基于GP病虫害预测预报中适应性函数的研究  

Study of fitness function in pest forecasting based on genetic programming

作　　者：任春风[1,2] 李淼[1] 

机构地区：[1]中国科学院合肥智能机械研究所 [2]中国科学技术大学信息科学技术学院,合肥230027

出　　处：《计算机工程与应用》2007年第6期197-198,243,共3页Computer Engineering and Applications

基　　金：国家高技术研究发展计划(863) (the National High- Tech Research and Development Plan of China under Grant No.2001AA115180) 。

摘　　要：适应性函数是遗传算法和遗传程序设计得以实现的关键因素,是评价个体好坏的定量表述,决定着演化过程中群体选择复制及群体整体性的质量。在GP程序过程中在常见适应性函数的基础上加以优化和调整,最后通过实例验证了优化调整后的适应性函数在病虫害预测预报中的准确度有了一定的提高。Fitness is the driving force of darwinian natural selection and of both conventional genetic algorithms and genetic programming,based on which to evaluate individuals of current population and to reproduce the next generation from the current generation.In modeling of genetic programming,based on traditional fitness function,fitness function is improved and adjusted by means of ways for this design.In the end,through the experiment,it is found that improved fitness function improves the performance of accuracy in pest forecasting.

关 键 词：遗传程序设计 适应性函数 规模爆炸 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]