刘云翔 陈斌 林涛 施伟



摘 要: 为了有效判别行驶车辆内车载乘客手机数量实际匹配的乘客人数,提出一种将聚类算法和呼叫指纹识别算法相组合的算法(CHC?CFA)。运用组合算法结合车辆内乘客携带手机的实时轨迹数据以及历史呼叫指纹数据建立同一用户识别模型,有效地判别出车辆内实际乘客人数,用于判别行驶车辆是否存在超员的异常问题,也可以对当前HOV车道的车辆内乘客数实时监测提供一种新的辅助检测方法。实验结果表明,该模型能有效判别行驶车辆内车载乘客手机数量实际匹配的乘客人数并有较高的检测准确率。
关键词: 同一用户识别; 移动大数据; CHC?CFA; 数据获取; 维度分析; 识别模型
中图分类号: TN919?34 文献标识码: A 文章编号: 1004?373X(2020)06?0070?05
Same user identification analysis model based on mobile big data
LIU Yunxiang1, CHEN Bin1, LIN Tao1, SHI Wei 2
(1. School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201400, China;
2. School of Automobile Engineering, Jiangsu Automobile Technician Institute, Yangzhou 225000, China)
Abstract: A combined algorithm CHC?CFA (condensed hierarchical clustering?call fingerprint algorithm) is proposed, which combines the clustering algorithm and call fingerprint recognition algorithm, so as to effectively identify the number of passengers actually matched with the number of mobile phones of passengers in the running vehicle. The same user identification model is established with the combined algorithm in combination of the real?time trajectory data and the historical call fingerprint data of the mobile phone carried by passengers in the vehicle. It can effectively identify the actual number of passengers inside the vehicle, which can be used to identify whether the running vehicle is overloaded, and also provide a new auxiliary detection method for the real?time monitoring of the number of passengers in the current HOV lane. The experiments show that the model can effectively identify the number of passengers actually matched with the number of mobile phones of passengers in a running vehicle, and has high detection accuracy.
Keywords: same user identification; mobile big data; CHC?CFA; data acquisition; dimensional analysis; identification model
根据国家统计局2018年发布的《中国改革开放40年通信业发展报告》显示,到2017年底,我国移动电话用户数量已经达到近14.17亿户,移动电话的普及率由1995年的0.3部/百人提高到2017年的102.5部/百人。随着个人智能移动手机终端的迅速普及,出行群体中手机拥有率和使用率已经达到非常高的比例,研究学者逐步意识到个人移动终端可以作为一种非常理想的智能交通探测平台[1]。目前,用户的智能移动手机内都集成GPS模块、陀螺仪、加速感应器等多种传感器,可以为用户提供基本的位置查询与导航等相关服务,通过采集出行群体中携带的手机相关数据可以对道路交通数据信息进行分析,这是一种新兴的智能交通动态监测手段[1?2]。……