Advertisement

Applied Intelligence

, Volume 32, Issue 1, pp 27–46 | Cite as

Polynomial-based radial basis function neural networks (P-RBF NNs) and their application to pattern classification

Article

Abstract

Polynomial neural networks have been known to exhibit useful properties as classifiers and universal approximators. In this study, we introduce a concept of polynomial-based radial basis function neural networks (P-RBF NNs), present a design methodology and show the use of the networks in classification problems. From the conceptual standpoint, the classifiers of this form can be expressed as a collection of “if-then” rules. The proposed architecture uses two essential development mechanisms. Fuzzy clustering (Fuzzy C-Means, FCM) is aimed at the development of condition parts of the rules while the corresponding conclusions of the rules are formed by some polynomials. A detailed learning algorithm for the P-RBF NNs is developed. The proposed classifier is applied to two-class pattern classification problems. The performance of this classifier is contrasted with the results produced by the “standard” RBF neural networks. In addition, the experimental application covers a comparative analysis including several previous commonly encountered methods such as standard neural networks, SVM, SOM, PCA, LDA, C4.5, and decision trees. The experimental results reveal that the proposed approach comes with a simpler structure of the classifier and better prediction capabilities.

Keywords

Polynomial neural networks Radial basis function neural networks Pattern classification Fuzzy clustering Two-class discrimination 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jain AK, Duin PW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–37. doi: 10.1109/34.824819 CrossRefGoogle Scholar
  2. 2.
    Liu C-L, Sako H (2006) Class-specific feature polynomial classifier for pattern classification and its application to handwritten numeral recognition. Pattern Recognit 39:669–681. doi: 10.1016/j.patcog.2005.04.021 MATHCrossRefGoogle Scholar
  3. 3.
    Hinton GE, Dayan P, Revow M (1997) Modeling the manifolds of images of handwritten digits. IEEE Trans Neural Netw 8(1):65–74. doi: 10.1109/72.554192 CrossRefGoogle Scholar
  4. 4.
    Kreßel U, Schurmann J (1997) Pattern classification techniques based on function approximation. In: Bunke H, Wang PSP (eds) Handbook of character recognition and document image analysis. World Scientific, Singapore, pp 49–78 Google Scholar
  5. 5.
    Shurmann J (1996) Pattern classification: a unified view of statistical and neural approaches. Wiley Interscience, New York Google Scholar
  6. 6.
    Holmstrom L, Koistinen P, Laaksonen J, Oja E (1997) Neural and statistical classifiers-taxonomy and two case studies. IEEE Trans Neural Netw 8(1):5–17. doi: 10.1109/72.554187 CrossRefGoogle Scholar
  7. 7.
    Lippman RP (1981) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22 CrossRefGoogle Scholar
  8. 8.
    Patrikar A, Provence J (1992) Pattern classification using polynomial networks. Electron Lett 28(12):1109–1110. doi: 10.1049/el:19920700 CrossRefGoogle Scholar
  9. 9.
    Ros F, Pintore M, Chretien JR (2007) Automatic design of growing radial basis function neural networks based on neighborhood concepts. Chemom Intell Lab Syst 87:231–240. doi: 10.1016/j.chemolab.2007.02.003 CrossRefGoogle Scholar
  10. 10.
    Sarimveis H, Doganis P, Alexandridis A (2006) A classification technique based on radial basis function neural networks. Adv Eng Softw 37:218–221. doi: 10.1016/j.advengsoft.2005.07.005 CrossRefGoogle Scholar
  11. 11.
    Er MJ, Wu SQ, Lu JW, Toh HL (2002) Face recognition with radical basis function (RBF) neural networks. IEEE Trans Neural Netw 13(5):697–710 Google Scholar
  12. 12.
    Jing X-Y, Yao Y-F, Zhang D, Yang J-Y, Li M (2007) Face and palmprint pixel level fusion and Kernel DCV-RBF classifier for small sample biometric recognition. Pattern Recognit 40:3209–3224. doi: 10.1016/j.patcog.2007.01.034 MATHCrossRefGoogle Scholar
  13. 13.
    Campbell WM, Assaleh KT, Broun CC (2002) Speaker recognition with polynomial classifiers. IEEE Trans Speech Audio Process 10(4):205–212. doi: 10.1109/TSA.2002.1011533 CrossRefGoogle Scholar
  14. 14.
    Giles GL, Maxwell T (1987) Learning, invariance, and generalization in high-order neural networks. Appl Opt 26(23):4972–4978 CrossRefGoogle Scholar
  15. 15.
    Pao YH (1989) Adaptive pattern recognition and neural networks. Addison–Wesley, Reading MATHGoogle Scholar
  16. 16.
    Pao YH, Phillips SM (1995) The functional link and learning optimal control. Neurocomputing 9:149–164. doi: 10.1016/0925-2312(95)00066-F MATHCrossRefGoogle Scholar
  17. 17.
    Philip Chen CL, LeClair SR, Pao YH (1998) An incremental adaptive implementation of functional-link processing for function approximation, time-series prediction, and system identification. Neurocomputing 18:11–31. doi: 10.1016/S0925-2312(97)00062-3 CrossRefGoogle Scholar
  18. 18.
    Al-Assaf Y, El Kadi H (2007) Fatigue life prediction of composite materials using polynomial classifiers and recurrent neural networks. Compos Struct 77:561–569. doi: 10.1016/j.compstruct.2005.08.012 CrossRefGoogle Scholar
  19. 19.
    Zhang C, Jiang J, Kamel M (2005) Intrusion detection using hierarchical neural networks. Pattern Recognit Lett 26:779–791. doi: 10.1016/j.patrec.2004.09.045 CrossRefGoogle Scholar
  20. 20.
    Staiano A, Tagliaferri R, Pedrycz W (2006) Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering. Neurocomputing 69:1570–1581. doi: 10.1016/j.neucom.2005.06.014 CrossRefGoogle Scholar
  21. 21.
    Aiyer A, Pyun K, Huang YZ, O’Brien DB, Gray RM (2005) Lloyd clustering of Gauss mixture models for image compression and classification. Signal Process Image Commun 20:459–485. doi: 10.1016/j.image.2005.03.003 CrossRefGoogle Scholar
  22. 22.
    Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New York MATHGoogle Scholar
  23. 23.
    Nikolaev N, Iba H (2002) Genetic programming of polynomial models for financial forecasting. In: Chen S-H (ed) Genetic algorithms and genetic programming in computational finance. Kluwer Academic, Boston, pp 103–123 Google Scholar
  24. 24.
    Janczak A (2005) Identification of nonlinear systems using neural networks and polynomial models: a block-oriented approach. In: Lecture notes in control and information sciences. Springer, New York, pp 1–30 Google Scholar
  25. 25.
    Oh S-K, Pderycz W, Park B-J (2004) Self-organizing neurofuzzy networks in modeling software data. Fuzzy Sets Syst 145:165–181. doi: 10.1016/j.fss.2003.10.009 CrossRefGoogle Scholar
  26. 26.
    Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley-Interscience, New York Google Scholar
  27. 27.
    Munoz-Exposito JE, Garcia-Galan S, Ruiz-Reyes N, Vera-Candeas P (2007) Adaptive network-based fuzzy inference system vs. other classification algorithms for warped LPC-based speech/music discrimination. Eng Appl Artif Intell 20:783–793. doi: 10.1016/j.engappai.2006.10.007 CrossRefGoogle Scholar
  28. 28.
    Bugmann G (1998) Classification using networks of normalized radial basis functions. In: Proceedings of international conference on advances in pattern recognition (ICAPR’98), pp 435–444 Google Scholar
  29. 29.
    Phatak DS, Koren I (1994) Connectivity and performance tradeoffs in the cascade correlation learning architecture. IEEE Trans Neural Netw 5(6):930–935. doi: 10.1109/72.329690 CrossRefGoogle Scholar
  30. 30.
    Simpson PK (1993) Fuzzy min-max neural networks, Part 2: clustering. IEEE Trans Fuzzy Syst 1(1):32–45. doi: 10.1109/TFUZZ.1993.390282 CrossRefGoogle Scholar
  31. 31.
    Zhang X, Dong G, Ramamohanarao K (2000) Information-based classification by aggregating emerging patterns. Lect Notes Comput Sci 1983:48–53 CrossRefGoogle Scholar
  32. 32.
    Lin Z, Weng S, Zhang C, Lu N, Xia Z (2004) Learning the supervised NLDR mapping for classification. Lect Notes Comput Sci 3173:900–905 Google Scholar
  33. 33.
    Li T, Zhu S, Ogihara M (2003) Using discriminant analysis for multi-class classification. In: Third IEEE international conference on data mining, pp 589–592 Google Scholar
  34. 34.
    Dzeroski S, Zenko B (2002) Stacking with multi-response model trees. In: Proceedings of the third international workshop on multiple classifier systems, pp 201–211 Google Scholar
  35. 35.
    Tahir MA, Bouridane A, Kurugollu F (2007) Simultaneous feature selection and feature weighting using hybrid tabu Search/k-nearest neighbor classifier. Pattern Recognit Lett 28:438–446. doi: 10.1016/j.patrec.2006.08.016 CrossRefGoogle Scholar
  36. 36.
    Perez-Jimenez AJ, Perez-Cortes JC (2006) Genetic algorithms for linear feature extraction. Pattern Recognit Lett 27:1508–1514. doi: 10.1016/j.patrec.2006.02.011 CrossRefGoogle Scholar
  37. 37.
    Mu T, Nandi AK (2007) Breast cancer detection from FNA using SVM with different parameter tuning systems and SOM–RBF classifier. J Franklin Inst 344:285–311. doi: 10.1016/j.jfranklin.2006.09.005 MATHCrossRefMathSciNetGoogle Scholar
  38. 38.
    Ho SY, Chen HM, Ho SJ, Chen TK (2004) Design of accurate classifiers with a compact fuzzy-rule base using an evolutionary scatter partition of feature space. IEEE Trans Syst Man Cybern B 34(2):1031–1044 CrossRefGoogle Scholar
  39. 39.
    Lam W, Keung C, Ling CX (2002) Learning good prototypes for classification using filtering and abstraction of instances. Pattern Recognit 35(7):1491–1506. doi: 10.1016/S0031-3203(01)00131-5 MATHCrossRefGoogle Scholar
  40. 40.
    Rocha M, Cortez P, Neves J (2005) Simultaneous evolution of neural network topologies and weights for classification and regression. Lect Notes Comput Sci 3512:59–66 Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Byoung-Jun Park
    • 1
  • Witold Pedrycz
    • 2
    • 3
  • Sung-Kwun Oh
    • 4
  1. 1.Telematics & USN Research DepartmentElectronics and Telecommunications Research Institute (ETRI)DaejeonSouth Korea
  2. 2.Department of Electrical & Computer EngineeringUniversity of AlbertaEdmontonCanada
  3. 3.Systems Science InstitutePolish Academy of SciencesWarsawPoland
  4. 4.Department of Electrical EngineeringUniversity of SuwonGyeonggi-doSouth Korea

Personalised recommendations