@inproceedings{b568073f01864887b480a8e54c3a3726,
title = "Inference patterns from Big Data using aggregation, filtering and tagging- A survey",
abstract = "This paper reviews various approaches to infer the patterns from Big Data using aggregation, filtering and tagging. Earlier research shows that data aggregation concerns about gathered data and how efficiently it can be utilized. It is understandable that at the time of data gathering one does not care much about whether the gathered data will be useful or not. Hence, filtering and tagging of the data are the crucial steps in collecting the relevant data to fulfill the need. Therefore the main goal of this paper is to present a detailed and comprehensive survey on different approaches. To make the concept clearer, we have provided a brief introduction of Big Data, how it works, working of two data aggregation tools (namely, flume and sqoop), data processing tools (hive and mahout) and various algorithms that can be useful to understand the topic. At last we have included comparisons between aggregation tools, processing tools as well as various algorithms through its pre-process, matching time, results and reviews.",
keywords = "aggregation, Big Data, filtering, Flume, Hadoop, HDFS, Hive, Mahout, MapReduce, Sqoop, tagging",
author = "Prakashbhai, {Pathak Anand} and Pandey, {Hari Mohan}",
year = "2014",
month = nov,
day = "6",
doi = "10.1109/CONFLUENCE.2014.6949238",
language = "English",
isbn = "9781479942367",
series = "Proceedings of the 5th International Conference on Confluence 2014: The Next Generation Information Technology Summit",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "66--71",
booktitle = "Proceedings of the 5th International Conference on Confluence 2014: The Next Generation Information Technology Summit",
address = "United States",
note = "5th International Conference on Confluence 2014 - The Next Generation Information Technology Summit ; Conference date: 25-09-2014 Through 26-09-2014",
}