Comparative performance of wavelet-based neural network approaches (original) (raw)

Abstract

An agriculture-dominated developing country like India has been always in need of efficient and reliable time series forecasting methodologies to describe various agricultural phenomenons, whereas agricultural price forecasting continue to be the challenging areas in this domain. The observed features of many temporal price data set constitute complex nonlinearity, and modeling these features often go beyond the capability of Box–Jenkins autoregressive integrated moving average methodology. Moreover, despite the popularity and sheer power of traditional neural network model, the empirical forecasting performance of this model has not been found satisfactory in all cases. To address the problem, wavelet-based modeling approach is recently upsurging. Present study discusses two wavelet-based neural network approaches envisaging monthly wholesale onion price of three markets, namely Bangalore, Hubli, and Solapur. Wavelet-based decomposition makes it possible to describe the useful pattern of the series from both global as well as local aspects and found to be highly proficient in denoising and capturing the inherent pattern of the series through a distinctive approach. Besides, wavelet method can also be used as a tool for function approximation. The improvement upon time-delay neural network also be made up to a great extent through using wavelet-based approaches as exhibited through proper empirical evidence.

Access this article

Log in via an institution

Subscribe and save

Buy Now

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

Instant access to the full article PDF.

Similar content being viewed by others

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

References

  1. Anjoy P, Paul RK (2017) Wavelet based hybrid approach for forecasting volatile potato price. J Indian Soc Agric Stat 71(1):7–14
    MathSciNet Google Scholar
  2. Anjoy P, Paul RK, Sinha K, Paul AK, Ray M (2017) A hybrid wavelet based neural networks model for predicting monthly wpi of pulses in India. Indian J Agric Sci 87(6):834–839
    Google Scholar
  3. Adhikari R, Agrawal RK (2014) A combination of artificial neural network and random walk models for financial time series forecasting. Neural Comput Appl 24(6):1441–1449
    Article Google Scholar
  4. Alexandridis AK, Zapranis AD (2013) Wavelet neural networks: a practical guide. Neural Netw 42:1–27
    Article MATH Google Scholar
  5. Antoniadis A (1997) Wavelets in statistics: a review. J Ita Stat Soc 6:97–144
    Article Google Scholar
  6. Díaz-Robles LA, Ortega JC, Fu JS, Reed GD, Chow JC, Watson JG, Moncada-Herrera JA (2008) A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile. Atmos Environ 42:8331–8340
    Article Google Scholar
  7. Farda AK, Akbari-Zadehb MR (2014) A hybrid method based on wavelet, ANN and ARIMA model for short-term load forecasting. J Exp Theor Artif Intell 26(2):167–182
    Article Google Scholar
  8. Granger CWJ, Anderson AP (1978) Introduction to bilinear time series models. Vandenhoeck and Ruprecht, Gottingen
    Google Scholar
  9. Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, Englewood Cliffs
    MATH Google Scholar
  10. Hung NQ, Babel MS, Weesakul S, Tripathi NK (2009) An artificial neural network model for rainfall forecasting in Bangkok, Thailand. Hydrol Earth Syst Sci 13:1413–1425
    Article Google Scholar
  11. Kohzadi N, Boyd MS, Kermanshahi B, Kaastra I (1995) A comparison of artificial neural network and time series models for forecasting commodity prices. Neurocomputing 10:169–181
    Article MATH Google Scholar
  12. Kuan CM, White H (1994) Artificial neural networks: an econometric perspective. Econ Rev 13:1–91
    Article MathSciNet MATH Google Scholar
  13. McLeod AI, Li WK (1983) Diagnostic checking ARMA time series models using squared residual autocorrelations. J Time Ser Anal 4:269–273
    Article MathSciNet MATH Google Scholar
  14. Mohammadi K, Eslami HR, Dardashti D (2005) Comparison of regression, ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). J Agric Sci Technol 7:17–30
    Google Scholar
  15. Pacelli V, Bevilacqua V, Azzollini M (2011) An artificial neural network model to forecast exchange rates. J Intell Learn Syst Appl 3:57–69
    Google Scholar
  16. Paul RK, Prajneshu GH (2013) Statistical modelling for forecasting of wheat yield based on weather variables. Indian J Agric Sci 83(2):180–183
    Google Scholar
  17. Paul RK, Das MK (2013) Forecasting of average annual fish landing in Ganga Basin. Fish Chimes 33(3):51–54
    Google Scholar
  18. Paul RK, Prajneshu GH (2013) Wavelet frequency domain approach for modelling and forecasting of Indian monsoon rainfall time-series data. J Indian Soc Agric Stat 67(3):319–327
    MathSciNet Google Scholar
  19. Paul RK, Alam W, Paul AK (2014) Prospects of livestock and dairy production in India under time series framework. Indian J Anim Sci 84(4):130–134
    Google Scholar
  20. Paul RK (2015) ARIMAX-GARCH-WAVELET model for forecasting volatile data. Model Assist Stat Appl 10(3):243–252
    Google Scholar
  21. Paul RK, Gurung B, Paul AK (2015) Modelling and forecasting of retail price of arhar dal in Karnal, Haryana. Indian J Agric Sci 85(1):69–72
    Google Scholar
  22. Paul RK, Sinha K (2016) Forecasting crop yield: a comparative assessment of ARIMAX and NARX model. RASHI 1(1):77–85
    Google Scholar
  23. Percival DB, Walden AT (2000) Wavelet methods for time series analysis. Cambridge University Press, Cambridge
    Book MATH Google Scholar
  24. Tong H, Lim KS (1980) Threshold autoregressive, limit cycles and cyclical data. J R Stat Soc Ser B Methodol 42:245–292
    MATH Google Scholar
  25. Vidakovic B (1999) Statistical modeling by wavelets. Wiley, New York
    Book MATH Google Scholar
  26. Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175
    Article MATH Google Scholar
  27. Zhang GP, Qi M (2005) Neural network forecasting for seasonal and trend time series. Eur J Oper Res 160(2):501–514
    Article MathSciNet MATH Google Scholar

Download references

Acknowledgements

We would like to express our sincere thanks and gratitude to the anonymous reviewers for their valuable suggestions that helped us a lot in improving this manuscript.

Author information

Authors and Affiliations

  1. ICAR-Indian Agricultural Statistics Research Institute, New Delhi, 110012, India
    Priyanka Anjoy & Ranjit Kumar Paul

Authors

  1. Priyanka Anjoy
    You can also search for this author inPubMed Google Scholar
  2. Ranjit Kumar Paul
    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toRanjit Kumar Paul.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper.

Rights and permissions

About this article

Cite this article

Anjoy, P., Paul, R.K. Comparative performance of wavelet-based neural network approaches.Neural Comput & Applic 31, 3443–3453 (2019). https://doi.org/10.1007/s00521-017-3289-9

Download citation

Keywords