Prediction of multidimensional time series based on GS-RSR-SVR and its application in agricultural economy
Keywords:
multidimensional time series, geo-statistics tool, reasonable sample rejection, support vector machine regression, predictionAbstract
This paper proposes a method that creatively applies a Geo-statistics tool (GS) to complete fast and adequate order determination and introduces a novel algorithm, named Reasonable Sample Rejection (RSR) to realize rational sample selection. Then, combined with Support Vector Machine Regression (SVR), a high precision non-linear prediction method named GSRSR-SVR is proposed for multidimensional time series. The main steps of the novel method includes: 1) determine the order for the dependent variable of the training samples based on one-dimensional GS aftereffect duration (range), 2) screen the independent variables according to Leave-One-Out Cross Validation (LOOCV) based on the minimum Mean Squared Error (MSE), 3) reject some oldest training samples based on the minimum correlation coefficient of fitting absolute relative error of training sets of different rejected sizes and sample number. Three real-world datasets was used to test the effectiveness of GSRSR-SVR. The results show that GS-RSR-SVR has higher prediction precision and more stable prediction ability than MLR, ARIMA, CAR, BPNN, SVR and SVR-CAR.
References
Andrew, M. L., E. R. Richard and P. K. William, 1993. Geostatistics and geographic information systems in applied insect ecology. Annu. Rev. Entomol., 38: 303-327.
Box, Q. E. P. and G. M. Jenkins, 1970. Time Series Analysis: Forecasting and Control. Holden-day Press, San Francisco, 1pp. 1-175.
Boker, J. and L. Keviczky, 1982. Structural properties and structure estimation of vector difference equations. International Journal of Control, 36: 461-476.
Corinna, C. and V. Vladimir, 1995. Support-vector networks. Machine Learning, 20: 273-291.
Chang, C. C. and C. J. Lin, 2011. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2: 1-27.
Deng, Z. L. and Y. X. Guo, 1985. Dynamic System Analysis and Its Application, Liaoning Science & Technology Press, Shenyang, pp. 22-43 (Ch).
Dong, D. W., 2011. A study on temporal and spatial differentiation of land intensive use based on spatial sate mining and geo-statistical analyst--a case of Wuhan urban circle, Master thesis, Central China Normal University, Wuhan, China, pp. 27-39 (Ch).
Gai, J. Y., 2007. Methods of Experimental Statistics, China Agriculture Press, Beijing, 376 pp. (Ch).
Han, Z. G., 2001. The progress of theory and application of multi-level recursive method. Control and Decision, 16: 129-132, 185 (Ch).
Hannan, E. J., 1980. The estimation of the order of an ARMA process. Annals of Statistics, 8: 1071-1081.
Li, H. B., Z. Q. Wang and Q. C. Wang, 1998. Theory and methodology of spatial heterogeneity quantification. Chinese Journal of Applied Ecology, 9: 651-657 (Ch).
Ping, F. P. and C. H. Wei, 2005. Support vector machines with simulated annealing algorithms electricity load forecasting. Energy Conversion and Management, 46: 2669-2688 (Ch).
Robert, J. M., 2008. Application of partial mutual information variable selection to ANN forecasting of water quality in water distribution systems. Environmental Modelling & Software, 3: 1-11.
Tang, Q. Y. and M. G. Feng, 2002. DPS data processing system for practical statistics, Science Press, Beijing, 989 pp. (Ch)
Tang, H. M. and Z. J. Xie, 2004. Stationarizing two classes of non-stationary processes by wavelet. Acta Scientiarum Naturalium Universitatis Pekinensis, 40: 19-28 (Ch).
Vapnik, V. N., 1995. The Nature of Statistical Learning Theory. Spring Verlag Press, New York, pp. 3-47.
Wang, H. Y. and S. Lu, 2006. Nonlinear time series analysis and its applications. Science Press, Beijing, pp. 19-28 (Ch).
Wang, Y. S., 2008. Prediction of the chaotic time series from parameter varying systems using artificial neural networks. Acta. Physica. Sinica., 57: 6120-6131.
Wu, C. Z. and W. Hong, 1999. Multidimensional time series analysis on tree growth. Chinese Journal of Applied Ecology, 10: 395-398 (Ch).
Wu, C. Z. and W. Hong, 2002. A proposed multidimensional time series model of individual age and diameter in tsuga longibracateatz. Acta. Phytoecological Sinica., 26: 403-407 (Ch).
Yuan, Z. M., Y. S. Zhang and J. Y. Xiong, 2008. Multidimensional time series analysis based on support vector machine regression and its application in agriculture. Scientia. Agricultura. Sinica., 41: 2485-2492 (Ch).
Zhang, Y. S., Z. M. Yuan, J. Y. Xiong and T. J. Zhou, 2007. Multidimensional time series analysis based on support vector regression and controlled autoregressive and its application in ecology. Acta. Ecologica. Sinica., 27: 2419-2424 (Ch).
Downloads
Published
Issue
Section
License
Copyright (c) 2013 Bulgarian Journal of Agricultural Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
