迁徙差分进化算法集成及其在RNA二级结构预测中的应用  

Migration differential evolution ensemble and its application in predicting RNA secondary structure

作　　者：胡桂武[1] 胡劲松[2] 

机构地区：[1]广东商学院数学与计算科学系,广州510320 [2]华南理工大学计算机科学与工程学院,广州510640

出　　处：《计算机应用》2008年第4期931-934,941,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60574078);广东省自然科学基金资助项目(06301003)

摘　　要：对优化问题和游牧民族迁徙行为的比较研究表明,两者存在相似之处。模拟游牧民族迁徙机制提出了一种迁徙策略,并且与差分进化算法相结合,提高了算法摆脱局部极值的能力;通过集成技术,充分发挥各种差分进化算法的优点,实现协同进化,提高了算法的全局搜索能力。最后应用于预测RNA二级结构,实验表明,该算法是有效的。A comparative study of optimization and nomadic migration shows that there are similarities between the two processes. Migration strategy was proposed by the simulation of nomadic migration, and the capability of overcoming local extremum was improved. At the same time, the algorithm with ensemble technique sufficiently exerted the advantages of different differential evolution and carried out harmonious evolution, and the global search capability of the algorithm was enhanced. Finally, the new algorithm has been used to predict RNA secondary structure; the experiments show that the algorithm is effective.

关 键 词：迁徙策略 核醣核酸 差分进化算法 协同进化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]