基于免疫遗传算法的粗糙集属性约简算法

属性约简是粗糙集理论中一个重要的研究课题,为了有效获取属性最小相对约简,提出了一种基于免疫遗传算法的粗糙集属性约简算法。该算法将免疫算法和遗传算法结合,并将核引入免疫遗传算法的初始抗体群来提高算法的性能,依照决策属性对条件属性的依赖度,并结合抗体浓度,能维持进化过程中个体的多样性,从而提高了算法的全局搜索能力,避免陷入局部最优。实验证明该算法能够快速得到相对最小约简。

Rough set attribute reduction algorithm based on Immune Genetic Algorithm

Attribution reduction is an important subject for the rough set theory.The paper proposes a rough set attribute reduction algorithm based on the Immune Genetic Algorithm（IGA）.The algorithm which this paper proposes combines the Immune algorithm with Genetic algorithm，and the core is joined to initial population in IGA in order to accelerate capability.According to the dependability of decision attribute to condition attribute，and combining with the consistency，it can keep individual’s variety of the population，sequentially it improves the search ability to the whole of the algorithm，avoids to get into brushfire local optimization.Experimental results show the algorithm is fast and effective.