基于疯狂捕猎秃鹰算法的K均值互补迭代聚类优化

K-means complementary iterative clustering optimization based on crazy-hunting bald eagle search algorithm

在处理庞大复杂的点云数据时,传统聚类方法精度低、耗时长并且受离群点影响大,针对以上问题,提出基于疯狂捕猎的柯西反向秃鹰搜索算法(QO-BESCH)的K均值互补迭代聚类优化方法.所提算法构建基于体元包围盒的初始聚类中心选择模型,提升初始化聚类中心质量;提出疯狂捕猎机制,同时融合动态自适应控制算子和柯西反向策略,提升秃鹰搜索算法(BES)的寻优能力,增加寻找聚类中心的成功率;利用QO-BESCH优化K均值聚类(KMC),在减小迭代次数的同时增加搜索效率,得到较好的聚类结果.利用UCI标准数据集对所提算法进行测试,并与8种聚类算法进行对比,实验结果证明了所提算法的优越性.将本研究算法结合PCL点云库应用于ModelNet40点云数据集聚类,结果表明,所提算法可以实现有效聚类,适用性较强.

A K-means complementary iterative clustering method optimized by quasi-oppositional bald eagle search base on crazy-hunting(QO-BESCH)was proposed,in order to solve the problems of low precision,long time and large influence of outliers in the process of processing large and complex point cloud data by traditional clustering methods.Firstly,the initial clustering center selection model based on volume cell bounding box was constructed to improve the quality of initial clustering center.Secondly,a crazy hunting mechanism was proposed,which combined dynamic adaptive control operators and quasi-oppositional strategy,significantly improved the searching ability of bald eagle search(BES)algorithm,and increased the success rate of searching clustering center.Finally,the Kmeans clustering(KMC)was optimized by using QO-BESCH to reduce the number of iterations and increase the search efficiency,and better clustering results were obtained.The proposed algorithm was tested by using UCI standard data set and compared with eight clustering algorithms.The experimental results show the effectiveness and superiority of the proposed algorithm.Further,the proposed algorithm was applied in combination with PCL point cloud library to cluster ModelNet40 point cloud dataset.Results show that the proposed algorithm can realize effective clustering and has strong applicability.