Unknown (and unexpected) multivariate patterns lurking in high-dimensional datasets are often very hard to find. This paper describes a human-centered exploration environment, which incorporates a coordinated suite of computational and visualization methods to explore high-dimensional data for uncovering patterns in multivariate spaces. Specifically, it includes: (1) an interactive feature selection method for identifying potentially interesting, multidimensional subspaces from a high-dimensional data space, (2) an interactive, hierarchical clustering method for searching multivariate clusters of arbitrary shape, and (3) a suite of coordinated visualization and computational components centered around the above two methods to facilitate a human-led exploration. The implemented system is used to analyze a cancer dataset and shows that it is efficient and effective for discovering unknown and unexpected multivariate patterns from high-dimensional data.
AgrawalRGehrkeJGunopulosDRaghavanP.Automatic Subspace Clustering of High Dimensional Data for Data Mining Applications. ACM SIGMOD International Conference on Management of Data (Seattle, WA, U.S.A., 1998), ACM Press: New York, 94–105.
2.
ProcopiucCMJonesMAgarwalPKMuraliTM. A Monte Carlo Algorithm for Fast Projective Clustering. ACM SIGMOD International Conference on Management of Data (Madison, WI, U.S.A., 2002), ACM Press: New York, 418–427.
3.
ChengCFuAZhangY.Entropy-based subspace clustering for mining numerical data. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Diego, CA, USA, 1999), ACM Press: New York, 84–93.
4.
FayyadUPiatetsky-ShapiroGSmythP.From data mining to knowledge discovery-an review. In: FayyadUPiatetsky-ShapiroGSmythPUthurusayR (Eds). Advances in Knowledge Discovery. AAAI Press/The MIT Press: Cambridge, MA, 1996; 1–33.
5.
LiuHMotodaH.Feature Selection for Knowledge Discovery and Data Mining. Kluwer Academic Publishers: Dordrecht, 1998; 214pp.
6.
DyJGBrodleyCE. Feature subset selection and order identification for unsuprervised learning. The Seventeenth International Conference on Machine Learning, Stanford University (CA, U.S.A., 2000), 247–254.
7.
DyJGBrodleyCE. Visualization and interactive feature selection for unsupervised data. The Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Boston, MA, U.S.A., 2000), ACM Press: New York, 360–364.
8.
KimYStreetWNMenczerF.Feature selection in unsupervised learning via evolutionary search. The Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Boston, MA, U.S.A., 2000), ACM Press: New York, 365–369.
9.
AggarwalCCWolfJLYuPSProcopiucCParkJS. Fast algorithms for projected clustering. ACM SIGMOD International Conference on Management of Data (Philadelphia, Pennsylvania, U.S.A., 1999), ACM Press: New York, 61–72.
10.
AggarwalCCYuPS. Finding generalized projected clusters in high dimensional spaces. ACM SIGMOD International Conference on Management of Data (Dallas, TX, U.S.A, 2000), ACM Press: New York, 70–81.
11.
JongHdRipA.The computer revolution in science: Steps toward the realization of computer-supported discovery environments. Artificial Intelligence1997; 91: 225–256.
AnkerstMEsterMKriegelH-P.Towards an effective cooperation of the user and the computer for classification. The Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Boston, MA, USA, 2000), ACM Press: New York, 179–188.
FriendlyM.Corrgrams: Exploratory displays for correlation matrices. The American Statistician2002; 19: 316–325.
16.
AnkerstMBerchtoldSKeimDA. Similarity clustering of dimensions for an enhanced visualization of multidimensional data. Information Visualization 1998 (Raleigh-Durham, NC, USA, 1998), 52–60.
17.
GordonAD. A review of hierarchical classification. Journal of the Royal Statistical Society. Series A (General)1987; 150: 119–137.
18.
GordonAD. Hierarchical classification. In: ArabiePHubertLJSoeteGD (Eds). Clustering and Classification. World Scientific Publisher: River Edge, NJ, USA; 1996; 65–122.
JainAKMurtyMNFlynnPJ. Data clustering: A review. ACM Computing Surveys (CSUR)1999; 31: 264–323.
21.
GuoDPeuquetDGaheganM.ICEAGE: Interactive clustering and exploration of large and high-dimensional geodata. GeoInformatica2003; 7: 229–253.
22.
EsterMKriegelH-PSanderJXuX.A density-based algorithm for discovering clusters in large spatial databases with noise. The Second International Conference on Knowledge Discovery and Data Mining (Portland, OR, USA, 1996), AAAI Press: New York, 226–231.
23.
SchikutaE.Grid-clustering: An efficient hierarchical clustering method for very large data sets. 13th Conference on Pattern Recognition, 1996, IEEE Computer Society Press: New York, 101–105.
24.
HinneburgAKeimDA. Optimal grid-clustering: towards breaking the curse of dimensionality in high-dimensional clustering. The 25th VLDB Conference (Edingburgh, Scotland, 1999), Morgan Kaufmann: Los Altos, CA, 506–517.
25.
AnkerstMBreunigMMKriegelH-PSanderJ.OPTICS: Ordering Points To Identify the Clustering Structure. ACM SIGMOD International Conference on Management of Data (Philadelphia, PA, USA, 1999), ACM Press: New York, 49–60.
GuoDGaheganMPeuquetDMacEachrenA.Breaking down dimensionality: an effective feature selection method for high-dimensional clustering. Workshop on Clustering High Dimensional Data and its Applications, the Third SIAM International Conference on Data Mining, May 1–3 (San Francisco, CA, U.S.A., 2003).
29.
PyleD.Data preparation for data mining. Morgan Kaufmann: Los Altos, CA, 1999, 540pp.
30.
SnedecorGWCochranWG. Statistical Methods. Iowa State University Press: IA, U.S.A.1989, 503pp.
31.
VandevDTsvetanovaGY. Perfect chains and single linkage clustering algorithm. Statistical Data Analysis, Proceedings SDA-95, 1995; 99–107.
32.
DudaROHartPEStorkDG. Pattern Classification. John Wiley & Sons: New York, 2001.
33.
GuoDPeuquetDGaheganM.Opening the black box: interactive hierarchical clustering for multivariate spatial patterns. The 10th ACM International Symposium on Advances in Geographic Information Systems (McLean, VA, USA, 2002), 131–136.
34.
ZhangTRamakrishnanRLivnyM.BIRCH: an efficient data clustering method for very large databases. ACM SIGMOD International Conference on Management of Data (Montreal, Canada, 1996), ACM Press: New York, 103–114.
35.
SzyperskiC.Component Software: Beyond Object-Oriented Programming. Addison-Wesley/ACM Press: New York, 1999, 589pp.
36.
GaheganMTakatsukaMWheelerMHardistyF.GeoVISTA Studio: a geocomputational workbench. 5th International Conference on GeoComputation, University of Greenwich (Medway Campus, U.K., 2000).
37.
GaheganMTakatsukaMWheelerMHardistyF.Introducing GeoVISTA Studio: An integrated suite of visualization and computational methods for exploration and knowledge construction in geography. Computers, Environment and Urban Systems2001; 26: 267–292.
38.
MacEachrenAMHardistyFGaheganMWheelerMDaiXGuoDTakatsukaM.Supporting visual integration and analysis of geospatiallyreferenced statistics through web-deployable, cross-platform tools. dg.o.2001, National Conference for Digital Government Research (Los Angeles, CA, 2001), 17–24.
39.
MacEachrenAMHardistyFDaiXPickleL.Supporting visual analysis of federal statistical summaries. Communications of the ACM2003; 46: 59–60.
40.
KullbackSLeiblerRA. On information and sufficiency. The Annals of Mathematical Statistics1951; 22: 79–86.
