Varying the population size of artificial foraging swarms on time varying landscapes
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
IEEE Computational Intelligence Magazine
Hi-index | 0.00 |
Target volume delineation in image stacks resulting from low contrast positron emission tomography (PET) remains a hot topic in the field of medical image processing. We propose an algorithm based on artificial ants moving in three dimensional image space controlled by transition rules which are able to self-reproduce. This investigation shows by variation of the transition rules that the impact on segmentation results is small because self-reproduction is the overwhelming effect in the simulation.