欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对人工萤火虫群优化（GSO）固定步长带来的收敛速度不快且容易陷入局部寻优的问题，对步长因子进行改进，提出一种基于S型变步长的萤火虫算法（S—VS—GSO），步长随着迭代次数的增加而改变，并利用改进后算法对支持向量参数C和g进行优化，并利用优化后的算法对空中机动目标进行分群聚类。仿真结果表明，改进后的算法相比较标准算法，收敛速度和全局寻优能力都有所改善，算法耗时相对于标准算法也有所减少，在战场目标分群应用中准确率也高于传统算法。
英文摘要：
Considering constant step of glowworm swarm optimization （GSO） of slower convergenee rate and easy to fall into local optimization, a new GSO algo variable step size is proposedto improve the fixed step size. Step size varies with leading to the problem rithm based on S style the increase of iterations, and then the improved algorithm is applied to optimize the support vector machine parameters C＆g, and the improved algorithm is applied to cluster the aerial maneuvering target. The simulation shows that the convergence rate as well as global optimization capability of the proposed algorithm is better than the standard one. In addition, the time it consumes is obviously less than that of the standard algorithm, and the accuracy for aerial maneuvering target of the improved algorithm is higher than that of conventional algorithm.
同期刊论文项目
同项目期刊论文
期刊信息
位置：