Experimental Analysis of Machine Learning Algorithms Based on Agricultural Dataset for Improving Crop Yield Prediction
Kusum Lata1, Sajidullah S. Khan2
1Kusum Lata*, Research Scholar, Department of Computing Sciences and Engineering, Sandip University, Nasik.
2Sajidullah S. Khan, Associate Professor, Department of Computing Sciences and Engineering, Sandip University, Nasik.
Manuscript received on September 11, 2019. | Revised Manuscript received on October 05, 2019. | Manuscript published on October 30, 2019. | PP: 3246-3251 | Volume-9 Issue-1, October 2019 | Retrieval Number: F9308088619/2019©BEIESP | DOI: 10.35940/ijeat.F9308.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Agriculture is the primary research study area in India as agriculture is the main source of income for various communities. In classification algorithm for agricultural dataset according to production, area, crop and seasons. Here, four classification algorithms are used with the help of WEKA tool. These algorithms are namely the present scenario, there is a call to renovate the enormous agriculture data into diverse technologies and make them accessible to the farmer for improved decision making. The endeavor of this work is to find out the finest Random Tree, J48, Bayes Net and K Star etc. The captured results revealed that Random tree algorithm performed well in terms of error rate and provides slightly better performance than KStar, Bayes Net and J48 classifiers. In this paper, our objective is to apply machine learning techniques to mine constructive information from the agricultural dataset to improve the crop yield prediction for major crops in Nashik district of Maharashtra.
Keywords: WEKA tool, J48, Bayes Net, KStar and Random Tree, Machine learning and Crop Yield Prediction.