Skip to main content

Interactive visualization in multiclass learning: integrating the SASSC algorithm with KLIMT


The paper deals with multiclass learning from the perspective of analytically interpreting the results of the analysis as well as that of navigating into them by using interactive visualization tools. It is showed that by combining the Sequential Automatic Search of Subset of Classifiers (SASSC) algorithm with the interactive visualization of classification trees provided by the Klassification—Interactive Methods for Trees (KLIMT) software it is possible to highlight important information deriving from the knowledge extraction process without neglecting the prediction accuracy of the classification method. Empirical evidence from two benchmark datasets demonstrates the advantages deriving from the joint use of SASSC and KLIMT.

This is a preview of subscription content, access via your institution.


  • Asuncion A, Newman DJ (2007) UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences.

  • Benabdeslem K, Bennani Y (2006) Dendogram-based SVM for multi-class classification. J Comput Inf Technol 14: 5–32

    Google Scholar 

  • Brand M (1998) Pattern discovery via entropy minimization. In: Heckerman D, Whittaker J (eds) Proceedings of the seventh international workshop on artificial intelligence and statistics. Morgan Kaufmann Publishers Inc, San Francisco, CA.

  • Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth, Belmont

    MATH  Google Scholar 

  • Conversano C, Mola F (2010) Detecting subset of classifiers for multi-attribute response prediction. In: Lauro CN, Greenacre MJ, Palumbo F (eds) Studies in classification, data analysis, and knowledge organization. Springer, Berlin-Heidelberg, pp 225–232

    Google Scholar 

  • Cutzu F (2003) Polychotomous classification with pairwise classifiers: a new voting principle In: Windeatt T, Roli F (eds) Multiple classifier system, Proceedings of the fourth international workshop MCS 2003. Springer, New York, pp 115–124

  • Deterding DH (1988) Speaker normalisation for automatic speech recognition. PhD thesis, University of Cambridge, Cambridge

  • Dietterich TG, Bakiri G (1995) Solving multi-classlearning problems via error-correcting output codes. J Artif Intell Res 2: 263–286

    MATH  Google Scholar 

  • Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New York

    MATH  Google Scholar 

  • Fogarty T (1992) First nearest neighbour classification on Frey and Slate’s letter recognition problem (technical note). Mach Learn 9: 387–388

    Google Scholar 

  • Frey PW, Slate DJ (1991) Letter recognition using Holland-style adaptive classifiers. Mach Learn 6: 161–182

    Google Scholar 

  • Furnkranz J (2002) Round robin classification. J Mach Learn Res 2: 721–747

    MathSciNet  Google Scholar 

  • Hastie TJ, Friedman J, Tibshirani RJ (2001) The elements of statistical learning. Springer, New York

    MATH  Google Scholar 

  • Hastie TJ, Tibshirani RJ (1998) Classification by pairwise coupling. Ann Stat 26(1): 451–478

    MathSciNet  MATH  Google Scholar 

  • Hoffman H (2008) Mosaic plots and their variants. In: Chen C, Hardle W, Unwin A (eds) Handbook of data visualization. Springer, Berlin-Heidelberg, pp 617–642

    Chapter  Google Scholar 

  • Hummel J (1996) Linked bar charts: analysing categorical data graphically. Comput Stat 11: 36–44

    Google Scholar 

  • Inselberg A (1998) Visual data mining with parallel coordinates. Comput Stat 53(1): 47–63

    Google Scholar 

  • Mola F, Conversano C (2008) Sequential automatic search of a subset of classifiers in multiclass learning. In: Brito P (ed) Compstat 2008 Proceedings in computational statistics. Springer, Berlin, pp 291–302

  • Paradis E (2006) Analysis of phylogenetics and evolution with R. Springer, New York

    MATH  Google Scholar 

  • R Development Core Team (2009) R: A language and environment for statistical computing. R Foundation for statistical computing. Vienna, Austria.

  • Rabiner LR, Schafer RW (1978) Difital processing of speech signals. Prentice Hall, Englewood Cliffs New Jersey

    Google Scholar 

  • Ripley B (2009) Tree: classification and regression trees. R package version 1.0-27.

  • Therneau TM, Atkinson B (2009) Rpart: recursive partitioning, R package version 3.1-45.

  • Urbanek S (2002) Different ways to see a tree—KLIMT. In: Haerdle W, Ronz B (eds) Compstat 2002 proceedings in computational statistics. Springer, Berlin-Heidelberg, pp 303–308

  • Urbanek S (2006) Trees. In: Unwin A, Theus M, Hofmann H (eds) Graphics of large datasets. Springer, New York, pp 177–202

    Chapter  Google Scholar 

  • Urbanek S (2008) Visualising trees and forests. In: Chen C, Hardle W, Unwin A (eds) Handbook of data visualization. Springer, Berlin-Heidelberg, pp 252–264

    Google Scholar 

  • Urbanek S, Unwin A (2002) Making trees interactive with KLIMT—a COSADA software project. Stat Comp Graphi Newsl 13(1): 13–16

    Google Scholar 

  • Urbanek S, Wichtrey T (2009) Iplots: iPlots—interactive graphics for R, R package version 1.1-3.

  • Weston J, Herbich R (2000) Adaptive margin support vector machines. In: Smola AJ, Bartlett PL, Scholkopf B, Schuurmans D (eds) Advances in large margin classifiers. MIT press, Cambridge, pp 281–295

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Claudio Conversano.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Conversano, C. Interactive visualization in multiclass learning: integrating the SASSC algorithm with KLIMT. Comput Stat 26, 711 (2011).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI:


  • Classification
  • Multiclass response
  • Subset selection
  • Semi-supervised learning
  • CART
  • Phylogenetic tree
  • Interactive visualization