Predicting the strength of Populus spp. clones using artificial neural networks and ε-regression support vector machines (ε-rSVM)
-
Shawn D. Mansfield
Abstract
Wood properties, including bending stiffness and strength, basic density and microfibril angle were experimentally obtained for six aspen and six hybrid poplar clones grown in Western Canada. Data analysis attempted to establish a relationship between wood mechanical properties and intrinsic wood attributes by means of artificial neural networks (ANN) and ε-regression support vector machines (ε-rSVM) employing a 5-fold cross validation approach (5-fold CV). Initial results for strength were acceptable, but require further improvement. Estimations of stiffness results (MOE) were inferior to those of strength (MOR) due to the fact that in several regression cases, the developed model worked well for narrow windows of data, but failed on a large scale due to the high variations in the values of the input data vectors. In such cases, the result is probably the development of regression with uneven performance throughout the input data set, and therefore the modeling capacity is poor. To avoid this predicament, different neural networks with one output neuron were developed in order to estimate either the stiffness or the strength, and at the same time the approximation capabilities of ε-rSVM were employed. In both methods, 5-fold CV was carried out in order to attain a more generalized solution by eliminating the boundary effect phenomena and by avoiding local behavior of the global support vector regression. The resultant models were evaluated by common metrics. The best ANN for the estimation of strength in combination with 5-fold CV, was a modular back propagation with average R2=0.70, and mean root mean square error (MRMSE) equal to 0.19 and mean average percent error (MAPE) equal to 12.5%. The Gaussian kernel 5-fold CV ε-rSVM estimated MOR with similar accuracy. The best 5-fold CV ANN for MOE estimation was a feed forward back propagation one, with average R2=0.60, MRMSE equal to 0.23 and MAPE equal to 41.5%, which was better than all other kernel methods employed.
©2011 by Walter de Gruyter Berlin Boston
Articles in the same Issue
- Original Papers
- Fundamental understanding of pulp property development under different thermomechanical pulp refining conditions as observed by a new Simons’ staining method and SEM observation of the ultrastructure of fibre surfaces
- Enhancing dewatering of thermo-mechanical pulp (TMP) based papermaking through enzymatic treatment
- Mechanisms of TMP peroxide bleaching using Mg-based alkalis
- Properties of wood chips for thermomechanical pulp (TMP) production as a function of spout angle
- Determination of local material properties of OSB sample by coupling advanced imaging techniques and morphology-based FEM simulation
- Combined bound water and water vapour diffusion of Norway spruce and European beech in and between the principal anatomical directions
- Oxygen plasma-treated enzymatic hydrolysis lignin as a natural binder for manufacturing biocomposites
- Influence of the adhesive formulation on the mechanical properties and bonding performance of polyurethane prepolymers
- Characterizing perpendicular-to-grain compression (C⊥) behavior in wood construction
- Predicting the strength of Populus spp. clones using artificial neural networks and ε-regression support vector machines (ε-rSVM)
- X-ray scattering and microtomography study on the structural changes of never-dried silver birch, European aspen and hybrid aspen during drying
- Equilibrium moisture content (EMC) in Norway spruce during the first and second desorptions
- Fungal degradation of bamboo samples
- qPCR as a tool to study basidiomycete colonization in wooden field stakes
- Meetings
- Meetings
Articles in the same Issue
- Original Papers
- Fundamental understanding of pulp property development under different thermomechanical pulp refining conditions as observed by a new Simons’ staining method and SEM observation of the ultrastructure of fibre surfaces
- Enhancing dewatering of thermo-mechanical pulp (TMP) based papermaking through enzymatic treatment
- Mechanisms of TMP peroxide bleaching using Mg-based alkalis
- Properties of wood chips for thermomechanical pulp (TMP) production as a function of spout angle
- Determination of local material properties of OSB sample by coupling advanced imaging techniques and morphology-based FEM simulation
- Combined bound water and water vapour diffusion of Norway spruce and European beech in and between the principal anatomical directions
- Oxygen plasma-treated enzymatic hydrolysis lignin as a natural binder for manufacturing biocomposites
- Influence of the adhesive formulation on the mechanical properties and bonding performance of polyurethane prepolymers
- Characterizing perpendicular-to-grain compression (C⊥) behavior in wood construction
- Predicting the strength of Populus spp. clones using artificial neural networks and ε-regression support vector machines (ε-rSVM)
- X-ray scattering and microtomography study on the structural changes of never-dried silver birch, European aspen and hybrid aspen during drying
- Equilibrium moisture content (EMC) in Norway spruce during the first and second desorptions
- Fungal degradation of bamboo samples
- qPCR as a tool to study basidiomycete colonization in wooden field stakes
- Meetings
- Meetings
