@inproceedings{600f2a64fffa4a2fab6ee6045ae11f67,
title = "CleanCloud: Cleaning big data on cloud",
abstract = "We describe CleanCloud, a system for cleaning big data based on Map-Reduce paradigm in cloud. Using Map-Reduce paradigm, the system detects and repairs various data quality problems in big data. We demonstrate the following features of CleanCloud: (a) the support for cleaning multiple data quality problems in big data; (b) a visual tool for watching the status of big data cleaning process and tuning the parameters for data cleaning; (c) the friendly interface for data input and setting as well as cleaned data collection for big data. CleanCloud is a promising system that provides scalable and effect data cleaning mechanism for big data in either files or databases.",
keywords = "Data cleaning, Entity resolution, Parallel computing",
author = "Hongzhi Wang and Xiaoou Ding and Xiangying Chen and Jianzhong Li and Hong Gao",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 26th ACM International Conference on Information and Knowledge Management, CIKM 2017 ; Conference date: 06-11-2017 Through 10-11-2017",
year = "2017",
month = nov,
day = "6",
doi = "10.1145/3132847.3133187",
language = "英语",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery ",
pages = "2543--2546",
booktitle = "CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management",
address = "美国",
}