粒子群遗传混合算法在点状注记配置中的应用  

A Hybrid Algorithm of PSO and GA for Automatic Placement of Point Annotation

作　　者：王立[1] 郑昊[1] 

机构地区：[1]华北计算技术研究所,北京100083

出　　处：《计算机与现代化》2012年第10期30-33,37,共5页Computer and Modernization

摘　　要：通过重新定义粒子位置、速度以及其相应的运算规则,本文将粒子群遗传混合算法应用到点状注记配置中。通过借鉴遗传算法中的变异操作的思想,本文使用变异算子对粒子进行变异操作,提高了粒子群的粒子多样性,避免了局部收敛和粒子搜索能力的下降。最后使用注记密度分别为12%和35%的地图数据对本算法进行测试。测试结果表明,本算法具有良好的稳定性,能够解决点状注记配置问题。By redefining the position,velocity and operation rules of the particle,a hybrid algorithm of PSO（Particle Swarm Optimization Algorithm） and GA（Genetic Algorithm） is designed to solve the problem of label placement for point-features.Inspired by the mutation operation in GA,a mutation operator is used to change the particle position.This operation can increase the diversity of the particle swarm,restrain premature stagnation,and prevents the decline in the search capacity of the particle.At last,this algorithm is tested by several examples.The annotation densities of these examples are 12% and 35%.The result shows that the algorithm has good stability to be able to solve the problem of label placement for point-features.

关 键 词：离散粒子群优化算法 遗传算法 注记自动配置 数字制图 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]