A Comparative Analysis of Machine Learning Models for Prediction of Wave Heights in Large Waterbodies

  • Authors

    • Priyanka Sinha
    • Shweta Vincent
    • Om Prakash Kumar
    2018-12-19
    https://doi.org/10.14419/ijet.v7i4.41.24308
  • Linear Regression, Logitstic Regression, Support Vector Machine, Support Vector Regression, Extreme Learning Machine

  • Abstract

    This paper presents a study of the various machine learning algorithms viz. Linear Regression, Logistic Regression, Support Vector Machine, Support Vector Regression and Extreme Machine Learning for the prediction of wave heights using data obtained from ocean buoys. The data from the ocean buoy number 62081 off the coast of Ireland in Europe has been chosen for study. It is found that the parameter of wind speed affects wave heights the most in comparison to other parameters. It is also observed that Extreme Learning Machine outperforms Support Vector Regression when classifying the data points as high tide or low tide. The MSE and CC parameters prove the suitability of Extreme Machine Learning over all the other algorithms discussed in this paper for the accurate prediction of wave heights.

     

     

     

  • References

    1. [1] N. Kumar, R. Savitha and A. Al Mamun, "Ocean wave height prediction using ensemble of Extreme Learning Machine", Journal of Neurocomputing, vol. 277, pp. 12-20, 2018.

      [2] G. Huang, Q. Zhu and C. Siew, "Extreme learning machine: Theory and applications", Journal of Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006.

      [3] S. Londhe and V. Panchang, "One-Day Wave Forecasts Based on Artificial Neural Networks", Journal of Atmospheric and Oceanic Technology, vol. 23, no. 11, pp. 1593-1603, 2006.

      [4] M. Kazeminezhad, A. Etemad-Shahidi and S. Mousavi, "Application of fuzzy inference system in the prediction of wave parameters", Ocean Engineering, vol. 32, no. 14-15, pp. 1709-1725, 2005.

      [5] I. Malekmohamadi, M. Bazargan-Lari, R. Kerachian, M. Nikoo and M. Fallahnia, "Evaluating the efficacy of SVMs, BNs, ANNs and ANFIS in wave height prediction", Ocean Engineering, vol. 38, no. 2-3, pp. 487-497, 2011.

      [6] A. Durán-Rosal, C. Hervás-Martínez, A. Tallón-Ballesteros, A. Martínez-Estudillo and S. Salcedo-Sanz, "Massive missing data reconstruction in ocean buoys with evolutionary product unit neural networks", Ocean Engineering, vol. 117, pp. 292-301, 2016.

      [7] S. Salcedo-Sanz, J. Nieto Borge, L. Carro-Calvo, L. Cuadra, K. Hessner and E. Alexandre, "Significant wave height estimation using SVR algorithms and shadowing information from simulated and real measured X-band radar images of the sea surface", Ocean Engineering, vol. 101, pp. 244-253, 2015.

      [8] A. Smola and B. Schölkopf, "A tutorial on support vector regression", Statistics and Computing, vol. 14, no. 3, pp. 199-222, 2004.

  • Downloads

  • How to Cite

    Sinha, P., Vincent, S., & Prakash Kumar, O. (2018). A Comparative Analysis of Machine Learning Models for Prediction of Wave Heights in Large Waterbodies. International Journal of Engineering & Technology, 7(4.41), 91-95. https://doi.org/10.14419/ijet.v7i4.41.24308

    Received date: 2018-12-18

    Accepted date: 2018-12-18

    Published date: 2018-12-19