基于模拟退火的模糊分类系统在数据挖掘中的应用

给出了一种基于模拟退火的模糊分类系统—SAFCS,该分类系统结合了SA元启发式搜索策略的学习能力和模糊系统的近似推理方法,旨在改善与分类问题有关的大型数据空间的搜索性能,找到模糊if-then规则的优化集.SAFCS可以从输入数据集中抽取精确的模糊分类规则,并在若干不同预定义类中将其应用于对新数据实例的分类.文末用某数据集检测了SAFCS的性能,结果表明,在与其他几个著名算法比较时该分类系统性能可靠.

Application Research of Fuzzy Classification System Based on Simulated Annealing

A Simulated annealing based fuzzy classification system (SAFCS) is presented in the paper,which hybridizes the learning capability of SA metaheuristic with the approximate reasoning method of fuzzy systems. The objective of SAFCS is to effectively explore the large search space usually associated with classification problems,and find the optimum set of fuzzy if-then rules. The SAFCS would be able to extract accurate fuzzy classification rules from input data sets,and applies them to classify new data instances in different predefined groups or classes. Experiments are performed with some data sets. The results indicate that the proposed SAFCS achieves competitive results in comparison with several well-known classification algorithms.