Skip to main content
Springer Nature Link
Log in

Hyperparameter Optimization of Evolving Spiking Neural Network for Time-Series Classification

  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

Spiking neural networks are the third generation of artificial neural networks that are inspired by a new brain-inspired computational model of ANN. Spiking neural network encodes and processes neural information through precisely timed spike trains. eSNN is an enhanced version of SNN, motivated by the principles of Evolving Connectionist System (ECoS), which is relatively a new classifier in the neural information processing area. The performance of eSNN is highly influenced by the values of its significant hyperparameters’ modulation factor (mod), threshold factor (c), and similarity factor (sim). In contrast to the manual tuning of hyperparameters, automated tuning is more reliable. Therefore, this research presents an optimizer-based eSNN architecture, intended to solve the issue regarding optimum hyperparameters’ values’ selection of eSNN. The proposed model is named eSNN-SSA where SSA stands for salp swarm algorithm, which is a metaheuristic optimization technique integrated with eSNN architecture. For the integration of eSNN-SSA, Thorpe’s standard model of eSNN is used with population rate encoding. To examine the performance of eSNN-SSA, various benchmarking data sets from the UCR/UAE time-series classification repository are utilized. From the experimental results, it is concluded that the salp swarm algorithm plays an effective role in improving the flexibility of the eSNN. The proposed eSNN-SSA offers solutions to conquer the disadvantages of eSNN in determining the best number of pre-synaptic neurons for time-series classification problems. The performance accuracy obtained by eSNN-SSA was on datasets spoken Arabic digits, articulatory word recognition, character trajectories, wafer, and GunPoint, i.e., 0.96, 0.97, 0.94, 1.0, and 0.94, respectively. The proposed approach outperformed standard eSNN in terms of time complexity.

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

Access this article

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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Availability of Data and Materials (Data Transparency)

Not applicable.

References

  1. Basu, J.K., Bhattacharyya, D., Kim, T.: Use of artificial neural network in pattern recognition. Int. J. Soft. Eng. Appl. 4(2) (2010)

  2. Zainuddin, Z., Ong, P.: Function approximation using artificial neural networks. WSEAS Trans. Math. 7(6), 333–338 (2008)

    MathSciNet  Google Scholar 

  3. Beskopylny, A., Lyapin, A., Anysz, H., Meskhi, B., Veremeenko, A., Mozgovoy, A.: Artificial neural networks in classification of steel grades based on non-destructive tests. Materials (Basel) 13(11), 2445 (2020)

    Article  Google Scholar 

  4. Heo, S., Lee, J.H.: Fault detection and classification using artificial neural networks. IFAC-PapersOnLine 51(18), 470–475 (2018)

    Article  Google Scholar 

  5. Hagan, M.T., Demuth, H.B., Beale, M.: Neural Network Design. PWS Publishing Co., Boston (1997)

    Google Scholar 

  6. Vreeken, J.: Spiking Neural Networks, an Introduction. Utrecht University Information and Computing Sciences, Utrecht (2003)

    Google Scholar 

  7. Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)

    Article  Google Scholar 

  8. Doborjeh, Z., et al.: Spiking neural network modelling approach reveals how mindfulness training rewires the brain. Sci. Rep. 9(1), 6367 (2019). https://doi.org/10.1038/s41598-019-42863-x

    Article  Google Scholar 

  9. Ahmed, F.Y., Yusob, B., Hamed, H.N.A.: Computing with spiking neuron networks: a review. Int. J. Adv. Soft. Comput. Appl. 6(1) (2014)

  10. Agebure, M.A., Wumnaya, P.A., Baagyere, E.Y.: A survey of supervised learning models for spiking neural network. Networks 5 (2021)

  11. Holland, J.H.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. MIT Press, Cambridge (1992)

    Book  Google Scholar 

  12. Kasabov, N.K.: The ECOS framework and the ECO learning method for evolving connectionist systems. J. Adv. Comput. Intell. Intell. Inform. 2(6), 195–202 (1998)

    Article  Google Scholar 

  13. Saleh, A.Y., Hameed, H., Najib, M., Salleh, M.: A novel hybrid algorithm of differential evolution with evolving spiking neural network for pre-synaptic neurons optimization. Int. J. Adv. Soft Comput. Appl 6(1), 1–16 (2014)

    Google Scholar 

  14. Abdull Hamed, H.N.: Novel integrated methods of evolving spiking neural network and particle swarm optimisation. Auckland University of Technology, Auckland (2012)

    Google Scholar 

  15. Kennedy, J.: Swarm intelligence. In: Handbook of nature-inspired and innovative computing, pp. 187–219. Springer, Berlin (2006)

    Chapter  Google Scholar 

  16. Anderson, P.A.V., Bone, Q.: Communication between individuals in salp chains. II. Physiology. Proc. R. Soc. London. Ser. B. Biol. Sci. 210(1181), 559–574 (1980)

    Google Scholar 

  17. Ruiz, A.P., Flynn, M., Large, J., Middlehurst, M., Bagnall, A.: The great multivariate time-series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Discov. 35(2), 401–449 (2021)

    Article  MathSciNet  Google Scholar 

  18. Roslan, F., Hamed, H.N.A., Isa, M.A.: The enhancement of evolving spiking neural network with firefly algorithm. J. Telecommun. Electron. Comput. Eng. 9(3–3), 63–66 (2017)

    Google Scholar 

  19. Yusuf, Z.M., Hamed, H.N.A., Yusuf, L.M., Isa, M.A.: Evolving spiking neural network (ESNN) and harmony search algorithm (HSA) for parameter optimization. In: 2017 6th International Conference on Electrical Engineering and Informatics (ICEEI), pp. 1–6 (2017)

  20. Saleh, A.Y., Shamsuddin, S.M., Hamed, H.N.A., Siong, T.C., Othman, M.K.: A new harmony search algorithm with evolving spiking neural network for classification problems. J. Telecommun. Electron. Comput. Eng. 9(3–11), 23–26 (2017)

    Google Scholar 

  21. Saleh, A.Y., Shamsuddin, S.M., Hamed, H.N.A.: Multi-objective differential evolution of evolving spiking neural networks for classification problems. In: IFIP International Conference on Artificial Intelligence Applications and Innovations, pp. 351–368 (2015)

  22. John, G.H., Kohavi, R., Pfleger, K.: Irrelevant features and the subset selection problem. In: Machine Learning Proceedings 1994. Elsevier, pp. 121–129 (1994)

  23. Hamed, H.N.A., Saleh, A.Y., Shamsuddin, S.M., Ibrahim, A.O.: Multi-objective K-means evolving spiking neural network model based on differential evolution. In: 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE), pp. 379–383 (2015)

  24. Saleh, A.Y., Shamsuddin, S.M., Hamed, H.N.A.: Memetic harmony search algorithm based on multi-objective differential evolution of evolving spiking neural networks. Int. J. Swarm Intel. Evol. Comput. 5(130), 2 (2016)

    Google Scholar 

  25. Saleh, A.Y., Hamed, H.N.B.A., Shamsuddin, S.M., Ibrahim, A.O.: A new hybrid k-means evolving spiking neural network model based on differential evolution. In: International Conference of Reliable Information and Communication Technology, pp. 571–583 (2017)

  26. Bohte, S.M., Kok, J.N., La Poutre, H.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1–4), 17–37 (2002)

    Article  Google Scholar 

  27. Séguier, R., Mercier, D.: Audio-visual speech recognition one pass learning with spiking neurons. In: International Conference on Artificial Neural Networks, pp. 1207–1212 (2002)

  28. Kasabov, N.K.: Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence. Springer, Berlin (2019)

    Book  Google Scholar 

  29. Kasabov, N.: Integrative connectionist learning systems inspired by nature: current models, future trends and challenges. Nat. Comput. 8(2), 199–218 (2009)

    Article  MathSciNet  Google Scholar 

  30. Schliebs, S., Kasabov, N.: Computational modeling with spiking neural networks, pp. 625–646. Springer Handb. Bio-/neuroinformatics, Berlin (2014)

    Google Scholar 

  31. Mirjalili, S., Gandomi, A.H., Mirjalili, S.Z., Saremi, S., Faris, H., Mirjalili, S.M.: Salp swarm algorithm: a bio-inspired optimizer for engineering design problems. Adv. Eng. Softw. 114, 163–191 (2017)

    Article  Google Scholar 

  32. Abualigah, L., Shehab, M., Alshinwan, M., Alabool, H.: Salp swarm algorithm: a comprehensive survey. Neural Comput. Appl. 32(15), 11195–11215 (2020)

    Article  Google Scholar 

  33. Ibrahim, R.A., Ewees, A.A., Oliva, D., Abd Elaziz, M., Lu, S.: Improved salp swarm algorithm based on particle swarm optimization for feature selection. J. Ambient Intell. Humaniz. Comput. 10(8), 3155–3169 (2019)

    Article  Google Scholar 

  34. Hamed, H.N.A., Kasabov, N., Shamsuddin, S.M.: Integrated feature selection and parameter optimization for evolving spiking neural networks using quantum inspired particle swarm optimization. In: 2009 International Conference of Soft Computing and Pattern Recognition, pp. 695–698 (2009)

  35. Dau, H.A., et al.: The UCR time-series archive. IEEE/CAA J. Autom. Sin. 6(6), 1293–1305 (2019)

    Article  Google Scholar 

  36. Forrester, A., Sobester, A., Keane, A.: Engineering design via surrogate modelling: a practical guide. Wiley, New York (2008)

    Book  Google Scholar 

  37. Al-Tashi, Q., Rais, H., Jadid Abdulkadir, S., Mirjalili, S.: Feature selection based on grey wolf optimizer for oil and gas reservoir classification. In: 2020 International Conference on Computational Intelligence (ICCI). IEEE, pp. 211–216 (2020)

  38. Ren, H., Li, J., Chen, H., Li, C.: Adaptive levy-assisted salp swarm algorithm: analysis and optimization case studies. Math. Comput. Simul. 181, 380–409 (2021)

    Article  MathSciNet  Google Scholar 

  39. Ragab, M.G., Abdulkadir, S.J., Aziz, N., Al-Tashi, Q., Alyousifi, Y., Alhussian, H., Alqushaibi, A.: A novel one-dimensional CNN with exponential adaptive gradients for air pollution index prediction. Sustainability. 12(23), 10090 (2020). https://doi.org/10.3390/su122310090

    Article  Google Scholar 

  40. Abdulkadir, S.J., Shamsuddin, S.M., Sallehuddin, R.: Three term back propagation network for moisture prediction. In: International Conference on Clean and Green Energy, pp. 103–107 (2012)

  41. Abdulkadir, S.J., Alhussian, H., Alzahrani, A.I.: Analysis of recurrent neural networks for henon simulated time-series forecasting. J. Telecommun. Electron. Comput. Eng. 10(1–8), 155–159 (2018)

    Google Scholar 

  42. Alhussian, H., Zakaria, N., Patel, A., Jaradat, A., Abdulkadir, S.J., Ahmed, A.Y., Bahbouh, H.T., Fageeri, S.O., Elsheikh, A.A., Watada, J.: Investigating the schedulability of periodic real-time tasks in virtualized cloud environment. IEEE Access 7, 29533–29542 (2019)

    Article  Google Scholar 

  43. Aman, M., Said, A.B.M., Kadir, S.J.A., Ullah, I.: Key concept identification: a sentence parse tree-based technique for candidate feature extraction from unstructured texts. IEEE Access 6, 60403–60413 (2018)

    Article  Google Scholar 

  44. Abdulkadir, S.J., Yong, S.-P.: Lorenz time-series analysis using a scaled hybrid model. In: 2015 International Symposium on Mathematical Sciences and Computing Research (iSMSC). IEEE, pp. 373–378 (2015)

Download references

Acknowledgements

We are thankful to the Editor and the reviewers for their valuable suggestions and remarks, which significantly enhanced the quality of the manuscript.

Funding

This research was supported by Universiti Teknologi PETRONAS, under the Yayasan Universiti Teknologi PETRONAS (YUTP) Fundamental Research Grant Scheme (YUTPFRG/015LC0-308).

Author information

Authors and Affiliations

  1. Computer Information Science Department, Universiti Teknologi PETRONAS, Seri Iskandar, Perak, Malaysia

    Tasbiha Ibad, Said Jadid Abdulkadir, Norshakirah Aziz, Mohammed Gamal Ragab & Qasem Al-Tashi

Authors
  1. Tasbiha Ibad
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Said Jadid Abdulkadir
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Norshakirah Aziz
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Mohammed Gamal Ragab
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Qasem Al-Tashi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Said Jadid Abdulkadir.

Ethics declarations

Conflict of interest

The authors proclaim no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ibad, T., Abdulkadir, S.J., Aziz, N. et al. Hyperparameter Optimization of Evolving Spiking Neural Network for Time-Series Classification. New Gener. Comput. 40, 377–397 (2022). https://doi.org/10.1007/s00354-022-00165-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00354-022-00165-3

Keywords