Hybrid e-regression and validation soft computing techniques: The case of wood dielectric loss factor

Authors:
Lazaros Iliadis;Stavros Tachos;Stavros Avramidis;Shawn Mansfield
Affiliations:
Democritus University of Thrace, Department of Forestry & Management of the Environment & Natural Resources, 193 Pandazidou st., N Orestiada 68200, Greece;University of Edinburgh, UK;University of British Columbia, Department of Wood Science, Vancouver, BC, Canada;University of British Columbia, Department of Wood Science, Vancouver, BC, Canada
Venue:
Neurocomputing
Year:
2013

Citing 3
Cited 0

An Overview of Hybrid Soft Computing Techniques for Classifier Design and Feature Selection

HIS '08 Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems
Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fuzzy Weighted Support Vector Regression With a Fuzzy Partition

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.01

Visualization

Abstract

This research effort has two orientations. First it aims in the application of hybrid soft computing techniques for the estimation of wood loss factor which is considered a very important feature for wood industry. This has been performed by employing fuzzy weighted Support Vector Machines (SVM), Global SVM and Artificial Neural Networks. The second part of this research focuses in the evaluation of the produced models by employing an innovative fuzzy logic method developed by our research team [10]. For this purpose, experimental data for two different wood species were used. The estimation of the dielectric properties of wood was done by using soft computing algorithms as a function of both ambient electro-thermal conditions applied during drying of wood and basic wood chemistry. The best fit neural models that were developed previously were compared to the current approaches in order to determine the optimal ones.