摘要
文章在标准粒子群算法基础上,通过引入混沌技术和小生境技术构建了一种改进的粒子群算法——混沌小生境粒子群算法,该算法改善了种群的多样性,提高了算法的全局寻优性能。并将该算法与模糊神经网络相结合构建了混沌小生境粒子群模糊神经网络模型。以我国上市公司为研究对象,运用所提出的模型对公司信用状况进行了评估预测,实证结果证明了该模型的有效性和可靠性。
引文
[1]Shapiro A F.The Merging of Neural Networks,Fuzzy Logic,and Genetic Algorithms[J].Insurance:Mathematics and Economics,2002,(31).
[2]Malhotra R,Malhotra D K.Differentiating Between Good Credits and Bad Credits Using Neuro-fuzzy Systems[J].European Journal of Operational Research,2002,(136).
[3]Karahoca D,Karahoca A,Yavuz O.An Early Warning System Approach for the Identification of Currency Crises With Data Mining Techniques[J].Neural Computation&Application,2013,(23).
[4]Kennedy J,Everhart R C.A Discrete Binary Version of the Particle Swarm Algorithm[A].In:Proceedings 1997 Conference on systems,man and cybernetics[C].Piscataway,NJ:IEEE Service Center,1997.
[5]杨启文,阮姗娜,陈俊风等.群体智能在旅行商问题中的应用综述[J].自动化技术与应用,2016,35(8).
[6]黄文雅.基于改进版粒子群优化算法的最优双层规划模型及其求解[J].统计与决策,2018,(1).
[7]高尚,杨静宇.混沌粒子群优化算法研究[J].模式识别与人工智能,2006,19(2).
[8]Lee C G,Cho D H,Jung H K.Niche Genetic Algorithm With Restricted Competition Selection for Multimodal Function Optimization[J].IEEE Trans on Magnetics,1999,35(3).
[9]唐振鹏,陈尾虹,黄友珀.上市公司信用风险的度量[J].统计与决策,2016,(24).