人机交互遗传算法的人机界面  

Interface of human-computer interactive genetic algorithm

作　　者：刘峻[1] 滕弘飞[1] 屈福政[1] 

机构地区：[1]大连理工大学机械工程学院,辽宁大连116024

出　　处：《大连理工大学学报》2005年第1期58-63,共6页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(50175009;50275019;50335040);高等学校博士学科点专项科研基金资助项目(20010141005).

摘　　要：为建立更有效的人机界面,研究了人机交互遗传算法(HCIGA)的人机界面技术,给出了最优适应度与平均适应度多代均值随进化代数的变化趋势图、个体与最优个体欧式距离与适应度关系直方图及其应用方法;实现了从宏观和微观层面揭示算法动态过程,解决何时及如何在线添加人工解或控制算子问题,以更好地发挥HCIGA作用;最后在以印刷电路板布局设计为背景的算例中进行了数值验证.结果表明,应用该人机界面的HCIGA计算精度较标准遗传算法(SGA)和HCIGA高,计算效率较SGA低、较HCIGA高.To make human-computer interaction more effective, the human-computer interaction technique for human-computer interactive genetic algorithm (HCIGA) is researched. Two interface tools and their application methods are presented: the convergence diagram of the best and average fitness against generations, and the histogram of individual distribution versus fitness compared with current optimum individual. The tools display the macro- and micro-state of the algorithm on the fly, and figure out when and how to add the artificial individuals into the population or to adjust the operators. Therefore, the merits of both human and computer can be developed effectively. On layout design of printed circuit board (PCB), HCIGA with the proposed interface demonstrates that it is superior to both standard genetic algorithm (SGA) and HCIGA in precision, and it is superior to HCIGA but is inferior to SGA in effectiveness.

关 键 词：人机交互遗传算法 人机交互界面 布局设计 个体分布-适应度直方图 

分 类 号：TP391.75[自动化与计算机技术—计算机应用技术] O242.23[自动化与计算机技术—计算机科学与技术]