@inproceedings{28511c5011394709bfa127c7452b140a,
title = "Improving expectation maximization algorithm over stellar data",
abstract = "Stellar data, only a few years ago, measured in the.1M of objects. Now, sets are routinely 1M. With the launch of ESA's Gaia in 2013, we expect 1000M stellar objects measured more precisely and with more measurements. Without question, astronomy is about Big Data and clustering is a very common task over astronomy domain. The expectation-maximization algorithm is among the top 10 data mining algorithms used in scientific and industrial applications, however, we observe that astronomical community does not make use of it as a clustering algorithm. In this work, we cluster ∼ 1M stellar objects (simulated Galactic spectral data) via the traditional expectation-maximization algorithm for clustering (EM-T) and our extended EM-T algorithm that we call EM∗ and present the experimental results.",
keywords = "astronomy, big data, clustering, data reduction, expectation maximization, heap",
author = "Hasan Kurban and Can Kockan and Mark Jenne and Dalkilic, {Mehmet M.}",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 5th IEEE International Conference on Big Data, Big Data 2017 ; Conference date: 11-12-2017 Through 14-12-2017",
year = "2017",
month = jul,
day = "1",
doi = "10.1109/BigData.2017.8258215",
language = "English",
series = "Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2559--2568",
editor = "Jian-Yun Nie and Zoran Obradovic and Toyotaro Suzumura and Rumi Ghosh and Raghunath Nambiar and Chonggang Wang and Hui Zang and Ricardo Baeza-Yates and Ricardo Baeza-Yates and Xiaohua Hu and Jeremy Kepner and Alfredo Cuzzocrea and Jian Tang and Masashi Toyoda",
booktitle = "Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017",
address = "United States",
}