Avtor/Urednik		Cigale, Boris; Divjak, Matjaž; Zazula, Damjan
Naslov		Application of simulated annealing to biosignal classification and segmentation
Tip		članek
Vir		In: Kokol P, Stiglic B, Zorman M, et al, editors. Proceedings of the 15th IEEE symposium on computer-based medical systems (CBMS 2002); 2002 Jun 4-7; Maribor. Los Alamitos: Institute of electrical and electronics engineers,
Leto izdaje		2002
Obseg		str. 165-70
Jezik		eng
Abstrakt		Simulated annealing is no doubt one of the most popular optimisation methods. Like similar methods (i.e. genetic algorithms) it is based on the natural phenomena. In this paper two examples of how to use this method in the medical applications are presented. In the first example the successfulness of the simulated annealing is compared to the genetic algorithm on the problem of the optimal coefficients determination for cellular neural networks, when used for segmentation of ovarian ultrasound images. In this field the later method produced better results. The second example discusses the usage of simulated annealing for optimisation of signal classification.
Deskriptorji		PATTERN RECOGNITION ULTRASONOGRAPHY NEURAL NETWORKS (COMPUTER)