@inproceedings{5dacc37ef3da47cd9625f919e5c80200,
title = "A development of streaming big data analysis system using in-memory cluster computing framework: Spark",
abstract = "In this paper, to deal with stream big data processing issue, we design and implement a big data analysis system using Spark which is an In-memory cluster computing framework. Spark is provided by ASF (Apache Software Foundation) open-source community, and is regarded as a next-generation high performance cluster computing technology. From the performance evaluation of the proposed system, we can see that Spark is 20+ times faster than conventional Mapreduce-based Hive SQL in terms of the response time. According to these results, we can confirm that the proposed system can be applied to solve the soft real-time big data analysis jobs for sensor data generated in a smart factory.",
keywords = "Cloud, Hive SQL, MapReduce, Real-time, Spark",
author = "Kiejin Park and Changwon Baek and Limei Peng",
note = "Publisher Copyright: {\textcopyright} Springer Science+Business Media Singapore 2016.; 11th International Conference on Future Information Technology, FutureTech 2016 ; Conference date: 20-04-2016 Through 22-04-2016",
year = "2016",
doi = "10.1007/978-981-10-1536-6_21",
language = "English",
isbn = "9789811015359",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "157--163",
editor = "Hai Jin and Young-Sik Jeong and Khan, {Muhammad Khurram} and Park, {James J.}",
booktitle = "Advanced Multimedia and Ubiquitous Engineering - FutureTech and MUE",
address = "Germany",
}