Skip to main content
SpringerLink
Log in

Fuzzy neural network based prediction model applied in primary component analysis

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

To solve the low accuracy and bad robustness problems in traditional water quality prediction method, this paper put forward a primary component analysis (PCA)–fuzzy neural network (FNN)–DEBP based prediction model of dissolved oxygen (DO) in aquaculture water quality. This model used PCA to extract the PC of aquaculture ecological indexes, then reduced the input vector dimension of the model, and utilized differential evolutionary algorithm to optimize the weight parameter of FNN, in order to automatically obtain the optimum parameters and build nonlinear prediction model of DO in aquaculture water quality. The model was applied in a predictive analysis on the water quality data online monitored from December 1st 2015 to December 8th 2015 in a Penaeus orientalis culture pond. The testing results show that this model has obtained a good predictive effect. Compared to BP-FNN model, in PCA–FNN–DEBP model, the absolute error of 95.8% test samples is less than 20%, and the maximum error is 0.22 mg/L, both of which are superior than BP-FNN prediction method. Due to rapid computation speed and high prediction accuracy, PCA–FNN–DEBP algorithm can provide strategic basis for the regulation and management of water quality in P. orientalis culture.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Guan, C., Liu, H., Song, H., et al.: The oxygenation effect of surge machine in Penaeus orientalis culture. Agric. Eng. J. 28(9), 208–212 (2012)

    Google Scholar 

  2. Gu, J., Gu, H., Men, T., et al.: Comparison of oxygenation performance of several mechanical oxygenation methods in pond aquaculture. Agric. Eng. J. 27(1), 148–152 (2011)

    Google Scholar 

  3. Maradona, A., Marshall, G., Mehrvar, M., et al.: Utilization of multiple organisms in a proposed early-warning biomonitoring system for real-time detection of contaminants: preliminary results and modeling[J]. J. Hazard. Mater. 219–220, 95–102 (2012)

    Article  Google Scholar 

  4. Nittami, T., Oi, H., Matsumoto, K., et al.: Influence of temperature, pH and dissolved oxygen concentration on enhanced biological phosphorus removal under strictly aerobic conditions. N. Biotechnol. 29(SI), 2–8 (2011)

    Article  Google Scholar 

  5. Xu, L., Li, Q., Liu, S., Li, D.: Prediction of pH value in industrialized aquaculture based on ensemble empirical mode decomposition and improved artificial bee colony algorithm. Trans. Chin. Soc. Agric. Eng. 32(3), 202–203, 207–209 (2016)

  6. Wang, R., Fu, Z., He, Y.: Dissolved oxygen predication model in pond freshwater aquaculture on basis of neural network. Anhui Agric. Sci. 38(33), 18868–18870, 18873 (2010)

  7. Song, X., Ma, Z., Wan, R., Gao, L.: Applicability of artificial neural network in the quality prediction of Litopenaeus vannamei culturing water. Period. Ocean Univ. China 44(6), 28–33 (2014)

    Google Scholar 

  8. Da, Y., Wang, X., Zhao, Y., Jiang, M., Ye, M.: Water quality prediction model based on relevance vector machine regression. Acta Sci. Circumst. 35(11), 3730–3735 (2015)

    Google Scholar 

  9. Tan, G., Yan, J., Gao, C.: Prediction of water quality time series data based on least squares support vector machine. Procedia Eng. 31, 1194–1199 (2012)

    Article  Google Scholar 

  10. Xu, D., Zhou, C., Sun, C., Du, Y.: Prediction model of aquaculture water temperature and pH based on BP neural network optimized by particle swarm algorithm. Fish. Mod. 43(1), 24–29 (2016)

    Google Scholar 

  11. Liu, S., Xu, L., Li, Z., et al.: Forecasting model for pH value of aquaculture water quality based on PCA-MCAFA-LSSVM. Trans. Chin. Soc. Agric. Mach. 45(5), 239–246 (2014)

    Google Scholar 

  12. Liu, Y., Liu, B.: Opportunities and challenges for marine industrialized aquaculture in China. Fish. Mod. 39(6), 1–4 (2012)

    Google Scholar 

  13. Hu, J., Wang, J., Zhang, X., Fu, Z.: Research status and development trends of information technologies in aquacultures. Trans. Chin. Soc. Agric. Mach. 44(7), 251–263 (2015)

    Google Scholar 

  14. Han, H.G., Chen, Q.L., Qiao, J.F.: An efficient selforganizing RBF neural network for water quality prediction. Neural Netw. 24, 717–725 (2011)

    Article  MATH  Google Scholar 

  15. Faruk, D.Ö.: A hybrid neural network and ARIMA model for water quality time series prediction. Eng. Appl. Artif. Intell. 23, 586–594 (2010)

    Article  Google Scholar 

  16. West, D., Dellana, S.: An empirical analysis of neural network memory structures for basin water quality forecasting. Int. J. Forecast. 27, 777–803 (2011)

    Article  Google Scholar 

  17. Zhang, Y., Gao, Q.: Research of a comprehensive water quality prediction model based on gray model and fuzzy neural network. Environ. Eng. J. 9(2), 537–545 (2015)

    Google Scholar 

  18. Jiang, B., Sun, L., Cao, J., et al.: The design of temperature and humidity controller in dry kiln based on GA optimized T-S fuzzy neural network. Lab. Investig. Discov. 34(11), 54–59 (2015)

    Google Scholar 

  19. Ma, C., Zhao, D.: Aquaculture pond dissolved oxygen model based on genetic algorithm and RBF network. China Rural Conserv. Hydropower 2(1), 14–16, 22 (2011)

  20. Wang, D., Li, S., Zhou, X.: Raw water quality evaluation method and application on basis of PSO-RBF neural network model. Southeast Univ. J. Nat. Sci. Ed. 41(5), 1019–1023 (2011)

    Google Scholar 

  21. Liu, S., Xu, L., Li, D.: Dissolved oxygen prediction model in river crab aquaculture based on ant colony optimized least squares support vector regression. Agric. Eng. J. 28(27), 167–175 (2012)

    Google Scholar 

  22. Long, W., Liang, X., Long, Z., et al.: LSSVM short-term load predication based on parameters optimized by improved ant colony algorithm. Cent. South Univ. J. Nat. Sci. Ed. 42(11), 3408–3414 (2011)

    Google Scholar 

  23. Stom, R., Price, K.: Differential Evolution—A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. University of California, Berkeley (2006)

    Google Scholar 

  24. Liu, B., Wang, L., et al.: Research progress in difference evolution algorithm. Control Decis. Mak. 22(7), 722 (2007)

    Google Scholar 

  25. Chen, J., Liu, L., Zhou, Z., Yong, X.: Mining method optimization based on basic component analysis and neural network. Cent. South Univ. J. Nat. Sci. Ed. 41(5), 1967–1972 (2010)

    Google Scholar 

  26. Zou, H., Jiang, L., Li, F.: Water quality evaluation method based on primary component analysis. Math. Pract. Underst. 38(8), 85–90 (2008)

    Google Scholar 

  27. Xu, Z., Zhou, D., Luo, Y.: Primary component based fuzzy neural network. Comput. Eng. Appl. 5(1), 34–36 (2006)

    Google Scholar 

  28. Li, X., Li, Q., Zhang, Y.: New kind of fuzzy neural network model. Comput. Eng. Appl. 46(11), 60–62 (2010)

    Google Scholar 

  29. Ma, C., Zhao, D.: Aquaculture pond dissolved oxygen model based on genetic algorithm and RBF network. China Rural Conserv. Hydropower 2(1), 14–26, 22 (2011)

  30. Zhang, Z., Luo, J.: Difference evolutionary algorithm based fuzzy neural network controller. Comput. Appl. Chem. 28(12), 1549–1552 (2011)

    Google Scholar 

Download references

Acknowledgements

Thanks to the support of Guangdong Province Science and Technology Project ([2012]145) and Zhanjiang Science and Technology Project (2015A03032).

Author information

Authors and Affiliations

  1. Guangdong Ocean University, Zhanjiang, 524088, China

    Xiaohong Peng, Shiyi Xie, Yinghuai Yu & Zhenlu Wu

Authors
  1. Xiaohong Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shiyi Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yinghuai Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhenlu Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaohong Peng.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Peng, X., Xie, S., Yu, Y. et al. Fuzzy neural network based prediction model applied in primary component analysis. Cluster Comput 20, 131–140 (2017). https://doi.org/10.1007/s10586-017-0738-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-017-0738-2

Keywords

Search

Navigation