摘要
为解决渣土车车载设备数据含有噪点无法准确判别电子联单的问题,建立一种基于逻辑回归的电子联单判别模型。综合考虑车辆申报状态、停留时长等25项影响因素,建立基于Sigmod函数的逻辑回归模型。采用交叉熵作为模型损失函数,利用梯度下降法对模型系数进行标定,全面提升模型判别准确率。应用深圳市建筑废弃物管理平台历史数据,对基于逻辑回归的电子联单判别模型的准确率进行验证。结果表明:基于逻辑回归模型的电子联单判别策略,采用按工地独立划分分阈时,电子联单准确率达到82.34%,相比传统电子联单判别方案提升29.1%,模型判别效果良好,可为电子联单制度在建筑废弃物全过程精准管控提供决策支持。
In order to solve the problem that the data of the on-board equipment of the muck truck contains noise and it is difficult to accurately identify the electronic joint list,this paper establishes a discrimination model based on logical regression.In this paper,considering 25 factors,using SIGMOD function establishes different electronic bill.Using the historical data of Shenzhen construction waste management system,the accuracy of the model was verified.The results show that the accuracy rate of e-bill reaches 82.34%when the threshold is divided according to the construction site,which is 29.1%higher than that of the traditional method.The model proposed in this paper can provide decision support for the efficient supervision and control of the whole process of construction waste.
作者
张晓峰
田英杰
金典琦
毕军
王付军
ZHANG Xiaofeng;TIAN Yingjie;JIN Dianqi;BI Jun;WANG Fujun(Sechool of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China;Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport,Beijing Jiaotong University,Beijing 100044,China;Shenzhen Urban Public Safety and Technology Institute,Shenzhen 518000,China)
出处
《重庆理工大学学报（自然科学）》
CAS
北大核心
2021年第6期202-208,共7页
Journal of Chongqing University of Technology：Natural Science
基金
国家重点研发计划课题(2018YFC0706005)。
关键词
建筑废弃物
全过程管控
电子联单
逻辑回归模型
construction waste
the whole process management
electronic bill
logical regression
