MCSA-CNN Algorithm for Image Noise Cancellation
Many optimization algorithms have been developed and adapted for several problems by intelligence computing. A new computational intelligence called the artificial immune system (AIS), which was inspired by the biological immune system, has attracted more and more interest in the last few years [1, 2, 4].
In this chapter, we propose a modified clonal selection algorithm (MCSA), with an adaptive maturation strategy and novel clone framework to search approximate optimal solutions. We propose the pyramid framework with self-adaption mutation probability in clones, and perform different mutation operators of Gaussian mutation, swapping mutation, and multipoint mutation in the respective levels of the pyramid; next, a response mechanism is applied to avoid local search for optimization. Employing the above improvements, the MCSA enables a better capability for optimization.
The organization of this chapter is summarized as follows. In Sect. 15.2, the clonal selection algorithm is proposed, and the modified maturation strategy is applied in MCSA in Sect. 15.3. Another important role is described in Sect. 15.4. In Sect. 15.5, a hybrid MCSA and CNN for image noise cancellation are submitted. Finally, the simulation results and conclusions are drawn in Sects. 15.6 and 15.7, respectively.
KeywordsMutation Operator Cellular Neural Network Clonal Selection Algorithm Approximate Optimal Solution Gaussian Mutation
Unable to display preview. Download preview PDF.
- 2.Fukuda, T., Mori, K., and Tsukiama, M. “Parallel search for multi-modal function optimization with diversity and learning of immune algorithm.” In (Ed.) D. Dasgupta, Artificial Immune Systems and Their Applications, Springer-Verlag, pp. 210–220, 1999.Google Scholar
- 3.de Castro, L.N. and Von Zuben, F.J. “Artificial Immune System: Part I—Basic Theory and Application.” TR-DCA 01/99, 1999.Google Scholar
- 4.de Castro, L.N. and Von Zuben, F.J. “Artificial Immune System: Part II—A Survey of Application.” DCA-RT 02/00, 2000.Google Scholar
- 10.Lopez, P., Vilarino, D.L. and Cabello, D. “Design of multilayer discrete time cellular neural networks for image processing tasks based on genetic algorithms.” IEEE International Symposium on Circuits and Systems, pp. 133–136, 2000.Google Scholar
- 11.Zeng, B. “Optimal median-type filtering under structural constraints,” IEEE Transactions on Image Processing, pp. 921–931, July 1999.Google Scholar