Skip to main content
Springer Nature Link
Log in

A Neuron Coverage-Based Self-organizing Approach for RBFNNs in Multi-class Classification Tasks

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2024 (ICANN 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15016))

Included in the following conference series:

  • 541 Accesses

Abstract

Radial Basis Function Neural Networks (RBFNN) constitute a distinct type of artificial neural network known for its unique architecture and ability to approximate complex functions, and as well lead to effective modeling in regression/classification tasks. Within the context of multi-class classification, this work introduces NC-SORBFNN as a self-organizing approach that adapts the structure of RBFNNs to the complexity of each task. NC-SORBFNN comprises an initialization step that makes use of a Self-Organizing Map (SOM) to give rise to a first set of hidden neurons that is next tuned by a self-adjustment process that goes through the data to make the network grow and shrink as required on the basis of the sample coverage of each neuron. The experimental results show the effectiveness of NC-SORBFNN, which in turn compares well with other similar solutions, leading in general to high performance for a low amount of hidden neurons.

This work has been partially supported by the EU-H2020 grant BUGWRIGHT2 (GA 871260) and by grant PID2022-139248NB-I00 (funded by MICIU/AEI/10.13039/501100011033 and by ERDF/EU). This publication reflects only the authors views and the EU is not liable for any use that may be made of the information contained therein.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Beltran-Perez, C., Wei, H.L., Rubio-Solis, A.: Generalized multiscale RBF networks and the DCT for breast cancer detection. Int. J. Autom. Comput. 17(1), 55–70 (2020)

    Article  Google Scholar 

  2. Chen, Z., Huang, F., Sun, W., Gu, J., Yao, B.: RBF-neural-network-based adaptive robust control for nonlinear bilateral teleoperation manipulators with uncertainty and time delay. IEEE Trans. Mechatron. 25(2), 906–918 (2020)

    Article  Google Scholar 

  3. Dachapak, C., Kanae, S., Yang, Z.J., Wada, K.: Orthogonal least squares for radial basis function network in reproducing Kernel Hilbert Space. IFAC Proceedings Volumes 37(12), 847–852 (2004)

    Article  Google Scholar 

  4. Dehuri, S., Jagadev, A.K., Cho, S.B.: Epileptic seizure identification from electroencephalography signal using DE-RBFNs ensemble. Procedia Comput. Sci. 23, 84–95 (2013)

    Article  Google Scholar 

  5. Fathi, V., Montazer, G.A.: An improvement in RBF learning algorithm based on PSO for real time applications. Neurocomputing 111, 169–176 (2013)

    Article  Google Scholar 

  6. Ferreira Cruz, D.P., Dourado Maia, R., 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)

    Article  Google Scholar 

  7. Ganapathy, K., Vaidehi, V., Chandrasekar, J.B.: Optimum steepest descent higher level learning radial basis function network. Expert Syst. Appl. 42(21), 8064–8077 (2015)

    Article  Google Scholar 

  8. Han, H.G., Li Chen, Q., Qiao, J.F.: An efficient self-organizing RBF neural network for water quality prediction. Neural Networks 24(7), 717–725 (2011)

    Google Scholar 

  9. Han, H.G., Guo, Y.N., Qiao, J.F.: Self-organization of a recurrent RBF neural network using an information-oriented algorithm. Neurocomputing 225, 80–91 (2017)

    Article  Google Scholar 

  10. Han, H.G., Lu, W., Hou, Y., Qiao, J.F.: An adaptive-PSO-based self-organizing RBF neural network. IEEE Trans. Neural Netw. Learn. 29(1), 104–117 (2018)

    Article  MathSciNet  Google Scholar 

  11. Han, H.G., Ma, M.L., Qiao, J.F.: Accelerated gradient algorithm for RBF neural network. Neurocomputing 441, 237–247 (2021)

    Article  Google Scholar 

  12. Han, H.G., Ma, M.L., Yang, H.Y., Qiao, J.F.: Self-organizing radial basis function neural network using accelerated second-order learning algorithm. Neurocomputing 469, 1–12 (2022)

    Article  Google Scholar 

  13. Han, H.G., Qiao, J.F.: A structure optimisation algorithm for feedforward neural network construction. Neurocomputing 99, 347–357 (2013)

    Article  Google Scholar 

  14. Han, H.G., Wang, L.D., Qiao, J.F.: Efficient self-organizing multilayer neural network for nonlinear system modeling. Neural Netw. 43, 22–32 (2013)

    Article  Google Scholar 

  15. Han, H.G., Wu, X., Zhang, L., Tian, Y., Qiao, J.F.: Self-organizing RBF neural network using an adaptive gradient multiobjective particle swarm optimization. IEEE Trans. Cybern. 49(1), 69–82 (2019)

    Article  Google Scholar 

  16. Hassanzadeh, Z., Kompany-Zareh, M., Ghavami, R., Gholami, S., Malek-Khatabi, A.: Combining radial basis function neural network with genetic algorithm to QSPR modeling of adsorption on multi-walled carbon nanotubes surface. J. Mol. Struct. 1098, 191–198 (2015)

    Article  Google Scholar 

  17. Henneron, T., Pierquin, A., Clénet, S.: Surrogate model based on the POD combined with the RBF interpolation of nonlinear magnetostatic FE model. IEEE Trans. Magn. 56(1), 1–4 (2020)

    Article  Google Scholar 

  18. Huang, G.B., Saratchandran, P., Sundararajan, N.: An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks. IEEE Trans. Syst. Man Cybern. B 34(6), 2284–2292 (2004)

    Article  Google Scholar 

  19. Huang, G.B., Saratchandran, P., Sundararajan, N.: A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans. Neural Networks 16(1), 57–67 (2005)

    Article  Google Scholar 

  20. Kashiwao, T., Nakayama, K., Ando, S., Ikeda, K., Lee, M., Bahadori, A.: A neural network-based local rainfall prediction system using meteorological data on the Internet: a case study using data from the Japan meteorological agency. Appl. Soft Comput. 56, 317–330 (2017)

    Article  Google Scholar 

  21. Keller, J.M., Liu, D., Fogel, D.B.: Fundamentals of Computational Intelligence: Neural Networks, Fuzzy Systems, and Evolutionary Computation. Wiley - IEEE Press, New York (2016)

    Google Scholar 

  22. Kim, J.S., Jung, S.: Implementation of the RBF neural chip with the back-propagation algorithm for on-line learning. Appl. Soft Comput. 29, 233–244 (2015)

    Article  Google Scholar 

  23. Kohonen, T.: Self-Organizing Maps, vol. 30 in Series in Information Sciences, 3rd edn. Springer, Cham (2001). https://doi.org/10.1007/978-3-642-56927-2

  24. Li, Z.Q., et al.: A proposed self-organizing radial basis function network for aero-engine thrust estimation. Aerosp. Sci. Technol. 87, 167–177 (2019)

    Article  Google Scholar 

  25. Liu, T., Chen, S., Liang, S., Gan, S., Harris, C.J.: Fast adaptive gradient RBF networks for online learning of nonstationary time series. IEEE Trans. Signal Process. 68, 2015–2030 (2020)

    Article  MathSciNet  Google Scholar 

  26. Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1(2), 281–294 (1989)

    Article  Google Scholar 

  27. Perez-Godoy, M.D., Rivera, A.J., Carmona, C.J., del Jesus, M.J.: Training algorithms for Radial Basis Function Networks to tackle learning processes with imbalanced data-sets. Appl. Soft Comput. 25, 26–39 (2014)

    Google Scholar 

  28. Shen, W., Guo, X., Wu, C., Wu, D.: Forecasting stock indices using radial basis function neural networks optimized by artificial fish swarm algorithm. Knowl.-Based Syst. 24(3), 378–385 (2011)

    Article  Google Scholar 

  29. Smith, J.S., Wu, B., Wilamowski, B.M.: Neural network training with Levenberg–Marquardt and adaptable weight compression. IEEE Trans. Neural Netw. Learn. 30(2), 580–587 (2019)

    Article  Google Scholar 

  30. Wang, S., Yao, X.: Multiclass imbalance problems: analysis and potential solutions. IEEE Trans. Syst. Man Cybern. B 42(4), 1119–1130 (2012)

    Article  Google Scholar 

  31. Wang, Y., Wang, T., Yang, X., Yang, J.: Gradient Descent-Barzilai Borwein-based neural network tracking control for nonlinear systems with unknown dynamics. IEEE Trans. Neural Netw. Learn. 34(1), 305–315 (2023)

    Article  MathSciNet  Google Scholar 

  32. Wu, J.C., Shen, J., Xu, M., Liu, F.S.: An evolutionary self-organizing cost-sensitive radial basis function neural network to deal with imbalanced data in medical diagnosis. Int. J. Comput. Intell. Syst. 13(1), 1608–1618 (2020)

    Article  Google Scholar 

  33. Xie, Y., Yu, J., Xie, S., Huang, T., Gui, W.: On-line prediction of ferrous ion concentration in goethite process based on self-adjusting structure RBF neural network. Neural Netw. 116, 1–10 (2019)

    Article  Google Scholar 

  34. Yang, Y., Wang, P., Gao, X.: A novel radial basis function neural network with high generalization performance for nonlinear process modelling. Processes 10(1), 140 (2022)

    Article  Google Scholar 

  35. Zhang, R., Huang, G.B., Sundararajan, N., Saratchandran, P.: Improved GAP-RBF network for classification problems. Neurocomputing 70(16), 3011–3018 (2007)

    Article  Google Scholar 

  36. Zhao, J., Wei, H., Zhang, C., Li, W., Guo, W., Zhang, K.: Natural gradient learning algorithms for RBF networks. Neural Comput. 27(2), 481–505 (2015)

    Article  MathSciNet  Google Scholar 

  37. Zheng, D., Jung, W., Kim, S.: RBFNN design based on modified nearest neighbor clustering algorithm for path tracking control. Sensors 21(24), 8349 (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics and Computer Science, University of the Balearic Islands (UIB), Palma, Spain

    Alberto Ortiz

  2. IDISBA (Health Research Institute of the Balearic Islands), Palma, Spain

    Alberto Ortiz

  3. IAIB (Artificial Intelligence Research Institute of the UIB), Palma, Spain

    Alberto Ortiz

Authors
  1. Alberto Ortiz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alberto Ortiz .

Editor information

Editors and Affiliations

  1. IDSIA USI-SUPSI, Lugano, Switzerland

    Michael Wand

  2. Comenius University, Bratislava, Slovakia

    Kristína Malinovská

  3. KAUST Center of Generative AI, Thuwal, Saudi Arabia

    Jürgen Schmidhuber

  4. Helmholtz Zentrum München, Neuherberg, Germany

    Igor V. Tetko

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ortiz, A. (2024). A Neuron Coverage-Based Self-organizing Approach for RBFNNs in Multi-class Classification Tasks. In: Wand, M., Malinovská, K., Schmidhuber, J., Tetko, I.V. (eds) Artificial Neural Networks and Machine Learning – ICANN 2024. ICANN 2024. Lecture Notes in Computer Science, vol 15016. Springer, Cham. https://doi.org/10.1007/978-3-031-72332-2_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72332-2_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72331-5

  • Online ISBN: 978-3-031-72332-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics