USE Support Vector Machine to Research on Livestock Production Prediction in Heilongjiang Province

Abstract:

This paper uses support vector machine to research on livestock production prediction in heilongjiang province. Use SVM on the input and output data for training and learning, approximate the implied function relationship by historical data, complete the mapping of the new data series, in order to complete the livestock production prediction for future years, and compare the prediction effects with other methods. From the results we can see that, the prediction accuracy of livestock production of the SVM model is superior to other prediction methods.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 4757-4761
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.4757
• Online since: August 2013
• Authors: Tang Yang, Li Cui Xia
• Keywords: Empirical Analysis, Livestock Production Prediction, Support Vector Machine (SVM)

References

[1] Vapnik V. The Nature of Statistical Learning Theory (Second Edition) [M]. New York: Springer Verlag, 1999. 225-260.

[2] Zhang Xuegong. Introduction to Statistical Learning Theory and Support Vector Machines [J]. Acta Automatica Sinica, 2000, 26(1): 32-42.

[3] Zhao Jiwen, Liu Yongbin, Kong Fanrang. Application of SVM with Genetic Algorithms Optimizing Kernel Parameters in Linear Motor Model[J].  Journal of System Simulation, 2006, 18 (12): 3547 – 3553.

[4] Yi Danhui. Data analysis and EViews application [M]. Bei Jing: China Renmin University Press, 2008(10): 53 – 54.

[5] M. Ldmna, Introduction to pattern Recognition, Journal of ACM， 1984. 6: 12-13.

[6] Divide. Chapter 12. Informational Today Inc.: Medford, New Jersey.