摘要
针对标准人工蜂群算法用于支持向量机参数寻优容易陷入局部最优解,精度不高,收敛速度慢等问题,提出一种改进的人工蜂群算法。该算法在雇佣蜂与跟随蜂更新蜜源时,采用基于当前最优解的局部搜索策略,以提高蜜蜂的局部搜索能力,加快收敛速度并获得更高的精度;引入混沌序列使产生的蜜源分布更均匀,防止陷入局部最优。仿真结果表明,改进的人工蜂群算法在搜索速度和精度上均优于同类算法。将改进的人工蜂群算法应用于基于支持向量机的网络行为分类,实验结果表明,网络行为分类速度及识别准确率均得到了一定的提高。
This paper proposes an improved artificial bee colony( ABC) algorithm. The improved algorithm is aimed to overcome the shortcomings of the standard ABC algorithm being easy to fall into local optimal solutions,to obtain low precision and to slow convergence. It is used for the parameter optimization of the support vector machines( SVM).When the employed bees or onlooker bees update the food sources,the improved ABC algorithm uses the local search strategy based on the current optimal solution to improve the local search capability of bees,and to accelerate the convergence and to get higher precision. Introducing the chaotic sequence makes the sources distributed more evenly and avoids falling into local optimal solutions. Compared with similar algorithms,the simulation results show that the improved ABC algorithm does a better job in search speed and precision. With the improved algorithm applied to the classification of network behavior by SVM,it obtains faster calculation speed and higher classification accuracy.
出处
《江南大学学报(自然科学版)》
CAS
2015年第5期505-511,共7页
Joural of Jiangnan University (Natural Science Edition)
基金
国家自然科学基金项目(61103223)
江苏省自然科学基金项目(BK2011003)
关键词
人工蜂群算法
当前最优解
混沌序列
支持向量机
网络行为分类
artificial bee colony
current optimal solution
chaotic sequence
support vector machines
network behavior classification