@comment{{This file has been generated by bib2bib 1.96}}
@comment{{Command line: /usr/bin/bib2bib -c 'category : "visualization"' -ob visualization.bib hahsler.bib}}
@inproceedings{hahsler:Hahsler2011c,
author = {Michael Hahsler and Sudheer Chelluboina},
title = {Visualizing Association Rules in Hierarchical Groups},
booktitle = {Computing Science and Statistics, Vol. 42, 42nd Symposium on the Interface:
Statistical, Machine Learning, and Visualization Algorithms
(Interface 2011)},
year = {2011},
month = {June},
pages = {},
location = {Cary, North Carolina},
date = {June 1--3, 2011},
publisher = {The Interface Foundation of North America},
editor = {},
abstract = {
Association rule mining is one of the most popular data mining methods.
However, mining association rules often results in a very large number
of found rules, leaving the analyst with the task to go through all the
rules and discover interesting ones. Sifting manually through large
sets of rules is time consuming and strenuous. Visualization has a long
history of making large amounts of data better accessible using
techniques like selecting and zooming. However, most association rule
visualization techniques are still falling short when it comes to a
large number of rules. In this paper we present a new interactive
visualization technique which lets the user navigate through a
hierarchy of groups of association rules. We demonstrate how this new
visualization techniques can be used to analyze a large sets of
association rules with examples from our implementation in the
R-package arulesViz.
},
pdf = {http://michael.hahsler.net/research/Interface2011/arulesViz/arulesViz.pdf},
category = {association rules, visualization}
}
@article{hahsler:Hahsler2011b,
author = {Michael Hahsler and Kurt Hornik},
title = {Dissimilarity Plots: {A} Visual Exploration Tool for Partitional Clustering},
journal = {Journal of Computational and Graphical Statistics},
year = {2011},
month = {June},
volume = {10},
number = {2},
pages = {335--354},
url = {http://pubs.amstat.org/doi/abs/10.1198/jcgs.2010.09139},
pdf = {http://michael.hahsler.net/research/dissplot_JCGS2011/dissplot_preprint.pdf},
abstract = {
For hierarchical clustering, dendrograms are a convenient
and powerful visualization technique. Although many visualization methods
have been suggested for partitional clustering, their usefulness
deteriorates quickly with increasing dimensionality of the data and/or they
fail to represent structure between and within clusters simultaneously. In
this paper we extend (dissimilarity) matrix shading with several reordering
steps based on seriation techniques. Both ideas, matrix shading and
reordering, have been well-known for a long time. However, only recent
algorithmic improvements allow us to solve or approximately solve the
seriation problem efficiently for larger problems. Furthermore, seriation
techniques are used in a novel stepwise process (within each cluster and
between clusters) which leads to a visualization technique that is
able to present the structure between clusters and the micro-structure
within clusters in one concise plot. This not only allows us to judge
cluster quality but also makes mis-specification of the number of clusters
apparent. We give a detailed discussion of the construction of
dissimilarity plots and demonstrate their usefulness with several examples.
Experiments show that dissimilarity plots scale very well with increasing
data dimensionality.
},
category = {seriation, visualization}
}
@techreport{hahsler:Hahsler2009,
author = {Michael Hahsler and Kurt Hornik},
title = {Dissimilarity Plots: A Visual Exploration Tool for Partitional Clustering},
institution = {Research Report Series, Department of Statistics and Mathematics, Wirtschaftsuniversit{\"a}t Wien},
year = {2009},
type = {Report},
number = {89},
address = {Augasse 2--6, 1090 Wien, Austria},
month = {September},
abstract = {For hierarchical clustering, dendrograms provide convenient
and powerful visualization. Although many visualization methods have
been suggested for partitional clustering, their usefulness
deteriorates quickly with increasing dimensionality of the data and/or
they fail to represent structure between and within clusters
simultaneously. In this paper we extend (dissimilarity) matrix shading
with several reordering steps based on seriation. Both methods,
matrix shading and seriation, have been well-known for a long time.
However, only recent algorithmic improvements allow to use seriation
for larger problems. Furthermore, seriation is used in a novel
stepwise process (within each cluster and between clusters) which
leads to a visualization technique that is independent of the
dimensionality of the data. A big advantage is that it presents the
structure between clusters and the micro-structure within clusters
in one concise plot. This not only allows for judging
cluster quality but also makes mis-specification of the number of clusters
apparent. We give a detailed discussion of the construction of
dissimilarity plots and demonstrate their usefulness with several
examples.},
nopdf = {http://michael.hahsler.net/research/dissplot_workingpaper2009/dissplot.pdf},
url = {http://epub.wu.ac.at/id/eprint/1244},
category = {seriation, visualization}
}
@article{hahsler:Hahsler2007g,
author = {Michael Hahsler and Kurt Hornik},
title = {{TSP} -- {I}nfrastructure for the Traveling Salesperson
Problem},
journal = {Journal of Statistical Software},
year = {2007},
volume = {23},
pages = {1-21},
number = {2},
month = {December},
abstract = {
The traveling salesperson (or, salesman) problem (TSP) is a well known and
important combinatorial optimization problem. The goal is to find the
shortest tour that visits each city in a given list exactly once and then
returns to the starting city. Despite this simple problem statement,
solving the TSP is difficult since it belongs to the class of NP-complete
problems. The importance of the TSP arises besides from its theoretical
appeal from the variety of its applications. Typical applications in
operations research include vehicle routing, computer wiring, cutting
wallpaper and job sequencing. The main application in statistics is
combinatorial data analysis, e.g., reordering rows and columns of data
matrices or identifying clusters. In this paper we introduce the
R~package TSP which provides a basic infrastructure for
handling and solving the traveling salesperson problem. The package
features S3 classes for specifying a TSP and its (possibly optimal)
solution as well as several heuristics to find good solutions. In addition,
it provides an interface to Concorde, one of the best exact TSP solvers
currently available.},
issn = {1548-7660},
url = {http://www.jstatsoft.org/v23/i02},
nopdf = {http://michael.hahsler.net/research/TSP_jss2007/v23i02/v23i02.pdf},
category = {seriation, visualization}
}
@article{hahsler:Hahsler2008,
author = {Michael Hahsler and Kurt Hornik and Christian Buchta},
title = {Getting Things in Order: An Introduction to the {R}
Package seriation},
journal = {Journal of Statistical Software},
year = {2008},
volume = {25},
pages = {1--34},
number = {3},
month = {March},
abstract = {Seriation, i.e., finding a linear order for a set of objects
given data and a loss or merit function, is a basic problem in data
analysis. Caused by the problem's combinatorial nature, it is hard
to solve for all but very small sets. Nevertheless, both exact
solution methods and heuristics are available. In this paper we
present the package~seriation which provides the infrastructure for
seriation with R. The infrastructure comprises data structures to
represent linear orders as permutation vectors, a wide array of
seriation methods using a consistent interface, a method to calculate
the value of various loss and merit functions, and several
visualization techniques which build on seriation. To illustrate how
easily the package can be applied for a variety of applications, a
comprehensive collection of examples is presented.},
issn = {1548-7660},
url = {http://www.jstatsoft.org/v25/i03},
nopdf = {http://michael.hahsler.net/research/seriation_JSS2008/seriation.pdf},
category = {seriation, visualization}
}
@techreport{hahsler:Hahsler2007e,
author = {Michael Hahsler and Kurt Hornik and Christian Buchta},
title = {Getting Things in Order: An Introduction to the {R} package seriation},
institution = {Research Report Series, Department of Statistics and Mathematics,
Wirtschaftsuniversit{\"a}t Wien},
year = {2007},
type = {Report},
number = {58},
address = {Augasse 2--6, 1090 Wien, Austria},
month = {August},
abstract = { Seriation, i.e., finding a linear order for a set of objects
given data and a loss or merit function, is a basic problem in data
analysis. Caused by the problem's combinatorial nature, it is
hard to solve for all but very small sets. Nevertheless, both exact
solution methods and heuristics are available. In this paper we
present the package seriation which provides the infrastructure for
seriation with R. The infrastructure comprises data structures to
represent linear orders as permutation vectors, a wide array of
seriation methods using a consistent interface, a method to calculate
the value of various loss and merit functions, and several
visualization techniques which build on seriation. To illustrate how
easily the package can be applied for a variety of applications, a
comprehensive collection of examples is presented. },
nopdf = {http://michael.hahsler.net/research/seriation_working2007/seriation.pdf},
url = {http://epub.wu.ac.at/id/eprint/852},
category = {seriation, visualization}
}
@techreport{hahsler:Hahsler2006g,
author = {Michael Hahsler and Kurt Hornik},
title = {{TSP} -- {I}nfrastructure for the Traveling
Salesperson Problem},
institution = {Research Report Series, Department of Statistics and Mathematics,
Wirtschaftsuniversit{\"a}t Wien},
year = {2006},
type = {Report},
number = {45},
address = {Augasse 2--6, 1090 Wien, Austria},
month = {December},
abstract = {The traveling salesperson or salesman problem (TSP) is a well
known and important combinatorial optimization problem. The goal is to
find the shortest tour that visits each city in a given list exactly
once and then returns to the starting city. Despite this simple
problem statement, solving the TSP is difficult since it belongs to
the class of NP-complete problems. The importance of the TSP arises
besides from its theoretical appeal from the variety of its
applications. In addition to vehicle routing, many other
applications, e.g., computer wiring, cutting wallpaper, job
sequencing or several data visualization techniques, require the
solution of a TSP. In this paper we introduce the R package TSP
which provides a basic infrastructure for handling and solving the
traveling salesperson problem. The package features S3 classes for
specifying a TSP and its (possibly optimal) solution as well as
several heuristics to find good solutions. In addition, it provides
an interface to Concorde, one of the best exact TSP solvers currently
available.},
nopdf = {http://michael.hahsler.net/research/TSP_working2006/TSP.pdf},
url = {http://epub.wu.ac.at/id/eprint/1230},
category = {seriation, visualization}
}
This file was generated by bibtex2html 1.96.