@inproceedings{stumme01conceptualclustering,
  address = {Universität Dortmund 763},
  author = {Stumme, G. and Taouil, R. and Bastide, Y. and Lakhal, L.},
  booktitle = {Proc. GI-Fachgruppentreffen Maschinelles Lernen (FGML'01)},
  editor = {Klinkenberg, R. and Rüping, S. and Fick, A. and Henze, N. and Herzog, C. and Molitor, R. and Schröder, O.},
  interhash = {c99f2ae002435208c58f9244d298a10b},
  intrahash = {f4ec21d5f63dbc213a3a6eae076c4b62},
  month = {October},
  title = {Conceptual Clustering with Iceberg Concept Lattices},
  url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2001/FGML01.pdf},
  year = 2001
}

@book{tango2010statistical,
  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},
  address = {New York, NY},
  author = {Tango, Toshiro},
  edition = 1,
  format = {ebook},
  interhash = {20ae4f5773d215aded8304c02a071251},
  intrahash = {aa3f9cbf0e4ff83c7323cb2f1d7422eb},
  isbn = {1441915729 (Sekundärausgabe)},
  primaryauthor = {Tango, Toshiro},
  publisher = {Springer New York},
  series = {Statistics for Biology and Health},
  shorttitle = {Statistical Methods for Disease Clustering},
  subtitle = {[Elektronische Ressource] / by Toshiro Tango},
  title = {Statistical Methods for Disease Clustering},
  titlestatement = {by Toshiro Tango},
  uniqueid = {HEB221142568},
  url = {http://scans.hebis.de/HEBCGI/show.pl?22114256_aub.html},
  year = 2010
}

@inproceedings{zhang1996birch,
  acmid = {233324},
  address = {New York, NY, USA},
  author = {Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron},
  booktitle = {Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data},
  doi = {10.1145/233269.233324},
  interhash = {bd3d8e33e8785ecf66408081db016ca4},
  intrahash = {250cecc10ceecd05a96bed00b6cf0fd7},
  isbn = {0-89791-794-4},
  location = {Montreal, Quebec, Canada},
  numpages = {12},
  pages = {103--114},
  publisher = {ACM},
  series = {SIGMOD '96},
  title = {BIRCH: An Efficient Data Clustering Method for Very Large Databases},
  url = {http://doi.acm.org/10.1145/233269.233324},
  year = 1996
}

@article{Jain:1999:DCR:331499.331504,
  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.},
  acmid = {331504},
  address = {New York, NY, USA},
  author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.},
  doi = {10.1145/331499.331504},
  hans = {otto},
  interhash = {5113b61d428d4de4423182e5f2b2f468},
  intrahash = {bd7234f7139a1651acfaed57b5c2551f},
  issn = {0360-0300},
  issue_date = {Sept. 1999},
  journal = {ACM Comput. Surv.},
  month = sep,
  number = 3,
  numpages = {60},
  pages = {264--323},
  publisher = {ACM},
  title = {Data Clustering: A Review},
  url = {http://doi.acm.org/10.1145/331499.331504},
  volume = 31,
  year = 1999
}

@book{DBLP:books/crc/aggarwal2013,
  bibsource = {DBLP, http://dblp.uni-trier.de},
  editor = {Aggarwal, Charu C. and Reddy, Chandan K.},
  ee = {http://www.crcpress.com/product/isbn/9781466558212, http://www.charuaggarwal.net/clusterbook.pdf},
  interhash = {5f150f838457faaa3805b0ed034c845f},
  intrahash = {7f1541e5800e6c36c67dd6bc0ef64ba7},
  isbn = {978-1-46-655821-2},
  publisher = {CRC Press},
  title = {Data Clustering: Algorithms and Applications},
  url = {http://www.charuaggarwal.net/clusterbook.pdf},
  year = 2014
}

@article{Jain:1999:DCR:331499.331504,
  acmid = {331504},
  address = {New York, NY, USA},
  author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.},
  doi = {10.1145/331499.331504},
  interhash = {5113b61d428d4de4423182e5f2b2f468},
  intrahash = {b19bcef82a04eb82ee4abde53ee7d1c2},
  issn = {0360-0300},
  issue_date = {Sept. 1999},
  journal = {ACM Comput. Surv.},
  month = sep,
  number = 3,
  numpages = {60},
  pages = {264--323},
  publisher = {ACM},
  title = {Data clustering: a review},
  url = {http://doi.acm.org/10.1145/331499.331504},
  volume = 31,
  year = 1999
}

@article{RePEc:eee:csdana:v:41:y:2002:i:1:p:59-90,
  abstract = {No abstract is available for this item.},
  author = {Dhillon, Inderjit S. and Modha, Dharmendra S. and Spangler, W. Scott},
  interhash = {3ff82dddf6ce4d86909347824554ddf8},
  intrahash = {03e92f40796a0093a6e882a83f5cd995},
  journal = {Computational Statistics \& Data Analysis},
  month = {November},
  number = 1,
  pages = {59-90},
  title = {Class visualization of high-dimensional data with applications},
  url = {http://www.cs.utexas.edu/~inderjit/public_papers/csda.pdf},
  volume = 41,
  year = 2002
}

@electronic{nedjah2009intelligent,
  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.},
  address = {Berlin},
  author = {Nedjah, Nadia},
  interhash = {fe4dc424274eac3c1588fda8bfa5290a},
  intrahash = {1a61a34d4984ee4451be75902c25c49b},
  isbn = {9783540856443 3540856447 9783540856436 3540856439},
  publisher = {Springer},
  refid = {656393969},
  title = {Intelligent text categorization and clustering},
  url = {http://rave.ohiolink.edu/ebooks/ebc/9783540856443},
  year = 2009
}

@incollection{springerlink:10.1007/978-3-540-74839-7_12,
  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.},
  address = {Berlin / Heidelberg},
  affiliation = {Department of Computer and Information Science, University of Konstanz},
  author = {Brandes, Ulrik and Delling, Daniel and Gaertler, Marco and Görke, Robert and Hoefer, Martin and Nikoloski, Zoran and Wagner, Dorothea},
  booktitle = {Graph-Theoretic Concepts in Computer Science},
  doi = {10.1007/978-3-540-74839-7_12},
  editor = {Brandstädt, Andreas and Kratsch, Dieter and Müller, Haiko},
  interhash = {b335302041d1865d7cfec7467e8e2999},
  intrahash = {6fd10991ee4e3880c64c11862884ead7},
  isbn = {978-3-540-74838-0},
  keyword = {Computer Science},
  openurl = {http://www.blub.de},
  pages = {121-132},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {On Finding Graph Clusterings with Maximum Modularity},
  url = {http://dx.doi.org/10.1007/978-3-540-74839-7_12},
  volume = 4769,
  year = 2007
}

@article{newman2006modularity,
  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.},
  author = {Newman, M. E. J.},
  doi = {10.1073/pnas.0601602103},
  interhash = {e664336d414a1e21d89f30cc56f5e739},
  intrahash = {5dd9d0c2155f242393e63547d8a2347f},
  journal = {Proceedings of the National Academy of Sciences},
  number = 23,
  pages = {8577--8582},
  title = {Modularity and community structure in networks},
  volume = 103,
  year = 2006
}