一种新的混合智能算法及其在属性约简中的应用

A New Hybrid Intelligent Algorithm and Its Application on Attribute Reduction

属性约简是粗糙集理论的核心部分.受细菌觅食过程的启发,本文将细菌觅食算法的思想应用于粒子群算法,提出了一种细菌觅食粒子群算法.细菌觅食过程的趋向操作可以指导粒子朝着更优方向进化,而粒子群算法又能提高细菌觅食算法的收敛速度和寻优能力.将该算法应用到属性约简中,数值实验结果表明,本文提出的细菌觅食粒子群优化的约简算法在寻优能力方面均优于Hu算法、粒子群约简算法和细菌觅食约简算法,能得到更好的最小属性约简.

Attribute reduction is the core of the rough set theory.Enlightened by bacterial foraging processing,this paper applies the idea of bacterial foraging algorithm and proposes particle swarm optimization with bacterial foraging algorithm （BF-PSO）.In this algorithm,the chemotaxis of bacterial foraging can guide the particles to evolve towards much better direction,in turn,the convergence speed and optimization capabilities are increasing by using PSO.The proposed algorithm is applied to the attribute reduction.Experiments show that attribute reduction based on BF-PSO algorithm achieve much better result in optimization capabilities by comparing with other algorithms,such as Hu algorithm,particle swarm optimization,bacterial foraging optimization and bacterial foraging particle swarm optimization,and experiments also show that the algorithm can find the better minimal attribute reduction.