@book{DBLP:books/crc/aggarwal2013,, title = {Data Clustering: Algorithms and Applications}, editor = {Aggarwal, Charu C. and Reddy, Chandan K.}, publisher = {CRC Press}, year = {2014}, url = {http://www.charuaggarwal.net/clusterbook.pdf}, isbn = {978-1-46-655821-2}, keywords = {clustering, toread} }

%0 = book %D = 2014 %I = CRC Press %T = Data Clustering: Algorithms and Applications %U = http://www.charuaggarwal.net/clusterbook.pdf

@incollection{radelaar2011improving, author = {Radelaar, Joni and Boor, Aart-Jan and Vandic, Damir and van Dam, Jan-Willem and Hogenboom, Frederik and Frasincar, Flavius}, title = {Improving the Exploration of Tag Spaces Using Automated Tag Clustering}, editor = {Auer, Sören and Díaz, Oscar and Papadopoulos, George}, booktitle = {Web Engineering}, series = {Lecture Notes in Computer Science}, publisher = {Springer Berlin / Heidelberg}, year = {2011}, volume = {6757}, pages = {274-288}, note = {10.1007/978-3-642-22233-7_19}, url = {http://dx.doi.org/10.1007/978-3-642-22233-7_19}, keywords = {clustering, tag, toread} }

%0 = incollection %A = Radelaar, Joni and Boor, Aart-Jan and Vandic, Damir and van Dam, Jan-Willem and Hogenboom, Frederik and Frasincar, Flavius %B = Web Engineering %D = 2011 %I = Springer Berlin / Heidelberg %T = Improving the Exploration of Tag Spaces Using Automated Tag Clustering %U = http://dx.doi.org/10.1007/978-3-642-22233-7_19

It has been known for a long time that citation networks are always highly clustered, such as the existences of abundant triangles and high clustering coefficient. In a growth model, one typical way to produce clustering is using the trid formation mechanism. However, we find that this mechanism fails to generate enough triangles in a real-world citation network. By analyzing the network, it is found that one paper always cites papers that are already highly connected. We point out that the highly connected papers may refer to similar research topic and one subsequent paper tends to cite all of them. Based on this assumption, we propose a growth model for citation networks in which a new paper i firstly attaches to one relevant paper j and then with a probability links those papers in the same clique to which j belongs. We compare our model to two real-world citation networks - one on a special research area and the other on multidisciplinary sciences. Results show that for the two networks the in-degree distributions are matched and the clustering features, i.e., the number of triangles and the average clustering coefficient, are well reproduced.

@misc{Ren2011, author = {Ren, Fu-Xin and Cheng, Xue-Qi and Shen, Hua-Wei}, title = {Modeling the clustering in citation networks}, year = {2011}, note = {cite arxiv:1104.4209}, url = {http://arxiv.org/abs/1104.4209}, keywords = {citation, clustering, info20, network}, abstract = { It has been known for a long time that citation networks are always highly clustered, such as the existences of abundant triangles and high clustering coefficient. In a growth model, one typical way to produce clustering is using the trid formation mechanism. However, we find that this mechanism fails to generate enough triangles in a real-world citation network. By analyzing the network, it is found that one paper always cites papers that are already highly connected. We point out that the highly connected papers may refer to similar research topic and one subsequent paper tends to cite all of them. Based on this assumption, we propose a growth model for citation networks in which a new paper i firstly attaches to one relevant paper j and then with a probability links those papers in the same clique to which j belongs. We compare our model to two real-world citation networks - one on a special research area and the other on multidisciplinary sciences. Results show that for the two networks the in-degree distributions are matched and the clustering features, i.e., the number of triangles and the average clustering coefficient, are well reproduced. } }

%0 = misc %A = Ren, Fu-Xin and Cheng, Xue-Qi and Shen, Hua-Wei %D = 2011 %T = Modeling the clustering in citation networks %U = http://arxiv.org/abs/1104.4209

@inproceedings{ls_leimeister, author = {Duennebeil, S. and Sunyaev, A. and Blohm, I. and Leimeister, J. M. and Krcmar, H.}, title = {Do German physicians want electronic health services? A characterization of potential adopters and rejectors in German ambulatory care}, booktitle = {3. International Conference on Health Informatics (HealthInf) 2010}, address = {Valencia, Spain}, year = {2010}, note = {163 (11-10)}, url = {http://www.uni-kassel.de/fb7/ibwl/leimeister/pub/JML_150.pdf}, keywords = {Adoption, Ambulatory, Care, Clustering, Data, Electronic, Equipment, Health, Infrastructure, Practice, Security, Services, Standardization, Technology, Telematics, itegpub, myown, pub_jml} }

%0 = inproceedings %A = Duennebeil, S. and Sunyaev, A. and Blohm, I. and Leimeister, J. M. and Krcmar, H. %B = 3. International Conference on Health Informatics (HealthInf) 2010 %C = Valencia, Spain %D = 2010 %T = Do German physicians want electronic health services? A characterization of potential adopters and rejectors in German ambulatory care %U = http://www.uni-kassel.de/fb7/ibwl/leimeister/pub/JML_150.pdf

The development of powerful computing environment and the geographical information system (GIS) in recent decades has thrust the analysis of geo-referenced disease incidence data into the mainstream of spatial epidemiology. This book offers a modern perspective on statistical methods for detecting disease clustering, an indispensable procedure to find a statistical evidence on aetiology of the disease under study.
With increasing public health concerns about environmental risks, the need for sophisticated methods for analyzing spatial health events is immediate. Furthermore, the research area of statistical methods for disease clustering now attracts a wide audience due to the perceived need to implement wide-ranging monitoring systems to detect possible health-related events such as the occurrence of the severe acute respiratory syndrome (SARS), pandemic influenza and bioterrorism

@book{tango2010statistical, author = {Tango, Toshiro}, title = {Statistical Methods for Disease Clustering}, series = {Statistics for Biology and Health}, publisher = {Springer New York}, address = {New York, NY}, year = {2010}, edition = {1}, url = {http://scans.hebis.de/HEBCGI/show.pl?22114256_aub.html}, isbn = {1441915729 (Sekundärausgabe)}, keywords = {bachelor, clustering, disease, kursarbeit, literaturliste}, abstract = {The development of powerful computing environment and the geographical information system (GIS) in recent decades has thrust the analysis of geo-referenced disease incidence data into the mainstream of spatial epidemiology. This book offers a modern perspective on statistical methods for detecting disease clustering, an indispensable procedure to find a statistical evidence on aetiology of the disease under study.
With increasing public health concerns about environmental risks, the need for sophisticated methods for analyzing spatial health events is immediate. Furthermore, the research area of statistical methods for disease clustering now attracts a wide audience due to the perceived need to implement wide-ranging monitoring systems to detect possible health-related events such as the occurrence of the severe acute respiratory syndrome (SARS), pandemic influenza and bioterrorism} }

%0 = book %A = Tango, Toshiro %C = New York, NY %D = 2010 %I = Springer New York %T = Statistical Methods for Disease Clustering %U = http://scans.hebis.de/HEBCGI/show.pl?22114256_aub.html

@phdthesis{bade2009personalized, author = {Bade, Korinna}, title = {Personalized Hierarchical Structuring}, school = {Otto-von-Guericke-Universitat Magdeburg}, year = {2009}, keywords = {clustering, hierarchical} }

%0 = phdthesis %A = Bade, Korinna %D = 2009 %T = Personalized Hierarchical Structuring

Web clustering engines organize search results by topic, thus offering a complementary view to the flat-ranked list returned by conventional search engines. In this survey, we discuss the issues that must be addressed in the development of a Web clustering engine, including acquisition and preprocessing of search results, their clustering and visualization. Search results clustering, the core of the system, has specific requirements that cannot be addressed by classical clustering algorithms. We emphasize the role played by the quality of the cluster labels as opposed to optimizing only the clustering structure. We highlight the main characteristics of a number of existing Web clustering engines and also discuss how to evaluate their retrieval performance. Some directions for future research are finally presented.

@article{Carpineto:2009:SWC:1541880.1541884, author = {Carpineto, Claudio and Osiński, Stanislaw and Romano, Giovanni and Weiss, Dawid}, title = {A survey of Web clustering engines}, journal = {ACM Comput. Surv.}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, volume = {41}, pages = {17:1--17:38}, url = {http://doi.acm.org/10.1145/1541880.1541884}, doi = {10.1145/1541880.1541884}, issn = {0360-0300}, keywords = {clustering, web, bachelor:2011:bachmann}, abstract = {Web clustering engines organize search results by topic, thus offering a complementary view to the flat-ranked list returned by conventional search engines. In this survey, we discuss the issues that must be addressed in the development of a Web clustering engine, including acquisition and preprocessing of search results, their clustering and visualization. Search results clustering, the core of the system, has specific requirements that cannot be addressed by classical clustering algorithms. We emphasize the role played by the quality of the cluster labels as opposed to optimizing only the clustering structure. We highlight the main characteristics of a number of existing Web clustering engines and also discuss how to evaluate their retrieval performance. Some directions for future research are finally presented.} }

%0 = article %A = Carpineto, Claudio and Osiński, Stanislaw and Romano, Giovanni and Weiss, Dawid %C = New York, NY, USA %D = 2009 %I = ACM %T = A survey of Web clustering engines %U = http://doi.acm.org/10.1145/1541880.1541884

In this poster, we investigate how to enhance web clustering by leveraging the tripartite network of social tagging systems. We propose a clustering method, called "Tripartite Clustering", which cluster the three types of nodes (resources, users and tags) simultaneously based on the links in the social tagging network. The proposed method is experimented on a real-world social tagging dataset sampled from del.icio.us. We also compare the proposed clustering approach with K-means. All the clustering results are evaluated against a human-maintained web directory. The experimental results show that Tripartite Clustering significantly outperforms the content-based K-means approach and achieves performance close to that of social annotation-based K-means whereas generating much more useful information.

@inproceedings{Lu:2009:ETN:1645953.1646167, author = {Lu, Caimei and Chen, Xin and Park, E. K.}, title = {Exploit the tripartite network of social tagging for web clustering}, booktitle = {Proceeding of the 18th ACM conference on Information and knowledge management}, series = {CIKM '09}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, pages = {1545--1548}, url = {http://doi.acm.org/10.1145/1645953.1646167}, doi = {10.1145/1645953.1646167}, isbn = {978-1-60558-512-3}, keywords = {clustering, web, bachelor:2011:bachmann}, abstract = {In this poster, we investigate how to enhance web clustering by leveraging the tripartite network of social tagging systems. We propose a clustering method, called "Tripartite Clustering", which cluster the three types of nodes (resources, users and tags) simultaneously based on the links in the social tagging network. The proposed method is experimented on a real-world social tagging dataset sampled from del.icio.us. We also compare the proposed clustering approach with K-means. All the clustering results are evaluated against a human-maintained web directory. The experimental results show that Tripartite Clustering significantly outperforms the content-based K-means approach and achieves performance close to that of social annotation-based K-means whereas generating much more useful information.} }

%0 = inproceedings %A = Lu, Caimei and Chen, Xin and Park, E. K. %B = Proceeding of the 18th ACM conference on Information and knowledge management %C = New York, NY, USA %D = 2009 %I = ACM %T = Exploit the tripartite network of social tagging for web clustering %U = http://doi.acm.org/10.1145/1645953.1646167

"Automatic Text Categorization and Clustering are becoming more and more important as the amount of text in electronic format grows and the access to it becomes more necessary and widespread. Well known applications are spam filtering and web search, but a large number of everyday uses exists (intelligent web search, data mining, law enforcement, etc.). Currently, researchers are employing many intelligent techniques for text categorization and clustering, ranging from support vector machines and neural networks to Bayesian inference and algebraic methods, such as Latent Semantic Indexing." "This volume offers a wide spectrum of research work developed for intelligent text categorization and clustering."-Jacket.

@electronic{nedjah2009intelligent, author = {Nedjah, Nadia}, title = {Intelligent text categorization and clustering}, publisher = {Springer}, address = {Berlin}, year = {2009}, url = {http://rave.ohiolink.edu/ebooks/ebc/9783540856443}, isbn = {9783540856443 3540856447 9783540856436 3540856439}, keywords = {clustering}, abstract = {"Automatic Text Categorization and Clustering are becoming more and more important as the amount of text in electronic format grows and the access to it becomes more necessary and widespread. Well known applications are spam filtering and web search, but a large number of everyday uses exists (intelligent web search, data mining, law enforcement, etc.). Currently, researchers are employing many intelligent techniques for text categorization and clustering, ranging from support vector machines and neural networks to Bayesian inference and algebraic methods, such as Latent Semantic Indexing." "This volume offers a wide spectrum of research work developed for intelligent text categorization and clustering."--Jacket.} }

%0 = electronic %A = Nedjah, Nadia %C = Berlin %D = 2009 %I = Springer %T = Intelligent text categorization and clustering %U = http://rave.ohiolink.edu/ebooks/ebc/9783540856443

@article{Leicht08community, author = {Leicht, E. A. and Newman, M. E. J.}, title = {Community Structure in Directed Networks}, journal = {Phys. Rev. Lett.}, publisher = {American Physical Society}, year = {2008}, volume = {100}, number = {11}, pages = {118703}, doi = {10.1103/PhysRevLett.100.118703}, keywords = {2011, clustering, community, directed, modularity, networks} }

%0 = article %A = Leicht, E. A. and Newman, M. E. J. %D = 2008 %I = American Physical Society %T = Community Structure in Directed Networks

Modularity is a recently introduced quality measure for graph clusterings. It has immediately received considerable attention in several disciplines, and in particular in the complex systems literature, although its properties are not well understood. We study the problem of finding clusterings with maximum modularity, thus providing theoretical foundations for past and present work based on this measure. More precisely, we prove the conjectured hardness of maximizing modularity both in the general case and with the restriction to cuts, and give an Integer Linear Programming formulation. This is complemented by first insights into the behavior and performance of the commonly applied greedy agglomaration approach.

@incollection{springerlink:10.1007/978-3-540-74839-7_12, author = {Brandes, Ulrik and Delling, Daniel and Gaertler, Marco and Görke, Robert and Hoefer, Martin and Nikoloski, Zoran and Wagner, Dorothea}, title = {On Finding Graph Clusterings with Maximum Modularity}, editor = {Brandstädt, Andreas and Kratsch, Dieter and Müller, Haiko}, booktitle = {Graph-Theoretic Concepts in Computer Science}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, address = {Berlin / Heidelberg}, year = {2007}, volume = {4769}, pages = {121-132}, url = {http://dx.doi.org/10.1007/978-3-540-74839-7_12}, doi = {10.1007/978-3-540-74839-7_12}, isbn = {978-3-540-74838-0}, keywords = {clustering, graph, modularity, theory}, abstract = {Modularity is a recently introduced quality measure for graph clusterings. It has immediately received considerable attention in several disciplines, and in particular in the complex systems literature, although its properties are not well understood. We study the problem of finding clusterings with maximum modularity, thus providing theoretical foundations for past and present work based on this measure. More precisely, we prove the conjectured hardness of maximizing modularity both in the general case and with the restriction to cuts, and give an Integer Linear Programming formulation. This is complemented by first insights into the behavior and performance of the commonly applied greedy agglomaration approach.} }

%0 = incollection %A = Brandes, Ulrik and Delling, Daniel and Gaertler, Marco and Görke, Robert and Hoefer, Martin and Nikoloski, Zoran and Wagner, Dorothea %B = Graph-Theoretic Concepts in Computer Science %C = Berlin / Heidelberg %D = 2007 %I = Springer %T = On Finding Graph Clusterings with Maximum Modularity %U = http://dx.doi.org/10.1007/978-3-540-74839-7_12

@inproceedings{grahl07conceptualKdml, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, title = {Conceptual Clustering of Social Bookmark Sites}, editor = {Hinneburg, Alexander}, booktitle = {Workshop Proceedings of Lernen -- Wissensentdeckung -- Adaptivität (LWA 2007)}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, year = {2007}, pages = {50-54}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf}, isbn = {978-3-86010-907-6}, keywords = {2007, Social, bookmark, bookmarking, clustering, collaborative, conceptual, folksonomies, folksonomy, itegpub, myown, social, tagging, tagorapub} }

%0 = inproceedings %A = Grahl, Miranda and Hotho, Andreas and Stumme, Gerd %B = Workshop Proceedings of Lernen -- Wissensentdeckung -- Adaptivität (LWA 2007) %D = 2007 %I = Martin-Luther-Universität Halle-Wittenberg %T = Conceptual Clustering of Social Bookmark Sites %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf

Many networks of interest in the sciences, including social networks, computer networks, and metabolic and regulatory networks, are found to divide naturally into communities or modules. The problem of detecting and characterizing this community structure is one of the outstanding issues in the study of networked systems. One highly effective approach is the optimization of the quality function known as “modularity” over the possible divisions of a network. Here I show that the modularity can be expressed in terms of the eigenvectors of a characteristic matrix for the network, which I call the modularity matrix, and that this expression leads to a spectral algorithm for community detection that returns results of demonstrably higher quality than competing methods in shorter running times. I illustrate the method with applications to several published network data sets.

@article{newman2006modularity, author = {Newman, M. E. J.}, title = {Modularity and community structure in networks}, journal = {Proceedings of the National Academy of Sciences}, year = {2006}, volume = {103}, number = {23}, pages = {8577--8582}, doi = {10.1073/pnas.0601602103}, keywords = {clustering, community, graph, modularity, network, structure}, abstract = {Many networks of interest in the sciences, including social networks, computer networks, and metabolic and regulatory networks, are found to divide naturally into communities or modules. The problem of detecting and characterizing this community structure is one of the outstanding issues in the study of networked systems. One highly effective approach is the optimization of the quality function known as “modularity” over the possible divisions of a network. Here I show that the modularity can be expressed in terms of the eigenvectors of a characteristic matrix for the network, which I call the modularity matrix, and that this expression leads to a spectral algorithm for community detection that returns results of demonstrably higher quality than competing methods in shorter running times. I illustrate the method with applications to several published network data sets.} }

%0 = article %A = Newman, M. E. J. %D = 2006 %T = Modularity and community structure in networks

Recently, research projects such as PADLR and SWAP
have developed tools like Edutella or Bibster, which are targeted at
establishing peer-to-peer knowledge management (P2PKM) systems. In
such a system, it is necessary to obtain provide brief semantic
descriptions of peers, so that routing algorithms or matchmaking
processes can make decisions about which communities peers should
belong to, or to which peers a given query should be forwarded.
This paper provides a graph clustering technique on
knowledge bases for that purpose. Using this clustering, we can show
that our strategy requires up to 58% fewer queries than the
baselines to yield full recall in a bibliographic P2PKM scenario.

@inproceedings{schmitz2006content, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, editor = {Sure, York and Domingue, John}, booktitle = {The Semantic Web: Research and Applications}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, volume = {4011}, pages = {530-544}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006content.pdf}, keywords = {2006, aggregation, clustering, content, graph, itegpub, l3s, myown, nepomuk, ontologies, ontology, seminar2006, theory}, abstract = {Recently, research projects such as PADLR and SWAP
have developed tools like Edutella or Bibster, which are targeted at
establishing peer-to-peer knowledge management (P2PKM) systems. In
such a system, it is necessary to obtain provide brief semantic
descriptions of peers, so that routing algorithms or matchmaking
processes can make decisions about which communities peers should
belong to, or to which peers a given query should be forwarded.
This paper provides a graph clustering technique on
knowledge bases for that purpose. Using this clustering, we can show
that our strategy requires up to 58% fewer queries than the
baselines to yield full recall in a bibliographic P2PKM scenario.} }

%0 = inproceedings %A = Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd %B = The Semantic Web: Research and Applications %C = Heidelberg %D = 2006 %I = Springer %T = Content Aggregation on Knowledge Bases using Graph Clustering %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006content.pdf

No abstract is available for this item.

@article{RePEc:eee:csdana:v:41:y:2002:i:1:p:59-90, author = {Dhillon, Inderjit S. and Modha, Dharmendra S. and Spangler, W. Scott}, title = {Class visualization of high-dimensional data with applications}, journal = {Computational Statistics & Data Analysis}, year = {2002}, volume = {41}, number = {1}, pages = {59-90}, url = {http://www.cs.utexas.edu/~inderjit/public_papers/csda.pdf}, keywords = {alphaworks, cluster, clustering, dm, visualization}, abstract = {No abstract is available for this item.} }

%0 = article %A = Dhillon, Inderjit S. and Modha, Dharmendra S. and Spangler, W. Scott %D = 2002 %T = Class visualization of high-dimensional data with applications %U = http://www.cs.utexas.edu/~inderjit/public_papers/csda.pdf

@inproceedings{stumme01conceptualclustering, author = {Stumme, G. and Taouil, R. and Bastide, Y. and Lakhal, L.}, title = {Conceptual Clustering with Iceberg Concept Lattices}, editor = {Klinkenberg, R. and Rüping, S. and Fick, A. and Henze, N. and Herzog, C. and Molitor, R. and Schröder, O.}, booktitle = {Proc. GI-Fachgruppentreffen Maschinelles Lernen (FGML'01)}, address = {Universität Dortmund 763}, year = {2001}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2001/FGML01.pdf}, keywords = {2001, analysis, closed, clustering, concept, conceptual, discovery, fca, formal, iceberg, itemsets, kdd, knowledge, lattices} }

%0 = inproceedings %A = Stumme, G. and Taouil, R. and Bastide, Y. and Lakhal, L. %B = Proc. GI-Fachgruppentreffen Maschinelles Lernen (FGML'01) %C = Universität Dortmund 763 %D = 2001 %T = Conceptual Clustering with Iceberg Concept Lattices %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2001/FGML01.pdf

@inproceedings{conf/mldm/ToivonenVVBV01, author = {Toivonen, Jarmo and Visa, Ari and Vesanen, Tomi and Back, Barbro and Vanharanta, Hannu}, title = {Validation of Text Clustering Based on Document Contents.}, editor = {Perner, Petra}, booktitle = {MLDM}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2001}, volume = {2123}, pages = {184-195}, url = {http://dblp.uni-trier.de/db/conf/mldm/mldm2001.html#ToivonenVVBV01}, isbn = {3-540-42359-1}, keywords = {clustering, text, toread} }

%0 = inproceedings %A = Toivonen, Jarmo and Visa, Ari and Vesanen, Tomi and Back, Barbro and Vanharanta, Hannu %B = MLDM %D = 2001 %I = Springer %T = Validation of Text Clustering Based on Document Contents. %U = http://dblp.uni-trier.de/db/conf/mldm/mldm2001.html#ToivonenVVBV01

Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overviewof pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.

@article{Jain:1999:DCR:331499.331504, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, title = {Data Clustering: A Review}, journal = {ACM Comput. Surv.}, publisher = {ACM}, address = {New York, NY, USA}, year = {1999}, volume = {31}, number = {3}, pages = {264--323}, url = {http://doi.acm.org/10.1145/331499.331504}, doi = {10.1145/331499.331504}, issn = {0360-0300}, keywords = {clustering, overview, review}, abstract = {Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overviewof pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.} }

%0 = article %A = Jain, A. K. and Murty, M. N. and Flynn, P. J. %C = New York, NY, USA %D = 1999 %I = ACM %T = Data Clustering: A Review %U = http://doi.acm.org/10.1145/331499.331504

@article{Jain:1999:DCR:331499.331504, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, title = {Data clustering: a review}, journal = {ACM Comput. Surv.}, publisher = {ACM}, address = {New York, NY, USA}, year = {1999}, volume = {31}, number = {3}, pages = {264--323}, url = {http://doi.acm.org/10.1145/331499.331504}, doi = {10.1145/331499.331504}, issn = {0360-0300}, keywords = {clustering} }

%0 = article %A = Jain, A. K. and Murty, M. N. and Flynn, P. J. %C = New York, NY, USA %D = 1999 %I = ACM %T = Data clustering: a review %U = http://doi.acm.org/10.1145/331499.331504

@inproceedings{zhang1996birch, author = {Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron}, title = {BIRCH: An Efficient Data Clustering Method for Very Large Databases}, booktitle = {Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data}, series = {SIGMOD '96}, publisher = {ACM}, address = {New York, NY, USA}, year = {1996}, pages = {103--114}, url = {http://doi.acm.org/10.1145/233269.233324}, doi = {10.1145/233269.233324}, isbn = {0-89791-794-4}, keywords = {birch, clustering, kdd} }

%0 = inproceedings %A = Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron %B = Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data %C = New York, NY, USA %D = 1996 %I = ACM %T = BIRCH: An Efficient Data Clustering Method for Very Large Databases %U = http://doi.acm.org/10.1145/233269.233324