Abstract
Genetic algorithm and neural network are two basic methods of data mining. This paper studies the related theory of genetic algorithm and neural network and, on this basis, proposes an improved mining method basing on the combination of genetic algorithm and LM optimization algorithm. This method uses genetic algorithm in two stages to improve the quality of network training. It first through the genetic algorithm to get an approximation of the overall solution by coarse control, as the initial value, and then takes genetic algorithm and LM optimized neural network algorithm to alternately train the network. By an example calculation, we can see it is feasible for crop output prediction model basing on neural network to finally inquire of the future crop output by fitting the historical data. The model achieves good results through the optimization of genetic algorithm and LM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang J, Liu KS, Wang XF (2000) Immune modulated symbiontic evolution in neural network design. J Comput Res Dev 37(8):924–930
Cong S (2001) Neural network, fuzzy system & the applications of motion control, vol 1. Press of University of Science and Technology of China, Hefei, p 324
Zhang SQ, Chen Q, Wan Enpu (1998) Grey system theory applies in crop yield. Geol Sci 18(6):581–585
Miao YB (2003) Precision agriculture intelligent measurement system research and application. Shanghai Jiaotong University Post-doctoral Thesis 3:14–16
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this paper
Cite this paper
Fan, Y. (2014). The Application of Data Mining Algorithm in Grain Output Prediction. In: Zhong, S. (eds) Proceedings of the 2012 International Conference on Cybernetics and Informatics. Lecture Notes in Electrical Engineering, vol 163. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-3872-4_97
Download citation
DOI: https://doi.org/10.1007/978-1-4614-3872-4_97
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-3871-7
Online ISBN: 978-1-4614-3872-4
eBook Packages: EngineeringEngineering (R0)