Adaptive GA-NN for MDF Prediction Model

Abstract:

This research presents a hybrid Genetic Algorithm Neural Network (GA-NN) model to replace the physical tests procedures of Medium Density Fiberboard (MDF). Data included in the model is MDF properties and its fiber characteristics. Multilayer Perceptron (MLP) NN model is reliable to learn from seven inputs fed to the network to produce prediction of three targets. In order to avoid result from local optimum scenario, GA optimizes synaptic weights of the network towards reducing prediction error. The research used a fixed probability rates for crossover and mutation for hybrid GA-NN model. GA-NN model is further improved using adaptive mechanism to help identify the best probability rates. The fitness value refers to Sum of Squared Error. Performance comparisons are among three models; namely NN with Back Propagation (BP), hybrid GA-NN and hybrid GA-NN with adaptive mechanism. Results show the hybrid GA-NN model perform much better than NN model used with back propagation optimizer. Adaptive mechanism in GA helps increase capability to converge at zero sooner than the ordinary GA.

• Periodical: Advanced Materials Research (Volume 980)
• Pages: 214-218
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.980.214
• Online since: June 2014
• Authors: Sh Ismail Faridah*, Abu Bakar Nordin
• Keywords: Adaptive, Genetic Algorithm (GA), Hybrid Model, MDF, Neural Network (NN), Prediction

References

[1] A.A. Radwan, H.M. El-Bakry, H.M. El-Hadad, A New Expert System for Repository Diseases by Using Neural Networks, Recent Researches in Applied Informatics WSEAS (2011) 296-306.

[2] A.A. Munot and K.K. Kumar, Long range prediction of Indian summer monsoon rainfall, Journal Earth System Science, 116-1 (2007) 73–79.

DOI: 10.1007/s12040-007-0008-4

[3] R. Lawrence, Using NN to Forecast Stock Market Prices, Univ of Manitoba (1997).

[4] H.A. Abbass, An evolutionary artificial neural networks approach for breast cancer diagnosis, Artificial Intelligence in Medicine, 25-3 (2002) 265-281.

DOI: 10.1016/s0933-3657(02)00028-3

[5] L.G. Esteban, F.G. Fernandez, P. Palacios and B.G. Rodrigo, Use of ANN as a predictive method to determine moisture resistance of particle and fiber boards under cyclic testing conditions, (UNE-EN 321) Wood and Fiber Science, 42-3 (2010) 1-11.

[6] D.F. Cook, C.C. Chiu, Predicting Internal Bond Strength of Particleboard utilizing a radial basis function Neural Network, Eng Application of Artificial Intelligence, 10-2 (1997) 171-177.

DOI: 10.1016/s0952-1976(96)00068-1

[7] T.M. Young, L.B. Shaffer, F.M. Guess, H. Bensmail, R.V. León, A comparison of multiple linear regression and quantile regression for modeling the internal bond of medium density fiberboard, Forest Products Journal 58-4 (2008).

[8] G. Painter, H. Budman and M. Pritzker, Prediction of oriented strand board properties from mat formation and compression operating conditions. Part 2: MOE prediction and process optimization, Wood Science Technology Springer 40 (2006) 291–307.

DOI: 10.1007/s00226-005-0050-9

[9] F.G. Fernandez, L.G. Esteban, P.D. Palacious, N. Navarro, M. Conde, Prediction of Std Particleboard Mech properties utilizing an ANN & subsequent comparison with a multivariate regression model, Investigacion Agraria: Sistemas y Recursos Forestales, 17-2 (2008).

DOI: 10.5424/srf/2008172-01033

[10] D.E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, Massachusetts: Addison-Wesley (1989).

[11] K.A. De Jong, Analysis of the behavior of a class of genetic adaptive systems, Ph.D. Dissertation, Dept of Computer and Comm Sciences, Univ of Michigan, Ann Arbor, MI, (1975).

[12] T. Back, Self Adaption in Genetic Algorithms, Towards a Practice of Autonomous Systems, MIT Press (1992) 263-271.

[13] L. Davis, Adapting operator probabilities in genetic algorithms, J. David Schaffer ed., Proceedings of the Third International Conference on Genetic Algorithms, San Mateo, CA: Morgan Kaufman Publishers, Inc., (1989) 61-69.

[14] N. Andre, H.W. Choo, S.Y. Baek, M.K. Jeong, T.M. Young, Prediction of internal bond strength in a medium density fibreboard process using multivariate statistical methods and variable selection, Wood Science Technology, Springer 42 (2008).

DOI: 10.1007/s00226-008-0204-7

[15] T.M. Young, Predictive Of The Physical Properties Of Wood Composites Using Genetic Algo, Wood Utilization Research Project, Univ of Tennessee Forest Product Center, (2004).

[16] F. Sh Ismail, N. Abu Bakar, N.E. Abdul Khalid and R. Mamat, Optimizing Oil Palm Fiberboard Properties Using Neural Network, IEEE Conference on Data Mining and Optimization, (2011) 271-275.

DOI: 10.1109/dmo.2011.5976540