基于手机信令数据的快递人员辨识方法

发布时间：2018-04-10 13:11

本文选题：城市配送 + 快递人员识别　；参考：《北京工业大学学报》2017年03期

【摘要】：提出一种基于朴素贝叶斯分类法(naive Bayesian classifier,NBC)的城市快递人员辨识方法.首先,通过相关问卷调查,研究快递派送人员的手机信令发生规则.然后,依据北京市移动用户手机通信信令数据,利用问卷调查数据和手机信令数据2种数据源中同时包含的通信数据属性,建立通信数据与调查数据中类别变量(快递人员/非快递人员)之间的贝叶斯概率关系,以此为基础构建NBC模型并对其进行训练.最后,使用未参与训练的样本数据测试标定后模型的准确性,测试结果显示快递人员的预测成功率达到88.3%.结果表明:该方法具有较高的精度,可以满足实际应用需求.
[Abstract]:This paper presents a method for identification of urban couriers based on naive Bayesian classifier (NBCs).First of all, through the relevant questionnaire, research express delivery personnel mobile phone signaling rules.Then, according to the mobile phone communication signaling data of Beijing mobile users, using the questionnaire data and mobile phone signaling data two kinds of data sources simultaneously contained in the communication data attributes,The Bayesian probabilistic relationship between communication data and category variables (couriers / non-couriers) in the survey data is established, and then the NBC model is constructed and trained.Finally, the accuracy of the calibrated model is tested by using the untrained sample data. The test results show that the successful rate of prediction for the couriers is 88.388.The results show that the method has high accuracy and can meet the practical requirements.
【作者单位】：北京工业大学北京市交通工程重点实验室;交通运输部公路科学研究院;
【基金】：北京市自然科学基金资助项目(8131001) 湖北省交通运输厅科技项目(2014721311)
【分类号】：F259.2

【相似文献】