Bacterial foraging optimization oriented by atomized feature cloud model strategy

Bacterial foraging optimization (BFO) algorithm, the newest social foraging behavior of Escherichia coli inspired optimization algorithm, is computationally expensive due to the slow nature of the collective intelligence of bacterial swarm. This paper presents a novel bacterial foraging oriented by atomized feature cloud model strategy(BFOAFC) with two main novel steps to accelerate BFO. The first is an atomized feature cloud model based generation jumping to generate a candidate swarm, and second is a novel updated formula to update the tumble movements in chemotaxis steps of virtual bacterial. A comprehensive set of complex benchmark functions including a wide range of dimensions is employed for experimental verification. Experimental results confirm that the BFOAFC outperforms the original BFO and BFO oriented by particle swarm optimization in terms of convergence speed and solution accuracy.