Yield Prediction of Paddy based on Temperature and Rain Fall Using Data Mining Techniques
S. P. Aishwarya1, Pramod Sunagar2, Anita Kanavalli3
1S. P. Aishwarya, Student, Department of CSE, MSRIT.
2Pramod Sunagar, Assistant Professor, Department of CSE, MSRIT.
3Dr. Anita Kanavalli, Professor and Head, Department of CSE, MSRIT.
Manuscript received on 10 October 2019 | Revised Manuscript received on 19 October 2019 | Manuscript Published on 02 November 2019 | PP: 65-70 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B10120982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1012.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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: The population of the world is estimated to be about 7 billion and might reach 9 billion in a few couple of years. With this growth in the global population, the world is facing challenges in food production. Prediction of agriculture is helpful in analyzing the risk, decide on storage, transportation and marketing. But rain and weather conditions are highly variable and, hence, it requires Data Mining. Data sets are extracted and analyzed to determine the rainfall patterns, humidity, wind speed and temperature, there by predicting the yield. The key idea here is to collect the data having various parameters affecting the yield, classify the data using KNN, then predict the yield using Apriori algorithm and analyze the productivity thus helping in decision making on marketing and risk. With the open source R Studio the graphical analysis is made. Since paddy is one of the basic food crop and also the major food crop grown in Karnataka state, the analysis is made on paddy yield considering two districts Koppal and Raichur which produces the major paddy yield.
Keywords: Data Mining, KNN Classifier, Apriori Algorithm, R, Koppal, Raichur.
Scope of the Article: Data Mining