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.
Similar content being viewed by others
References
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
Liu, Y., Liu, B.: Opportunities and challenges for marine industrialized aquaculture in China. Fish. Mod. 39(6), 1–4 (2012)
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)
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)
Faruk, D.Ö.: A hybrid neural network and ARIMA model for water quality time series prediction. Eng. Appl. Artif. Intell. 23, 586–594 (2010)
West, D., Dellana, S.: An empirical analysis of neural network memory structures for basin water quality forecasting. Int. J. Forecast. 27, 777–803 (2011)
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)
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)
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)
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)
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)
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)
Stom, R., Price, K.: Differential Evolution—A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. University of California, Berkeley (2006)
Liu, B., Wang, L., et al.: Research progress in difference evolution algorithm. Control Decis. Mak. 22(7), 722 (2007)
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)
Zou, H., Jiang, L., Li, F.: Water quality evaluation method based on primary component analysis. Math. Pract. Underst. 38(8), 85–90 (2008)
Xu, Z., Zhou, D., Luo, Y.: Primary component based fuzzy neural network. Comput. Eng. Appl. 5(1), 34–36 (2006)
Li, X., Li, Q., Zhang, Y.: New kind of fuzzy neural network model. Comput. Eng. Appl. 46(11), 60–62 (2010)
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)
Zhang, Z., Luo, J.: Difference evolutionary algorithm based fuzzy neural network controller. Comput. Appl. Chem. 28(12), 1549–1552 (2011)
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
Corresponding author
Rights and permissions
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-017-0738-2