基于Levy飞行策略的改进樽海鞘群算法  

Improved Salp Swarm Algorithm Based on Levy Flight Strategy

作　　者：张严 秦亮曦[1] ZHANG Yan;QIN Liang-xi(School of Computer,Electronics and Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《计算机科学》2020年第7期154-160,共7页Computer Science

基　　金：广西科技计划(桂科AB16380260);公益性行业(气象)科研专项(GYHY201406027)。

摘　　要：针对樽海鞘群算法(Salp Swarm Algorithm,SSA)在寻优过程中存在的收敛速度较慢、容易陷入局部最优的缺点,提出了一种改进的采用莱维飞行策略的条件化更新的樽海鞘群算法(Levy Flight-based Conditional Updating Salp Swarm Algorithm,LECUSSA),并将其运用于分类算法的特征子集选择过程。首先,利用莱维飞行策略的长短跳跃特点对领导者位置进行随机更新,以增强全局最优的搜索能力;其次,增加对追随者位置的更新条件,让追随者不再盲目地跟随,从而加快收敛速度。在23个优化基准函数上对LECUSSA算法与其他算法进行了性能比较实验;并把算法运用到支持向量机(Support Vector Machine,SVM)算法的分类特征子集选择中,采用8个UCI数据集对特征选择后的分类结果进行了性能比较实验。实验结果表明,LECUSSA具有良好的全局最优搜索能力和较快的收敛速度,利用LECUSSA算法进行特征选择后,能够找到最佳分类准确率的特征子集。Aiming at the shortcomings of slow convergence speed and easy to fall into local optimum in the optimization process of the Salp swarm algorithm(SSA),a Levy Flight-based Conditional Updating Salp Swarm Algorithm(abbreviated as LECUSSA)is proposed and it is used in the feature subset selection of classification algorithm.Firstly,the leader position is updated randomly by using the long and short jump characteristics of Levy Flight strategy,which enhances the global optimal search ability.Secondly,the conditional updating condition to the follower’s position is added to make the follower no longer follow blindly,thus accelerating the convergence speed.The performance of LECUSSA algorithm is compared with other algorithms on 23 benchmark functions.The algorithm is applied to the selection of classification feature subset of SVM algorithm,and 8 UCI datasets are used to compare the performance of the classification results after feature selection.The experimental results show that LECUSSA has good global optimal search ability and fast convergence speed.After feature selection using LECUSSA algorithm,the feature subset with the best classification accuracy can be found.

关 键 词：樽海鞘群算法 莱维飞行 条件化更新 特征选择 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]