Data clustering is an important technique for exploratory data analysis, and has been studied for several years. It has been shown to be useful in many practical domains such as data classification and image processing. Recently, there has been a growing emphasis on exploratory analysis of very large datasets to discover useful patterns and/or correlations among attributes. This is called data mining, and data clustering is regarded as a particular branch. However existing data clustering methods do not adequately address the problem of processing large datasets with a limited amount of resources (e.g., memory and cpu cycles). So as the dataset size increases, they do not scale up well in terms of memory requirement, running time, and result quality.
%0 Journal Article
%1 Zhang1997BIRCH
%A Zhang, Tian
%A Ramakrishnan, Raghu
%A Livny, Miron
%B Data Mining and Knowledge Discovery
%D 1997
%I Kluwer Academic Publishers
%J Data Mining and Knowledge Discovery
%K birch clustering machine-learning
%N 2
%P 141--182
%R 10.1023/a:1009783824328
%T BIRCH: A New Data Clustering Algorithm and Its Applications
%U http://dx.doi.org/10.1023/a:1009783824328
%V 1
%X Data clustering is an important technique for exploratory data analysis, and has been studied for several years. It has been shown to be useful in many practical domains such as data classification and image processing. Recently, there has been a growing emphasis on exploratory analysis of very large datasets to discover useful patterns and/or correlations among attributes. This is called data mining, and data clustering is regarded as a particular branch. However existing data clustering methods do not adequately address the problem of processing large datasets with a limited amount of resources (e.g., memory and cpu cycles). So as the dataset size increases, they do not scale up well in terms of memory requirement, running time, and result quality.
@article{Zhang1997BIRCH,
abstract = {Data clustering is an important technique for exploratory data analysis, and has been studied for several years. It has been shown to be useful in many practical domains such as data classification and image processing. Recently, there has been a growing emphasis on exploratory analysis of very large datasets to discover useful patterns and/or correlations among attributes. This is called data mining, and data clustering is regarded as a particular branch. However existing data clustering methods do not adequately address the problem of processing large datasets with a limited amount of resources (e.g., memory and cpu cycles). So as the dataset size increases, they do not scale up well in terms of memory requirement, running time, and result quality.},
added-at = {2018-12-02T16:09:07.000+0100},
author = {Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron},
biburl = {https://www.bibsonomy.org/bibtex/23ac08b883f1e3bfbcc24c86fd21e4413/karthikraman},
booktitle = {Data Mining and Knowledge Discovery},
citeulike-article-id = {1470726},
citeulike-linkout-0 = {http://dx.doi.org/10.1023/a:1009783824328},
citeulike-linkout-1 = {http://www.springerlink.com/content/h145003651488451},
citeulike-linkout-2 = {http://link.springer.com/article/10.1023/A:1009783824328},
day = 1,
doi = {10.1023/a:1009783824328},
interhash = {739dd26a0e3f1634bf8c60035f2edc5b},
intrahash = {3ac08b883f1e3bfbcc24c86fd21e4413},
issn = {13845810},
journal = {Data Mining and Knowledge Discovery},
keywords = {birch clustering machine-learning},
month = jun,
number = 2,
pages = {141--182},
posted-at = {2010-05-20 17:25:45},
priority = {2},
publisher = {Kluwer Academic Publishers},
timestamp = {2018-12-02T16:09:07.000+0100},
title = {{BIRCH}: A New Data Clustering Algorithm and Its Applications},
url = {http://dx.doi.org/10.1023/a:1009783824328},
volume = 1,
year = 1997
}