No abstract

This paper introduces a comparison of training algorithms of radial basis function (RBF) neural networks for classification purposes. RBF networks provide effective solutions in many science and engineering fields. They are especially popular in the pattern classification and signal processing areas. Several algorithms have been proposed for training RBF networks. The Artificial Bee Colony (ABC) algorithm is a new, very simple and robust population based optimization algorithm that is inspired by the intelligent behavior of honey bee swarms. The training performance of the ABC algorithm is compared with the Genetic algorithm, Kalman filtering algorithm and gradient descent algorithm. In the experiments, not only well known classification problems from the UCI repository such as the Iris, Wine and Glass datasets have been used, but also an experimental setup is designed and inertial sensor based terrain classification for autonomous ground vehicles was also achieved. Experimental results show that the use of the ABC algorithm results in better learning than those of others.

No abstract

No abstract

3 dimensional (3D) modeling of an object or an environment using point clouds is an important problem in many scientific fields such as photogrammetry, remote sensing, materials processing, reverse engineering, construction industry, virtual reality and medicine etc. Laser scanning is an effective technique that facilitates 3D modeling process with providing large amount of 3D point cloud data in a short time. In this study, design process of point laser sensor and line laser sensor based low cost scanner systems is proposed. Performed 3D data measurements with these two different laser scanners show that; point laser range sensor based scanner, that can capture lesser 3D point for per second, provides more detailed and more sensitive measurements. It can be preferred in applications when the details are very important and are suitable for modeling small objects. However, line laser range sensor based scanner can capture much more 3D point data per second and it is suitable for applications where time critical models with large objects and environment.