiecker H. (2016). Variability of European beech wood density as influenced by interactions between tree-ring growth and aspect. Forest Ecosystems, 3(1), 6. Eskandarian S, Bahrami P, Kazemi P. (2017). A comprehensive data mining approach to estimate the rate of penetration: Application of neural network, rule based models and feature ranking. Journal of Petroleum Science and Engineering, 156, 605–615.
Foca G, Masino F, Antonelli A, Ulrici A. (2011). Prediction of compositional and sensory characteristics using RGB digital images and multivariate calibration techniques. Analytica Chimica Acta, 706(2), 238– 245. Gogebakan M, Erol H. (2018). A New Semi-Supervised Classification Method Based on Mixture Model Clustering for Classification of Multispectral Data. Journal of the Indian Society of Remote Sensing, 46(8), 1323–31.
Simon H. (1999). Neural networks: a comprehensive foundation, Prentice Hall. Hryniewicz P, Banaś W, Gwiazda A, Foit K, Sękala A, Kost G. (2015). Technological process supervising using vision systems cooperating with the LabVIEW vision builder. IOP Conference Series: Materials Science and Engineering, IOP Publishing, 95(1), 012086.
Khalid M, Lee E, Yusof R. (2008). Design of an intelligent wood species recognition system. International Journal of Simulation System, Science and Technology, 9(3), 9-19.
Komi M, Jun Li, Yongxin Z, Xianguo Z. (2017). Application of data mining methods in diabetes prediction,” in: 2017 2nd International Conference on Image, Vision and Computing (ICIVC), IEEE, 1006– 1010. Masanori K, Nakano T. (2004). Artificial weathering of tropical woods. part 2: color change. Holzforschung 58(5), 558–65.
Montes S, Hernández RE, Beaulieu J, Weber JC. (2007). Genetic variation in wood color and ıts correlations with tree growth and wood density of calycophyllum spruceanum at an early age in the peruvian amazon. New Forests 35(1), 57–73.
Lana MM, Tijskens LMM, van Kooten O. (2006). Effects of storage temperature and stage of ripening on RGB colour aspects of fresh-cut tomato peric