AMELIORATED METHODOLOGY FOR THE DESIGN OF SUGARCANE YIELD PREDICTION USING DECISION TREE
AbstractThe productivity and quality of a Crop depends upon several parameters including but not limited to environment parameters like temperature, humidity, rainfall, wind, the quality and quantity of the pesticide, type, quantity and quality of fertilizer and so on. High productivity and yield is of utmost essentiality in a country like India where the growing population demands more grains that the field produces right now. Thus there is an urgent need to bring in more scientific studies in this direction. As amount of agricultural fields is limited and cannot be increased, it is important to get maximum productivity out of each crop. Past records of yield of a crop in different months, the known crop diseases and the weather plays a good indication as to what should be the ideal condition for high yield of a crop. However the dependencies among the parameters are so fuzzy that it is difficult to estimate the exact yield and need for exact quantity of pesticides and fertilizer to minimize the risk of crop disease, crop failure and to improve the yield. In this work a Framework is proposed that can be used to provide guidance to the farmer to detect the fault at the earlier stage to reduce losses. Decision tree, an efficient, globally competitive and vibrant classifier is used to predict sugarcane yield.
Zhu, Wenjun, et al., â€œImproving Crop Yields Forecasting Using Weather Data: A Comprehensive Approach Combining Principal Component Analysis and Credibility Modelâ€ 2012.  Othman, MohdFauzi bin, Yau, Thomas Moh Shan. â€œComparison of Different Classification Techniques Using WEKA for Breast Cancerâ€ , 2007.  Uno, Y., et.al., â€œArtificial Neural Networks to Predict Corn Yield from Compact Airborne Spectographic Imager Dataâ€ 2005.  Veenadhari, S., et al., â€œSoybean Productivity Modelling Using Decision Tree Algorithmsâ€ 2011.
Witten, I. H., Franke, E., & Hall, M. A. Data Mining: â€œPractical Machine Learning Tools and Techniquesâ€. San Francisco: Morgan Kaufman (2005).
Luger, G. F. â€œArtificial Intelligence (5th ed)â€. London: Addison Wesley (2005).
Raorane, A.A., Kulkarni, R.V., â€œData Mining: An Effective Tool for Yield Estimation in the Agricultural Sectorâ€ 2012.  Marinkovic, et al., â€œData Mining Approach for Predictive Modelling of Agriculture Yield Dataâ€ 2010.
Han J and M Kamber â€œData Mining Concepts and Techniquesâ€ Second Edition Elsevier Publication, 2009.
Beard, D. A., Gray, D. M., & Carmody, P. Farmersâ€Ÿ â€œmanagement of seasonal variability and climate change in WAâ€. Crop Updates 2010.
Ekasingh, B. S., Ngamsomsuke, K., Letcher, R. A., & Spate, J. M. â€œA Data Mining approach to simulating land use decisions: Modeling farmer's crop choice from farm level data for integrated water resource managementâ€. Paper presented at the Proceedings of the International Conference on Simulation and Modeling (2005).
The submitter hereby warrants that the Work (collectively, the “Materials”) is original and that he/she is the author of the Materials. To the extent the Materials incorporate text passages, figures, data or other material from the works of others, the undersigned has obtained any necessary permissions. Where necessary, the undersigned has obtained all third party permissions and consents to grant the license above and has all copies of such permissions and consents.
The submitter represents that he/she has the power and authority to make and execute this assignment. The submitter agrees to indemnify and hold harmless the COMPUSOFT from any damage or expense that may arise in the event of a breach of any of the warranties set forth above. For authenticity, validity and originality of the research paper the author/authors will be totally responsible.