基于Hadoop的车位空闲模式挖掘方法  

Mining method for parking space idle pattern based on Hadoop

作　　者：张艺琼 王海青 王锁柱[2] 高琳琦[3] ZHANG Yiqiong;WANG Haiqing;WANG Suozhu;GAO Linqi(Information Engineering College,Capital Normal University,Beijing 100048,China;School of Management,Capital Normal University,Beijing 100048,China;School of Management,Tianjin Normal University,Tianjin 300387,China)

机构地区：[1]首都师范大学信息工程学院,北京100048 [2]首都师范大学管理学院,北京100048 [3]天津师范大学管理学院,天津300387

出　　处：《天津师范大学学报（自然科学版）》2021年第1期69-74,共6页Journal of Tianjin Normal University：Natural Science Edition

基　　金：国家自然科学基金资助项目(61371177);北京市教委科技计划资助项目(KM201810028021).

摘　　要：提出一种基于Hadoop平台的车位空闲模式挖掘方法.利用Apriori算法的思想定义空闲模式,并通过构造带标记的事务矩阵,在搜索过程中实现对事务集和连接步的压缩,同时采用MapReduce并行计算框架设计具体实现方案.实验结果表明,与传统方法相比,该方法提高了计算效率,能快速完成车位空闲模式的挖掘.A mining method for parking space idle pattern based on Hadoop platform is proposed.The idea of Apriori algorithm is used to define the idle mode,and the marked transaction matrix is constructed to achieve the compression of transaction set and connection step in the search process.Meanwhile,the MapReduce parallel computing framework is adopted to design the concrete implementation scheme.The experimental results show that compared with the traditional method,the proposed method has higher computational efficiency and can quickly find the parking space idle pattern.

关 键 词：HADOOP APRIORI MAPREDUCE 频繁项集 车位空闲模式 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]