Providing a Bird Swarm Algorithm based on Classical Conditioning Learning Behavior and Comparing this Algorithm with sinDE, JOA, NPSO and D-PSO-C Based on Using in Nanoscience

There can be no doubt that nanotechnology will play a major role in our future technology. Computer science offers more opportunities for quantum and nanotechnology systems. Soft Computing techniques such as swarm intelligence, can enable systems with desirable emergent properties. Optimization is an important and decisive activity in structural designing. The inexpensive requirement in memory and computation suits well with nanosized autonomous agents whose capabilities may be limited by their size. To apply in nanorobot control, a modification of PSO algorithm is required. Using birds’ classical conditioning learning behavior in this paper, particles will learn to perform a natural conditional behavior towards an unconditioned stimulus. Particles in the problem space are divided into multiple categories and if any particle finds the diversity of its category in a low level, it will try to move towards its best personal experience. We also used the idea of birds’ sensitivity to the space in which they fly and tried to move the particles more quickly in improper spaces so that they would depart the spaces. On the contrary, we reduced the particles’ speed in valuable spaces in order to do more search. The proposed method was implemented in MATLAB software and compared to similar results. It was shown that the proposed method finds a good solution to the problem regardless of nondeterministic functions or stochastic conditions.