Abstract
Quality classification of wood boards is an essential task in the sawmill industry, which is still usually performed by human operators in small to median companies in developing countries. Machine learning algorithms have been successfully employed to investigate the problem, offering a more affordable alternative compared to other solutions. However, such approaches usually present some drawbacks regarding the proper selection of their hyperparameters. Moreover, the models are susceptible to the features extracted from wood board images, which influence the induction of the model and, consequently, its generalization power. Therefore, in this paper, we investigate the problem of simultaneously tuning the hyperparameters of an artificial neural network (ANN) as well as selecting a subset of characteristics that better describes the wood board quality. Experiments were conducted over a private dataset composed of images obtained from a sawmill industry and described using different feature descriptors. The predictive performance of the model was compared against five baseline methods as well as a random search, performing either ANN hyperparameter tuning and feature selection. Experimental results suggest that hyperparameters should be adjusted according to the feature set, or the features should be selected considering the hyperparameter values. In summary, the best predictive performance, i.e., a balanced accuracy of 0.80, was achieved in two distinct scenarios: (i) performing only feature selection, and (ii) performing both tasks concomitantly. Thus, we suggest that at least one of the two approaches should be considered in the context of industrial applications.
The authors are grateful to FAPESP grants #2016/06538-0, #2018/02822-1 and #2019/07825-1.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdullah, A., Ismail, N.K.N., Kadir, T.A.A., Zain, J.M., Jusoh, N.A., Ali, N.M.: Agar wood grade determination system using image processing technique. In: Proceedings of the International Conference on Electrical Engineering and Informatics Institut Teknologi Bandung (2007)
Affonso, C., Rossi, A.L.D., Vieira, F.H.A., Carvalho, A.C.P.L.F.: Deep learning for biological image classification. Expert Syst. Appl. 85, 114–122 (2017). https://doi.org/10.1016/j.eswa.2017.05.039
Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M.: The balanced accuracy and its posterior distribution. In: 2010 20th International Conference on Pattern Recognition, pp. 3121–3124, August 2010. https://doi.org/10.1109/ICPR.2010.764
Cao, Y., et al.: A new intelligence fuzzy-based hybrid metaheuristic algorithm for analyzing the application of tea waste in concrete as natural fiber. Comput. Electron. Agric. 190, 106420 (2021)
De Souza, L.A., et al.: Fine-tuning generative adversarial networks using metaheuristics-a case study on Barrett’s esophagus identification. In: Bildverarbeitung für die Medizin, pp. 205–210 (2021)
Gu, I.Y.H., Andersson, H., Vicen, R.: Automatic classification of wood defects using support vector machines. In: Bolc, L., Kulikowski, J.L., Wojciechowski, K. (eds.) ICCVG 2008. LNCS, vol. 5337, pp. 356–367. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02345-3_35
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. Newsl. 11(1), 10–18 (2009). https://doi.org/10.1145/1656274.1656278
Haralick, R., Shanmugam, K., Distein, I.: Textual features for image classification. IEEE Trans. Syst. Man Cybern. SMC 3(6), 610–621 (1973)
Kennedy, J., Eberhart, R.C.: A discrete binary version of the particle swarm algorithm. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 5, pp. 4104–4108, October 1997. https://doi.org/10.1109/ICSMC.1997.637339
Kennedy, J., Eberhart, R.: Swarm Intelligence. Morgan Kaufmann Publishers (2001)
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948. Perth, Australia (1995)
Luo, G.: A review of automatic selection methods for machine learning algorithms and hyper-parameter values. Netw. Model. Anal. Health Inform. Bioinforma. 5(1), 1–16 (2016). https://doi.org/10.1007/s13721-016-0125-6
Ojala, T., Pietikainen, M., Harwood, D.: Comparative study of texture measures with classification based on feature distributions. Pattern Recogn., 51–59 (1996)
Passos, L.A., Paulo Papa, J.: Fine-tuning infinity restricted Boltzmann machines. In: 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 63–70. IEEE (2017)
Pereira, C.R., Passos, L.A., Rodrigues, D., de Souza, A.N., Papa, J.P.: JADE-based feature selection for non-technical losses detection. In: Tavares, J.M.R.S., Natal Jorge, R.M. (eds.) VipIMAGE 2019. LNCVB, vol. 34, pp. 141–156. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32040-9_16
Pham, D.T., Alcock, R.J.: Automatic detection of defects on birch wood boards. Proc. Inst. Mech. Eng. Part E J. Process Mech. Eng. 210(1), 45–52 (1996). https://doi.org/10.1243/0954408991529852
Qi, C., Fourie, A., Chen, Q.: Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill. Constr. Build. Mater. 159, 473–478 (2018). https://doi.org/10.1016/j.conbuildmat.2017.11.006
R Core Team: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2014)
Roder, M., Passos, L.A., de Rosa, G.H., de Albuquerque, V.H.C., Papa, J.P.: Reinforcing learning in deep belief networks through nature-inspired optimization. Appl. Soft Comput. 108, 107466 (2021)
Roder, M., de Rosa, G.H., Passos, L.A., Papa, J.P., Rossi, A.L.D.: Harnessing particle swarm optimization through relativistic velocity. In: 2020 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8. IEEE (2020)
Roder, M., Rossi, A.L.D., de Oliveira Affonso, C.: Boosting machine learning techniques for wood quality classification by particle swarm optimization. In: Encontro Nacional de Inteligência Artificial e Computacional. Sociedade Brasileira de Computação (2017)
Rodrigues, D., de Rosa, G.H., Passos, L.A., Papa, J.P.: Adaptive improved flower pollination algorithm for global optimization. In: Yang, X.-S., He, X.-S. (eds.) Nature-Inspired Computation in Data Mining and Machine Learning. SCI, vol. 855, pp. 1–21. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-28553-1_1
Shi, Y., Eberhart, R.: A modified particle swarm optimizer. In: 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98TH8360), pp. 69–73, May 1998. https://doi.org/10.1109/ICEC.1998.699146
Tiryaki, S., Malkoçoğlu, A., Özşahin, Ş.: Using artificial neural networks for modeling surface roughness of wood in machining process. Constr. Build. Mater. 66, 329–335 (2014). https://doi.org/10.1016/j.conbuildmat.2014.05.098
Vieira, F.H.A.: Image processing through machine learning for wood quality classification. Ph.D. thesis, Faculdade de Engenharia de Guaratinguetá (FEG), UNESP (2016)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1(6), 80–83 (1945)
Acknowledgments
The authors are grateful to FAPESP grants #2016/06538-0, #2018/02822-1, #2019/07825-1, and #2023/10823-6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Roder, M., Passos, L.A., Papa, J.P., Rossi, A.L.D. (2023). Feature Selection and Hyperparameter Fine-Tuning in Artificial Neural Networks for Wood Quality Classification. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14196. Springer, Cham. https://doi.org/10.1007/978-3-031-45389-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-45389-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45388-5
Online ISBN: 978-3-031-45389-2
eBook Packages: Computer ScienceComputer Science (R0)