The general problem of an off-line parameter tuning in the Binary Genetic Algorithm (BGA) is introduced. An example of such a tuning: a class of Correlational Tuning Methods (CTMs) is proposed. The main idea of a CTM is that it uses a mapping called measurement function as an assessment of the BGA's effciency. An example of a measurement function is described and two examples of CTMs: a modified "trials and errors" method and a modified genetic meta-algoritlm (metaBGA) are shown. Finally, experimental results with the metaBGA for four kinds of test fitness functions, where the code permutation is the tuned parameter, are presented.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this paper the attention is focused on the processing of digital images, in particular on the segmentation of medical images. A new 3D fuzzy segmentation technique is presented to outline the adventages of a relatively simple software tool that may help the user to find contours of the objects of interest in images. The proposed technique is based on a seed growing approach, which takes into account both contextual and topological information in the image. The uncertainty of the image is considered through the use of fuzzy measures, well suited to represent the characteristics of a medical image. The result is a set of possible contours for the volume of interest at different certainty values. They mey be viewed as alternative comtours of the same object. If the method is used interactively, the user has the possibility to scroll very quickly through the different contours to select the most appropriate one for a specific application, according to his own knowledge.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.