Please choose your delivery country and your customer group
The paper presents the results obtained to demonstrate the strengths of the Bees Algorithm as an optimisation tool. Many complex multi-variable optimisation problems cannot be solved easily. This has generated interest in 'intelligent' search algorithms that find nearoptimal solutions in reasonable running times. The Bees Algorithm developed in the authors' laboratory is inspired by the food foraging behaviour of honey bees and could be regarded as belonging to the category of 'intelligent' optimisation tools. This paper presents an application of the Bees Algorithm to the problem of identifying defects in plywood veneer. Veneer sheets can contain defects, which could create quality problems when the sheets are bonded together. Researchers have developed systems for automatically detecting and identifying defects in plywood veneer. At the heart of such systems there is usually a classifier module that receives features of artefacts detected in wood veneer images and classifies those artefacts accordingly. Different types of classifiers have been constructed. In this work, the Support Vector Machine (SVM), well known for its high classification accuracies, was adopted. The Bees Algorithm was employed both to optimise the parameters of the SVM and to select the features to be provided to the classifier.