An efficient data processing framework for mining the massive trajectory of moving objects

详细信息    查看全文

• 作者：Yuanchun Zhou^a ; ¹ ; Yang Zhang^a ; ¹ ; Yong Ge^b ; Zhenghua Xue^a ; Yanjie Fu^c ; Danhuai Guo^a ; Jing Shao^a ; Tiangang Zhu^a ; Xuezhi Wang^a ; Jianhui Li^a ; ^lijh@cnic.cn
• 关键词：Big data ; Trajectory of moving object ; Compression contribution model ; Parallel linear referencing ; Two step consistent hashing
• 刊名：Computers, Environment and Urban Systems
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：61
• 期：part_PB
• 页码：129-140
• 全文大小：1683 K
• 卷排序：61

文摘

A novel framework for efficient processing of trajectory data of moving objects. Propose a big data distribution module based on a two-step consistent hashing algorithm. Propose a data transformation module based on a parallel linear referencing strategy. Propose a compression-aware I/O performance improvement module. Conduct extensive empirical studies on large scale 1.114 TB synthetic data and real 578 GB GPS data.