Judgement of Learning for Metacognitive Type-2 Fuzzy Inference System

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 801)

Abstract

This paper proposes the McIT2FIS-JOL algorithm for oceanic wave data prediction. The learning algorithm is preceded by a meta-memory layer for judgement of learning (JOL). The input is divided into subsets. Each subset is learnt by the learning algorithm, which in turn is regulated by the metacognitive layer. Each model begins with zero rules. The underlying learning algorithm then employs prediction error and novelty of sample to add rules to the network. The metacognitive component of the underlying learning algorithm determines whether each incoming sample is learnt, deleted, or reserved for future use. Once the models have learnt from their subsequent subsets, the learning of the input provided to each model is judged by employing JOL. The model whose JOL measure is the best is then utilised for processing the entire input. The performance of McIT2FIS-JOL is evaluated on a real world oceanic wave data prediction problem. It is compared with MLP, SAFIS, and its predecessor McIT2FIS. The results indicate that significant learning is possible utilising a smaller sample of incoming data, improving learning time.

Keywords

Interval Type-2 Fuzzy systems Meta-cognition Meta-memory Judgement of learning Oceanic wave data prediction 

Notes

Acknowledgement

I deeply thank Professor Suresh Sundaram, Associate Professor at Nanyang Technological University, Singapore, at the Computational Intelligence Lab, for his valuable guidance throughout the research period.

References

  1. 1.
    Babu, G.S., Savitha, R., Suresh, S.: A projection based learning in meta-cognitive radial basis function network for classification problems. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2012).  https://doi.org/10.1109/IJCNN.2012.6252769
  2. 2.
    Babu, G.S., Suresh, S.: Meta-cognitive neural network for classification problems in a sequential learning framework. Neurocomputing 81, 86–96 (2011).  https://doi.org/10.1016/j.neucomm.2011.12.001CrossRefGoogle Scholar
  3. 3.
    Bahaj, A.S.: Generating electricity from the oceans. Renew. Sustain. Energy Rev. 15(7), 3399–3416 (2011)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Das, A.K., Anh, N., Suresh, S., Srikanth, N.: An interval type-2 fuzzy inference system and its meta-cognitive learning algorithm. Evol. Syst. 7, 95–105 (2016).  https://doi.org/10.1007/s12530-016-9148-6CrossRefGoogle Scholar
  5. 5.
    Das, A.K., Subramanian, K., Sundaram, S.: An evolving interval type-2 neurofuzzy inference system and its metacognitive sequential learning algorithm. IEEE Trans. Fuzzy Syst. 23(6), 2080–2093 (2015).  https://doi.org/10.1109/TFUZZ.2015.2403793CrossRefGoogle Scholar
  6. 6.
    Das, A.K., Suresh, S., Srikanth, N.: Meta-cognitive interval type-2 neuro-fuzzy inference system for wind prediction. In: 2014 International Conference on Multisensor Fusion and Information Integration for Intelligent Systems (MFI), pp. 1–6 (2014)Google Scholar
  7. 7.
    Eriksson, M., Waters, R., Svensson, O., Isberg, J., Leijon, M.: Wave power absorption: experiments in open sea and simulation. J. Appl. Phys. 102(8), 084910 (2007).  https://doi.org/10.1063/1.2801002CrossRefGoogle Scholar
  8. 8.
    Goodman, L.A., Kruskal, W.H.: Measures of association for cross classifications. J. Am. Stat. Assoc. 49(268), 732–764 (1954).  https://doi.org/10.1007/978-1-4612-9995-0_1MATHGoogle Scholar
  9. 9.
    Hart, J.T.: Memory and the memory-monitoring process. J. Verbal Learn. Verbal Behav. 6(5), 685–691 (1967)CrossRefGoogle Scholar
  10. 10.
    Nelson, T.O.: Metamemory: a theoretical framework and new findings. Psychol. Learn. Motiv. 26, 125–173 (1990).  https://doi.org/10.1016/S0079-7421(08)60053-5CrossRefGoogle Scholar
  11. 11.
    Nelson, T.O., Narens, L.: Why investigate metacognition? In: Metacognition: Knowing About Knowing, pp. 1–25 (1994)Google Scholar
  12. 12.
    Savitha, R., Suresh, S., Sundararajan, N.: A meta-cognitive learning algorithm for a fully complex-valued relaxation network. Neural Netw. 32, 209–218 (2012).  https://doi.org/10.1016/j.neunet.2012.02.015CrossRefMATHGoogle Scholar
  13. 13.
    Subramanian, K., Das, A.K., Sundaram, S., Ramasamy, S.: A meta-cognitive interval type-2 fuzzy inference system and its projection based learning algorithm. Evol. Syst. 5(4), 219–230 (2014).  https://doi.org/10.1007/s12530-013-9102-9CrossRefGoogle Scholar
  14. 14.
    Suresh, S., Subramanian, K.: A sequential learning algorithm for meta-cognitive neuro-fuzzy inference system for classification problems. In: 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2507–2512. IEEE (2011).  https://doi.org/10.1109/IJCNN.2011.6033545
  15. 15.
    Waters, R., Stålberg, M., Danielsson, O., Svensson, O., Gustafsson, S., Strömstedt, E., Eriksson, M., Sundberg, J., Leijon, M.: Experimental results from sea trials of an offshore wave energy system. Appl. Phys. Lett. 90(3), 034105 (2007).  https://doi.org/10.1063/1.2432168CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Dhirubhai Ambani Institute of Information and Communication TechnologyGandhinagarIndia

Personalised recommendations