摘要
针对多分类问题中样本类间不均衡引起的电缆状态分类准确性不高的问题,提出一种基于贝叶斯优化极端梯度提升树的电缆状态分类方法。首先,利用贝叶斯优化对极端梯度提升树算法里面的超参数进行训练,获取最优超参数配置。其次,将最优超参数配置应用于极端梯度提升树算法中,得到Bo-XGBoost分类模型。最后,通过实例验证该分类方法相较于SVM、TabNet、LightGBM等方法有更高的准确性,可为电缆状态分类提供一种新方向。
Addressing the issue of low accuracy in cable condition classification due to imbalanced sam-ple classes in multiclass classification problems,a cable condition classification method based on Bayes-ian-optimized extreme gradient boosting was proposed.Firstly,Bayesian optimization was employed to train the hyperparameters within the XGBoost algorithm,with the aim of acquiring the optimal hyperpa-rameter configuration.Then,this optimal hyperparameter configuration was applied to the XGBoost algo-rithm,which resulted in the Bo-XGBoost classification model.Finally,the verification through case stud-ies demonstrated that this classification method achieved higher accuracy compared to methods such as SVM,TabNet,and LightGBM,thereby providing a new direction for cable condition classification.
作者
佘维
王欣
陈斌
吕钟毓
张海丽
田钊
SHE Wei;WANG Xin;CHEN Bin;LYU Zhongyu;ZHANG Haili;TIAN Zhao(School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China;Songshan Laboratory,Zhengzhou 450046,China;Zhengzhou Key Laboratory of Blockchain and Data Intelligence,Zhengzhou 450002,China;XJ Electric Co.Ltd.,Xuchang 461099,China)
出处
《郑州大学学报(理学版)》
北大核心
2025年第6期1-7,共7页
Journal of Zhengzhou University:Natural Science Edition
基金
嵩山实验室预研项目(YYYY022022003)
河南省重点研发与推广专项(科技攻关)(212102310039)。
关键词
贝叶斯优化
极端梯度提升树
电缆状态分类
超参数优化
Bayesian optimization
extreme gradient boosting tree
cable condition classification
hyperparameter optimization
作者简介
第一作者:佘维(1977-),男,教授,主要从事复杂系统建模与仿真、机器学习、区块链与数据智能研究,E-mail:wshe@zzu.edu.cn;通信作者:田钊(1985-),男,副教授,主要从事群体智能、机器学习、区块链与数据智能研究,E-mail:tianzhao@zzu.edu.cn。
