Data stream clustering: A survey. Silva, J. A., Faria, E. R., Barros, R. C., Hruschka, E. R., Carvalho, A. C. P. L. F. d., & Gama, J. ACM Computing Surveys, 46(1):13:1–13:31, July, 2013. ![Data stream clustering: A survey [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Data stream mining is an active research area that has recently emerged to discover knowledge from large amounts of continuously generated data. In this context, several data stream clustering algorithms have been proposed to perform unsupervised learning. Nevertheless, data stream clustering imposes several challenges to be addressed, such as dealing with nonstationary, unbounded data that arrive in an online fashion. The intrinsic nature of stream data requires the development of algorithms capable of performing fast and incremental processing of data objects, suitably addressing time and memory limitations. In this article, we present a survey of data stream clustering algorithms, providing a thorough discussion of the main design components of state-of-the-art algorithms. In addition, this work addresses the temporal aspects involved in data stream clustering, and presents an overview of the usually employed experimental methodologies. A number of references are provided that describe applications of data stream clustering in different domains, such as network intrusion detection, sensor networks, and stock market analysis. Information regarding software packages and data repositories are also available for helping researchers and practitioners. Finally, some important issues and open questions that can be subject of future research are discussed.
@article{silva_data_2013,
title = {Data stream clustering: {A} survey},
volume = {46},
issn = {0360-0300},
shorttitle = {Data stream clustering},
url = {https://doi.org/10.1145/2522968.2522981},
doi = {10.1145/2522968.2522981},
abstract = {Data stream mining is an active research area that has recently emerged to discover knowledge from large amounts of continuously generated data. In this context, several data stream clustering algorithms have been proposed to perform unsupervised learning. Nevertheless, data stream clustering imposes several challenges to be addressed, such as dealing with nonstationary, unbounded data that arrive in an online fashion. The intrinsic nature of stream data requires the development of algorithms capable of performing fast and incremental processing of data objects, suitably addressing time and memory limitations. In this article, we present a survey of data stream clustering algorithms, providing a thorough discussion of the main design components of state-of-the-art algorithms. In addition, this work addresses the temporal aspects involved in data stream clustering, and presents an overview of the usually employed experimental methodologies. A number of references are provided that describe applications of data stream clustering in different domains, such as network intrusion detection, sensor networks, and stock market analysis. Information regarding software packages and data repositories are also available for helping researchers and practitioners. Finally, some important issues and open questions that can be subject of future research are discussed.},
number = {1},
urldate = {2022-03-25},
journal = {ACM Computing Surveys},
author = {Silva, Jonathan A. and Faria, Elaine R. and Barros, Rodrigo C. and Hruschka, Eduardo R. and Carvalho, André C. P. L. F. de and Gama, João},
month = jul,
year = {2013},
keywords = {Data stream clustering, online clustering},
pages = {13:1--13:31},
}
Downloads: 0
{"_id":"uxuZ9QZJwMKf53Z9r","bibbaseid":"silva-faria-barros-hruschka-carvalho-gama-datastreamclusteringasurvey-2013","author_short":["Silva, J. A.","Faria, E. R.","Barros, R. C.","Hruschka, E. R.","Carvalho, A. C. P. L. F. d.","Gama, J."],"bibdata":{"bibtype":"article","type":"article","title":"Data stream clustering: A survey","volume":"46","issn":"0360-0300","shorttitle":"Data stream clustering","url":"https://doi.org/10.1145/2522968.2522981","doi":"10.1145/2522968.2522981","abstract":"Data stream mining is an active research area that has recently emerged to discover knowledge from large amounts of continuously generated data. In this context, several data stream clustering algorithms have been proposed to perform unsupervised learning. Nevertheless, data stream clustering imposes several challenges to be addressed, such as dealing with nonstationary, unbounded data that arrive in an online fashion. The intrinsic nature of stream data requires the development of algorithms capable of performing fast and incremental processing of data objects, suitably addressing time and memory limitations. In this article, we present a survey of data stream clustering algorithms, providing a thorough discussion of the main design components of state-of-the-art algorithms. In addition, this work addresses the temporal aspects involved in data stream clustering, and presents an overview of the usually employed experimental methodologies. A number of references are provided that describe applications of data stream clustering in different domains, such as network intrusion detection, sensor networks, and stock market analysis. Information regarding software packages and data repositories are also available for helping researchers and practitioners. Finally, some important issues and open questions that can be subject of future research are discussed.","number":"1","urldate":"2022-03-25","journal":"ACM Computing Surveys","author":[{"propositions":[],"lastnames":["Silva"],"firstnames":["Jonathan","A."],"suffixes":[]},{"propositions":[],"lastnames":["Faria"],"firstnames":["Elaine","R."],"suffixes":[]},{"propositions":[],"lastnames":["Barros"],"firstnames":["Rodrigo","C."],"suffixes":[]},{"propositions":[],"lastnames":["Hruschka"],"firstnames":["Eduardo","R."],"suffixes":[]},{"propositions":[],"lastnames":["Carvalho"],"firstnames":["André","C.","P.","L.","F.","de"],"suffixes":[]},{"propositions":[],"lastnames":["Gama"],"firstnames":["João"],"suffixes":[]}],"month":"July","year":"2013","keywords":"Data stream clustering, online clustering","pages":"13:1–13:31","bibtex":"@article{silva_data_2013,\n\ttitle = {Data stream clustering: {A} survey},\n\tvolume = {46},\n\tissn = {0360-0300},\n\tshorttitle = {Data stream clustering},\n\turl = {https://doi.org/10.1145/2522968.2522981},\n\tdoi = {10.1145/2522968.2522981},\n\tabstract = {Data stream mining is an active research area that has recently emerged to discover knowledge from large amounts of continuously generated data. In this context, several data stream clustering algorithms have been proposed to perform unsupervised learning. Nevertheless, data stream clustering imposes several challenges to be addressed, such as dealing with nonstationary, unbounded data that arrive in an online fashion. The intrinsic nature of stream data requires the development of algorithms capable of performing fast and incremental processing of data objects, suitably addressing time and memory limitations. In this article, we present a survey of data stream clustering algorithms, providing a thorough discussion of the main design components of state-of-the-art algorithms. In addition, this work addresses the temporal aspects involved in data stream clustering, and presents an overview of the usually employed experimental methodologies. A number of references are provided that describe applications of data stream clustering in different domains, such as network intrusion detection, sensor networks, and stock market analysis. Information regarding software packages and data repositories are also available for helping researchers and practitioners. Finally, some important issues and open questions that can be subject of future research are discussed.},\n\tnumber = {1},\n\turldate = {2022-03-25},\n\tjournal = {ACM Computing Surveys},\n\tauthor = {Silva, Jonathan A. and Faria, Elaine R. and Barros, Rodrigo C. and Hruschka, Eduardo R. and Carvalho, André C. P. L. F. de and Gama, João},\n\tmonth = jul,\n\tyear = {2013},\n\tkeywords = {Data stream clustering, online clustering},\n\tpages = {13:1--13:31},\n}\n\n\n\n","author_short":["Silva, J. A.","Faria, E. R.","Barros, R. C.","Hruschka, E. R.","Carvalho, A. C. P. L. F. d.","Gama, J."],"key":"silva_data_2013","id":"silva_data_2013","bibbaseid":"silva-faria-barros-hruschka-carvalho-gama-datastreamclusteringasurvey-2013","role":"author","urls":{"Paper":"https://doi.org/10.1145/2522968.2522981"},"keyword":["Data stream clustering","online clustering"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["data stream clustering","online clustering"],"search_terms":["data","stream","clustering","survey","silva","faria","barros","hruschka","carvalho","gama"],"title":"Data stream clustering: A survey","year":2013}