摘要
针对数据中存在冗余的问题,结合肯德尔等级系数、欧式距离和粒子群优化算法提出了MRMCPSO算法.在轴承数据集上的实验结果表明,MRMCPSO算法在分类准确率达到90%以上时,与其他4个算法相比较,筛选出来的列数低于1.22‰.
Aiming at the problem of redundancy in the data,the MRMCPSO algorithm was proposed by combining Kendall s rank coefficient,Euclidean distance and particle swarm optimization algorithm.The experimental results on the bearing dataset showed that when the classification accuracy of MRMCPSO algorithm reached more than 90%,compared with the other four algorithms,the number of filtered columns was less than 1.22‰.
作者
郑月锋
李文倩
ZHENG Yue-feng;LI Wen-qian(College of Mathematics and Computer,Jilin Normal University,Siping 136000,China)
出处
《吉林师范大学学报（自然科学版）》
2022年第4期129-134,共6页
Journal of Jilin Normal University:Natural Science Edition
基金
吉林省教育科学技术研究项目(JJKH20210456KJ)。
