Advertisement

Review on RBFNN Design Approaches: A Case Study on Diabetes Data

  • Ramalingaswamy Cheruku
  • Diwakar Tripathi
  • Y. Narasimha Reddy
  • Sathya Prakash Racharla
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 705)

Abstract

Radial Basis Function Neural Networks (RBFNNs) are more powerful machine learning technique as it requires non-iterative training. However, the hidden layer of RBFNN grows on par with the growing dataset size. This results in increase in network complexity, training time, and testing times. It is desirable to design appropriate RBFNN which balance between simplicity and accuracy. In the literature, many approaches are proposed for reducing the neurons in the RBFNN hidden layer. In this paper, a comprehensive survey is performed on hidden layer reduction techniques with respect to Pima Indians Diabetes (PID) dataset.

Keywords

Diabetes mellitus RBFNN Hidden layer size RBFNN Design Hidden layer reduction 

References

  1. 1.
    Cheruku, R., Edla, D.R., Kuppili, V.: Sm-ruleminer: spider monkey based rule miner using novel fitness function for diabetes classification. Comput. Biol. Med. 81, 79–92 (2017)CrossRefGoogle Scholar
  2. 2.
    Cheruku, R., Edla, D.R., Kuppili, V., Dharavath, R.: Rst-batminer: a fuzzy rule miner integrating rough set feature selection and bat optimization for detection of diabetes disease. Appl. Soft Comput. (2017)Google Scholar
  3. 3.
    WHO: World Health Organization. http://www.who.int/diabetes/action_online/basics/en/. Accessed 30 Sept 2016
  4. 4.
    Lichman, M.: UCI machine learning repository (2013). http://archive.ics.uci.edu/ml
  5. 5.
    Broomhead, D.S., Lowe, D.: Radial Basis Functions, Multi-variable Functional Interpolation and Adaptive Networks, Tech. rep. Royal Signals and Radar Establishment, Malvern (United Kingdom) (1988)Google Scholar
  6. 6.
    Yegnanarayana, B.: Artificial neural networks. PHI Learning Pvt. Ltd. (2009)Google Scholar
  7. 7.
    Cruz, D.P.F., Maia, R.D., da Silva, L.A., de Castro, L.N.: Beerbf: a bee-inspired data clustering approach to design RBF neural network classifiers. Neurocomputing 172, 427–437 (2016)CrossRefGoogle Scholar
  8. 8.
    Cheruku, R., Edla, D.R., Kuppili, V.: Diabetes classification using radial basis function network by combining cluster validity index and bat optimization with novel fitness function. Int. J. Comput. Intell. Syst. 10(1), 241–265 (2017).  https://doi.org/10.2991/ijcis.2017.10.1.17CrossRefGoogle Scholar
  9. 9.
    Hartigan, J.A., Wong, M.A.: Algorithm as 136: a k-means clustering algorithm. J. R. Stat. Soc. Ser. C (Appl. Stat.) 28(1), 100–108 (1979)zbMATHGoogle Scholar
  10. 10.
    Shen, J., Chang, S.I., Lee, E.S., Deng, Y., Brown, S.J.: Determination of cluster number in clustering microarray data. Appl. Math. Comput. 169(2), 1172–1185 (2005)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Qasem, S.N., Shamsuddin, S.M.: Radial basis function network based on time variant multi-objective particle swarm optimization for medical diseases diagnosis. Appl. Soft Comput. 11(1), 1427–1438 (2011)CrossRefGoogle Scholar
  12. 12.
    Qasem, S.N., Shamsuddin, S.M., Zain, A.M.: Multi-objective hybrid evolutionary algorithms for radial basis function neural network design. Knowl. Based Syst. 27, 475–497 (2012)CrossRefGoogle Scholar
  13. 13.
    Goh, C.K., Teoh, E.J., Tan, K.C.: Hybrid multiobjective evolutionary design for artificial neural networks. IEEE Trans. Neural Netw. 19(9), 1531–1548 (2008)CrossRefGoogle Scholar
  14. 14.
    Abbass, H.A.: Speeding up backpropagation using multiobjective evolutionary algorithms. Neural Comput. 15(11), 2705–2726 (2003)CrossRefGoogle Scholar
  15. 15.
    Garcıa-Pedrajas, N., Hervás-Martınez, C., Munoz-Pérez, J.: Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks). Neural Netw. 15(10), 1259–1278 (2002)CrossRefGoogle Scholar
  16. 16.
    Paetz, J.: Reducing the number of neurons in radial basis function networks with dynamic decay adjustment. Neurocomputing 62, 79–91 (2004)CrossRefGoogle Scholar
  17. 17.
    Oliveira, A.L., Melo, B.J., Meira, S.R.: Improving constructive training of RBF networks through selective pruning and model selection. Neurocomputing 64, 537–541 (2005)CrossRefGoogle Scholar
  18. 18.
    Cheruku, R., Edla, D.R., Kuppili, V., Dharavath, R.: Pso-rbfnn: a pso-based clustering approach for rbfnn design to classify disease data. In: International Conference on Artificial Neural Networks. Springer (2017).  https://doi.org/10.1007/978-3-319-68612-729
  19. 19.
    Edla, D.R., Cheruku, R.: Diabetes-finder: a bat optimized classification system for type-2 diabetes. Procedia Comput. Sci. 115c, 235–242 (2017)CrossRefGoogle Scholar
  20. 20.
    Ded, K., Pratap, A., Agarwal, S., et al.: A fast and elitist multi-objective genetic algorithm: Nsga2. IEEE Trans. Evolut. Comput. 6(2), 149–172 (2002)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Ramalingaswamy Cheruku
    • 1
  • Diwakar Tripathi
    • 1
  • Y. Narasimha Reddy
    • 2
  • Sathya Prakash Racharla
    • 3
  1. 1.Department of Computer Science and EngineeringNational Institute of Technology GoaPondaIndia
  2. 2.Department of CSEBrindavan Institute of Technology and ScienceKurnoolIndia
  3. 3.Department of CSECVR College of EngineeringHyderabadIndia

Personalised recommendations