Measurement of lumber moisture content based on PCA and GS-SVM

Abstract

Lumber moisture content (LMC) is the important parameter to judge the dryness of lumber and the quality of wooden products. Nevertheless the data acquired are mostly redundant and incomplete because of the complexity of the course of drying, by interference factors that exist in the dryness environment and by the physical characteristics of the lumber itself. To improve the measuring accuracy and reliability of LMC, the optimal support vector machine (SVM) algorithm was put forward for regression analysis LMC. Environmental factors such as air temperature and relative humidity were considered, the data of which were extracted with the principle component analysis method. The regression and prediction of SVM was optimized based on the grid search (GS) technique. Groups of data were sampled and analyzed, and simulation comparison of forecasting performance shows that the main component data were extracted to speed up the convergence rate of the optimum algorithm. The GS-SVM shows a better performance in solving the LMC measuring and forecasting problem.

Keywords

Lumber moisture content (LMC) / Principle component analysis (PCA) / Grid search (GS) / Support vector machine (SVM)

References

[1] Ataei M, Osanloo M. Using a combination of genetic algorithm and the grid search method to determine optimum cutoff grades of multiple metal deposits. Int J Surf Min Reclam Environ, 2004, 18: 60-78.

[2] Awadalla HSF, El-Dib AF, Mohamad MA, Reuss M, Hussein HMS. Mathematical modelling and experimental verification of wood drying process. Energy Convers Manag, 2004, 45: 197-207.

[3] Beyramysoltan S, Rajkó R, Abdollahi H. Investigation of the equality constraint effect on the reduction of the rotational ambiguity in three-component system using a novel grid search method. Anal Chim Acta, 2013, 791: 25-35.

[4] Camdevyren H, Demyr N, Kanik A, Keskyn S. Use of principal component scores in multiple linear regression models for prediction of Chlorophyll-a in reservoirs. Ecol Model, 2005, 181: 581-589.

[5] Chen GY, Xie WF. Pattern recognition with SVM and dual-tree complex wavelets. Image Vis Comput, 2007, 25: 960-966.

[6] Dahmani H, Selouani S, Doghmane N, O’Shaughnessy D, Chetouani M. On the relevance of using rhythmic metrics and SVM to assess dysarthric severity. Int J Biom, 2014, 6: 248-271.

[7] Diosan L, Rogozan A, Pecuchet JP. Learning SVM with complex multiple kernels evolved by genetic programming. Int J Artif Intell Tools, 2010, 19: 647-677.

[8] Fox SB, Culha M, Sepaniak MJ. Development of a grid search molecular mechanics modeling strategy to study elution behavior in cyclodextrin modified capillary electrophoresis. J Liq Chromatogr Relat Technol, 2001, 24: 1209-1228.

[9] Helena B, Pardo R, Vega M, Barrado E, Fernandez JM, Fernandez L. Temporal evolution of groundwater composition in an alluvial aquifer (Pisuerga river, Spain) by principal component analysis. Water Res, 2000, 34: 807-816.

[10] Huang SC. Integrating nonlinear graph based dimensionality reduction schemes with SVMs for credit rating forecasting. Expert Syst Appl, 2009, 36: 7515-7518.

[11] Isaksson T, Thelandersson S. Experimental investigation on the effect of detail design on wood moisture content in outdoor above ground applications. Build Environ, 2013, 59: 239-249.

[12] Kecman V. Support vector machines: an introduction, 2005, Berlin: Springer.

[13] Klaric M, Pervan S. Improving of maintenance of humidifying system in conventional wood kiln dryers. Drv Ind, 2012, 63: 87-94.

[14] Kuang YC, Yu JQ, Hu YC, Wang Y. Research and application of real estate document image classification based on SVMs and KNN. J Inf Comput Sci, 2013, 10: 6093-6100.

[15] Liu PY, Jia KB. A motion-characteristics-based unsymmetrical-cross multi-hexagon-grid search algorithm for fast motion estimation. Inf Technol J, 2013, 12: 3128-3133.

[16] Lu WZ, Wang WJ, Wang XK, Xu ZB, Leung AYT. Using improved neural network to analyze RSP, NOx and NO2 levels in urban air in Mong Kok, Hong Kong. Environ Monit Assess, 2003, 87: 235-254.

[17] Martinovic D, Horman I, Demirdzic I. Numerical and experimental analysis of a wood drying process. Wood Sci Technol, 2001, 35: 143-156.

[18] Nelson JDB, Damper RI, Gunn SR, Guo B. Signal theory for SVM kernel design with applications to parameter estimation and sequence kernels. Neurocomputing, 2008, 72: 15-22.

[19] Noori R, Kerachian R, Khodadadi A, Shakibayinia A. Assessment of importance of water quality monitoring stations using principal component and factor analyses: a case study of the Karoon River. J Water Wastewater, 2007, 63: 60-69.

[20] Noori R, Abdoli MA, Ameri-Ghasrodashti A, Jalili-Ghazizade M. Prediction of municipal solid waste generation with combination of support vector machine and principal component analysis: a case study of mashhad. Environ Prog Sustain Energy, 2009, 28: 249-258.

[21] Noori R, Abdoli MA, Jalili-Ghazizade M, Samifard R. Comparison of ANN and PCA based multivariate linear regression applied to predict the weekly municipal solid waste generation in Tehran. Iran J Public Health, 2009, 38: 74-84.

[22] Noori R, Karbassi AR, Sabahi MS. Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste predicting. J Environ Manag, 2010, 91: 767-771.

[23] Noori R, Khakpour A, Omidvar B, Farokhnia A. Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic. Expert Syst Appl, 2010, 37: 5856-5862.

[24] Noori R, Sabahi MS, Karbassi AR, Baghvand A, Zadeh HT. Multivariate statistical analysis of surface water quality based on correlations and variations in the data set. Desalination, 2010, 260: 129-136.

[25] Noori R, Karbassi AR, Moghaddamnia A, Han D, Zokaei-Ashtiani MH, Farokhnia A, Gousheh MG. Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction. J Hydrol, 2011, 401: 177-189.

[26] Noori R, Karbassi AR, Khakpour A, Shahbazbegian M, Badam HMK, Vesali-Naseh M. Chemometric analysis of surface water quality data: case study of the gorganrud river basin, Iran. Environ Model Assess, 2012, 17: 411-420.

[27] Noori R, Deng Z, Kiaghadi A, Kachoosangi F. How reliable are ANN, ANFIS, and SVM techniques for predicting longitudinal dispersion coefficient in natural rivers?. J Hydraul Eng, 2015, 142: 04015039.

[28] Ouyang Y. Evaluation of river water quality monitoring stations by principal component analysis. Water Res, 2005, 39: 2621-2635.

[29] Patra S, Bruzzon L. A novel SOM-SVM-based active learning technique for remote sensing image classification. IEEE Trans Geosci Remote Sens, 2014, 52: 6899-6910.

[30] Pouteau R, Collin A. Spatial location and ecological content of support vectors in an SVM classification of tropical vegetation. Remote Sens Lett, 2013, 4: 686-695.

[31] Rakotomamonjy A. Analysis of SVM regression bounds for variable ranking. Neurocomputing, 2007, 70: 1489-1501.

[32] Rodi W. Grid-search event location with non-Gaussian error models. Phys Earth Planet Inter, 2006, 158: 55-66.

[33] Roy K, Bhattacharya P. Improvement of iris recognition performance using region-based active contours, genetic algorithms and SVMs. Int J Pattern Recognit Artif Intell, 2010, 24: 1209-1236.

[34] Salvador CM, Chou CCK. Analysis of semi-volatile materials (SVM) in fine particulate matter. Atmos Environ, 2014, 95: 288-295.

[35] Skuratov NV. Intelligent wood drying control: problems and decisions. Drying Technol, 2008, 26: 585-589.

[36] Subasi A. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput Biol Med, 2013, 43: 576-586.

[37] Tarjoman M, Fatemizadeh E, Badie K. An implementation of a CBIR system based on SVM learning scheme. J Med Eng Technol, 2013, 37: 43-47.

[38] Theodoros E, Tomaso P, Massimiliano P. Regularization and statistical learning theory for data analysis. Comput Stat Data Anal, 2002, 38: 421-432.

[39] Vapnik VN. Statistical learning theory, 1998 2 New York: Wiley.

[40] Wang L. Support vector machines: theory and applications, 2005, Berlin: Springer 1 48

[41] Zhang DY, Liu YQ, Jun C. Application of single neuron adaptive PID controller during the process of timber drying. J For Res, 2003, 14: 244-248.

[42] Zhang DY, Sun LP, Cao J. Modeling of temperature-humidity for wood drying based on time-delay neural network. J For Res, 2006, 17: 141-144.