Advertisement

Improving pattern discovery and visualisation with self-adaptive neural networks through data transformations

  • Huiru ZhengEmail author
  • Haiying Wang
Original Article

Abstract

The ability to reveal the relevant patterns in an intuitively attractive way through incremental learning makes self-adaptive neural networks (SANNs) a power tool to support pattern discovery and visualisation. Based on the combination of the information related to both the shape and magnitude of the data, this paper introduces a SANN, which implements new similarity matching criteria and error accumulation strategies for network growth. It was tested on two datasets including a real biological gene expression dataset. The results obtained have demonstrated several significant features exhibited by the proposed SANN model for improving pattern discovery and visualisation.

Keywords

Self-adaptive neural networks Pattern discovery and visualisation Similarity measure Chi-squares statistics 

References

  1. 1.
    Wang JTL, Shapiro BA, Shasha D (1999) Pattern discovery in biomolecular data: tools, techniques, and applications. Oxford University Press, New YorkGoogle Scholar
  2. 2.
    Shalizi CR, Crutchfield JP (2000) Pattern discovery and computational mechanics, Santa Fe Insitute Working Paper 00-01-008, Available at: arXiv.org/abs/cs.LG/0001027Google Scholar
  3. 3.
    Pleasance ED, Jones SJM (2005) Evaluation of SAGE tags for Ttranscriptome study. In: Wang SM (ed) SAGE: current technologies and applications, Horizon Scientific Press, Norwich, pp 1–27Google Scholar
  4. 4.
    Polyak K, Riggins GJ (2001) Gene discovery using the serial analysis of gene expression technique: implications for cancer research. J Clin Oncol 19(11):2948–2958Google Scholar
  5. 5.
    Brodlie KW, Carpenter LA, Earnshaw RA, Gallop JR, Hubbard RJ, Mumford AM, Osland CD, Quarendon P (eds) (1992) Scientific visualisation, techniques and applications, Springer, New YorkGoogle Scholar
  6. 6.
    Grinstein GG, Ward MO (2002) Introduction to data visualisation. In: Fayyad U, Grinstein GG, Wierse A (eds) Information visualisation in data mining and knowledge discovery, Morgan Kaufmann Publishers, San Francisco, pp 21–45Google Scholar
  7. 7.
    Wang HY (2004) Self-Adaptive Neural Network Approaches to Discovering, Visualising and Classifying Patterns in Semi-Structured and Structured Biomedical Data, PhD thesis, University of UlsterGoogle Scholar
  8. 8.
    Rezende S, Taborelli R, Félix L, Rocha A (1998) Visualisation for knowledge discovery in databases. In: Proceedings of the International Conference on Data Mining (ICDM’98), Rio de Janeiro, BrasilGoogle Scholar
  9. 9.
    Morik K, Wurst M (2002) Knowledge discovery and knowledge visualisation, In: Perspektiven vernetzter Wissensraeume, Workshop, Available at: http://www-ai.cs.uni-dortmund.de/DOKUMENTE/morik_wurst_2002a.pdf
  10. 10.
    Kohonen T (1995) Self-organising maps. Springer, HeidelbergCrossRefGoogle Scholar
  11. 11.
    Alahakoon D, Halgamuge SK, Srinivasan B (2000) Dynamic self-organising maps with controlled growth for knowledge discovery. IEEE Trans Neural Networks 11(3):601–614CrossRefGoogle Scholar
  12. 12.
    Wang H, Azuaje F, Black N (2004) An integrated and interactive framework for improving biomedical pattern discovery and visualization. IEEE Trans Inform Technol Biomed 8(1):16–27CrossRefGoogle Scholar
  13. 13.
    Fritzke B (1994) Growing cell structure–a self-organising network for unsupervised and supervised learning. Neural Netw 7:1441–1460CrossRefGoogle Scholar
  14. 14.
    Herrero J, Valencia A, Dopazo J (2001) A hierarchical unsupervised growing neural network for clustering gene expression patterns. Bioinformatics 17:126–136CrossRefGoogle Scholar
  15. 15.
    Kim K, Zhang S, Jiang K, Cai L, Lee I, Feldman L, Huang H (2007) Measuring similarities between gene expression profiles through new data transformations. BMC Bioinform 8:29Google Scholar
  16. 16.
    Zheng H, Wang H, Azuaje F (2008) Improving pattern discovery and visualization of SAGE data through poisson-based self-adaptive neural networks, IEEE Trans Inform Technol Biomed 12(4), pp 459–469Google Scholar
  17. 17.
    Tamayo P, Slonim D, Mesirov J, Zhu Q, Kitareewan S, Dmitrovsky E, Lander E, Golub T (1999) Interpreting patterns of gene expression with self-organising maps: methods and application to hematopoietic differentiation. In: Proc Natl Acad Sci USA 96:2907–2912Google Scholar
  18. 18.
    Fisher RA (1936) The use of multiple measurements in taxonomic problems. Annals of Eugenics VII:179–188Google Scholar
  19. 19.
    Blackshaw S, Harpavat S, Trimarchi J, Cai L, Huang H, Kuo W, Lee K, Fraioli R, Cho S, Yung R, Asch E, Wong W, Ohno-Machado L, Weber G, Cepko CL (2004) Genomic analysis of mouse retinal development. PLoS Biol 2(9)Google Scholar
  20. 20.
    Cai L, Huang H, Blackshaw S, Liu JS, Cepko C, Wong W (2004) Clustering analysis of SAGE data: a Poisson approach. Genome Biol 5:R51Google Scholar
  21. 21.
    Tavazoie S, Hughes JD, Campbell MJ, Cho RJ, Church GM (1999) “Systematic determination of genetic network architecture.” Nat Genet 22:281–285Google Scholar
  22. 22.
    Reed R (1993) “Pruning algorithms—a survey”. IEEE Trans Neural Netw 4(5):740–747CrossRefGoogle Scholar
  23. 23.
    Velculescu VE, Zhang L, Vogelstein B, Kinzler KW (1997) “Serial analysis of gene expression”. Science 276:1268–1272CrossRefGoogle Scholar
  24. 24.
    Grossberg S (1976) “Adaptive pattern classification and universal recoding: I. parallel development and coding of neural feature detectors”. Biol Cybern 23:121–134MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2011

Authors and Affiliations

  1. 1.School of Computing and Mathematics, Computer Science Research InstituteUniversity of UlsterCo. AntrimUK

Personalised recommendations