基于局部离群因子的模糊支持向量机算法  

Fuzzy support vector machine algorithm based on local outliers factor

作　　者：张庆宝 鞠哲 张万里 ZHANG Qingbao;JU Zhe;ZHANG Wanli(College of Science,Shenyang Aerospace University,Shenyang 110136,China)

机构地区：[1]沈阳航空航天大学理学院,沈阳110136

出　　处：《沈阳航空航天大学学报》2024年第6期90-96,共7页Journal of Shenyang Aerospace University

基　　金：国家重点研发计划子项(项目编号:2019YFC1903901-01)。

摘　　要：模糊支持向量机是一种结合了支持向量机和模糊理论的分类算法。现有的模糊支持向量机算法可以在一定程度上克服噪声数据的影响,但存在成本敏感性,导致对数据的先验分布估计不准确。提出一种新的模糊支持向量机算法,该算法在设计样本的模糊隶属度函数时,利用采样点及其邻域密度的相似性构建的离群因子来更好地获取数据的分布信息。利用UCI数据集对优化后的模型进行验证,证明了其良好的性能。Fuzzy support vector machine is a classification algorithm that combines support vector machine and fuzzy theory.The existing fuzzy support vector machine algorithms can overcome the impact of noise data to some extent,but they have cost sensitivity,leading to inaccurate estimation of the prior distribution of data.A new fuzzy support vector machine algorithm was proposed.When designing the fuzzy membership function of samples,this algorithm better captures the distribution information of data by using the outlier factor constructed by the similarity of sampling points and their neighborhood density.The optimized model is validated using UCI datasets,which proves its good performance.

关 键 词：模糊支持向量机 邻域密度 离群因子 隶属度函数 不平衡数据 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]