Self-Adaptive Anytime Stream Clustering. Kranen, P., Assent, I., Baldauf, C., & Seidl, T. In 2009 Ninth IEEE International Conference on Data Mining, pages 249–258, December, 2009. ISSN: 2374-8486doi abstract bibtex Clustering streaming data requires algorithms which are capable of updating clustering results for the incoming data. As data is constantly arriving, time for processing is limited. Clustering has to be performed in a single pass over the incoming data and within the possibly varying inter-arrival times of the stream. Likewise, memory is limited, making it impossible to store all data. For clustering, we are faced with the challenge of maintaining a current result that can be presented to the user at any given time. In this work, we propose a parameter free algorithm that automatically adapts to the speed of the data stream. It makes best use of the time available under the current constraints to provide a clustering of the objects seen up to that point. Our approach incorporates the age of the objects to reflect the greater importance of more recent data. Moreover, we are capable of detecting concept drift, novelty and outliers in the stream. For efficient and effective handling, we introduce the ClusTree, a compact and self-adaptive index structure for maintaining stream summaries. Our experiments show that our approach is capable of handling a multitude of different stream characteristics for accurate and scalable anytime stream clustering.
@inproceedings{kranen_self-adaptive_2009,
title = {Self-{Adaptive} {Anytime} {Stream} {Clustering}},
doi = {10.1109/ICDM.2009.47},
abstract = {Clustering streaming data requires algorithms which are capable of updating clustering results for the incoming data. As data is constantly arriving, time for processing is limited. Clustering has to be performed in a single pass over the incoming data and within the possibly varying inter-arrival times of the stream. Likewise, memory is limited, making it impossible to store all data. For clustering, we are faced with the challenge of maintaining a current result that can be presented to the user at any given time. In this work, we propose a parameter free algorithm that automatically adapts to the speed of the data stream. It makes best use of the time available under the current constraints to provide a clustering of the objects seen up to that point. Our approach incorporates the age of the objects to reflect the greater importance of more recent data. Moreover, we are capable of detecting concept drift, novelty and outliers in the stream. For efficient and effective handling, we introduce the ClusTree, a compact and self-adaptive index structure for maintaining stream summaries. Our experiments show that our approach is capable of handling a multitude of different stream characteristics for accurate and scalable anytime stream clustering.},
booktitle = {2009 {Ninth} {IEEE} {International} {Conference} on {Data} {Mining}},
author = {Kranen, Philipp and Assent, Ira and Baldauf, Corinna and Seidl, Thomas},
month = dec,
year = {2009},
note = {ISSN: 2374-8486},
keywords = {Adaptive algorithm, Algorithm design and analysis, Clustering algorithms, Consumer behavior, Data analysis, Data mining, Memory management, NOT SELF-ADAPTIVE PARAMS, Partitioning algorithms, Sensor phenomena and characterization, Time factors, anytime algorithms, clustree, self-adaptive algorithms, stream clustering},
pages = {249--258},
}
Downloads: 0
{"_id":"d6Ns5JWRFDD9fG3YM","bibbaseid":"kranen-assent-baldauf-seidl-selfadaptiveanytimestreamclustering-2009","author_short":["Kranen, P.","Assent, I.","Baldauf, C.","Seidl, T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Self-Adaptive Anytime Stream Clustering","doi":"10.1109/ICDM.2009.47","abstract":"Clustering streaming data requires algorithms which are capable of updating clustering results for the incoming data. As data is constantly arriving, time for processing is limited. Clustering has to be performed in a single pass over the incoming data and within the possibly varying inter-arrival times of the stream. Likewise, memory is limited, making it impossible to store all data. For clustering, we are faced with the challenge of maintaining a current result that can be presented to the user at any given time. In this work, we propose a parameter free algorithm that automatically adapts to the speed of the data stream. It makes best use of the time available under the current constraints to provide a clustering of the objects seen up to that point. Our approach incorporates the age of the objects to reflect the greater importance of more recent data. Moreover, we are capable of detecting concept drift, novelty and outliers in the stream. For efficient and effective handling, we introduce the ClusTree, a compact and self-adaptive index structure for maintaining stream summaries. Our experiments show that our approach is capable of handling a multitude of different stream characteristics for accurate and scalable anytime stream clustering.","booktitle":"2009 Ninth IEEE International Conference on Data Mining","author":[{"propositions":[],"lastnames":["Kranen"],"firstnames":["Philipp"],"suffixes":[]},{"propositions":[],"lastnames":["Assent"],"firstnames":["Ira"],"suffixes":[]},{"propositions":[],"lastnames":["Baldauf"],"firstnames":["Corinna"],"suffixes":[]},{"propositions":[],"lastnames":["Seidl"],"firstnames":["Thomas"],"suffixes":[]}],"month":"December","year":"2009","note":"ISSN: 2374-8486","keywords":"Adaptive algorithm, Algorithm design and analysis, Clustering algorithms, Consumer behavior, Data analysis, Data mining, Memory management, NOT SELF-ADAPTIVE PARAMS, Partitioning algorithms, Sensor phenomena and characterization, Time factors, anytime algorithms, clustree, self-adaptive algorithms, stream clustering","pages":"249–258","bibtex":"@inproceedings{kranen_self-adaptive_2009,\n\ttitle = {Self-{Adaptive} {Anytime} {Stream} {Clustering}},\n\tdoi = {10.1109/ICDM.2009.47},\n\tabstract = {Clustering streaming data requires algorithms which are capable of updating clustering results for the incoming data. As data is constantly arriving, time for processing is limited. Clustering has to be performed in a single pass over the incoming data and within the possibly varying inter-arrival times of the stream. Likewise, memory is limited, making it impossible to store all data. For clustering, we are faced with the challenge of maintaining a current result that can be presented to the user at any given time. In this work, we propose a parameter free algorithm that automatically adapts to the speed of the data stream. It makes best use of the time available under the current constraints to provide a clustering of the objects seen up to that point. Our approach incorporates the age of the objects to reflect the greater importance of more recent data. Moreover, we are capable of detecting concept drift, novelty and outliers in the stream. For efficient and effective handling, we introduce the ClusTree, a compact and self-adaptive index structure for maintaining stream summaries. Our experiments show that our approach is capable of handling a multitude of different stream characteristics for accurate and scalable anytime stream clustering.},\n\tbooktitle = {2009 {Ninth} {IEEE} {International} {Conference} on {Data} {Mining}},\n\tauthor = {Kranen, Philipp and Assent, Ira and Baldauf, Corinna and Seidl, Thomas},\n\tmonth = dec,\n\tyear = {2009},\n\tnote = {ISSN: 2374-8486},\n\tkeywords = {Adaptive algorithm, Algorithm design and analysis, Clustering algorithms, Consumer behavior, Data analysis, Data mining, Memory management, NOT SELF-ADAPTIVE PARAMS, Partitioning algorithms, Sensor phenomena and characterization, Time factors, anytime algorithms, clustree, self-adaptive algorithms, stream clustering},\n\tpages = {249--258},\n}\n\n\n\n","author_short":["Kranen, P.","Assent, I.","Baldauf, C.","Seidl, T."],"key":"kranen_self-adaptive_2009","id":"kranen_self-adaptive_2009","bibbaseid":"kranen-assent-baldauf-seidl-selfadaptiveanytimestreamclustering-2009","role":"author","urls":{},"keyword":["Adaptive algorithm","Algorithm design and analysis","Clustering algorithms","Consumer behavior","Data analysis","Data mining","Memory management","NOT SELF-ADAPTIVE PARAMS","Partitioning algorithms","Sensor phenomena and characterization","Time factors","anytime algorithms","clustree","self-adaptive algorithms","stream clustering"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["XJ7Gu6aiNbAiJAjbw","XvjRDbrMBW2XJY3p9","3C6BKwtiX883bctx4","5THezwiL4FyF8mm4G","RktFJE9cDa98BRLZF","qpxPuYKLChgB7ox6D","PfM5iniYHEthCfQDH","iwKepCrWBps7ojhDx"],"keywords":["adaptive algorithm","algorithm design and analysis","clustering algorithms","consumer behavior","data analysis","data mining","memory management","not self-adaptive params","partitioning algorithms","sensor phenomena and characterization","time factors","anytime algorithms","clustree","self-adaptive algorithms","stream clustering"],"search_terms":["self","adaptive","anytime","stream","clustering","kranen","assent","baldauf","seidl"],"title":"Self-Adaptive Anytime Stream Clustering","year":2009}