Application of kernel-genetic algorithm as nonlinear feature selection in tropical wood species recognition system

Classifying tropical wood species pose a considerable economic challenge and failure to classify the wood species accurately can have significant effects on timber industries. Previous works on tropical wood species recognition systems considered methods for classification of linear features of the wood species. However, tropical wood species are known to exhibit nonlinear features due to several factors such as age of the tree, samples taken from different parts of the tree, etc. to address the nonlinear features of the tropical wood species, a Kernel-Genetic Algorithm (K-GA) technique for feature selection is proposed. This method combines the Kernel Discriminant Analysis (KDA) technique with Genetic Algorithm (GA) to generate nonlinear wood features and at the same time reduce dimension of the wood database. The proposed system achieved a classification accuracy of 98.69%, showing marked improvement to the work done previously