@inproceedings{ea8f064f571e4b2aaf5963a025643899,
title = "Big data stream learning with SAMOA",
abstract = "Big data is flowing into every area of our life, professional and personal. Big data is defined as datasets whose size is beyond the ability of typical software tools to capture, store, manage and analyze, due to the time and memory complexity. Velocity is one of the main properties of big data. In this demo, we present SAMOA (Scalable Advanced Massive Online Analysis), an open-source platform for mining big data streams. It provides a collection of distributed streaming algorithms for the most common data mining and machine learning tasks such as classification, clustering, and regression, as well as programming abstractions to develop new algorithms. It features a pluggable architecture that allows it to run on several distributed stream processing engines such as Storm, S4, and Samza. SAMOA is written in Java and is available at http://samoa-project.net under the Apache Software License version 2.0.",
keywords = "Classification, Clustering, Data Streams, Distributed Systems, Machine Learning, Regression, Toolbox",
author = "Albert Bifet and Morales, \{Gianmarco De Francisci\}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 14th IEEE International Conference on Data Mining Workshops, ICDMW 2014 ; Conference date: 14-12-2014",
year = "2015",
month = jan,
day = "26",
doi = "10.1109/ICDMW.2014.24",
language = "English",
series = "IEEE International Conference on Data Mining Workshops, ICDMW",
publisher = "IEEE Computer Society",
number = "January",
pages = "1199--1202",
editor = "Zhi-Hua Zhou and Wei Wang and Ravi Kumar and Hannu Toivonen and Jian Pei and \{Zhexue Huang\}, Joshua and Xindong Wu",
booktitle = "Proceedings - 14th IEEE International Conference on Data Mining Workshops, ICDMW 2014",
edition = "January",
}