Open Access Open Access  Restricted Access Subscription Access

An Overview on Data Mining Techniques for Rice Yield Prediction on Clustered Region Of Kerala


Affiliations
1 School of CSA, REVA University, Bangalore, India
 

Data mining is the process of sorting through large data sets to identify patterns and establish relationships to solve problems through data analysis. Data mining extract knowledge from the historical data. Rice production depends on climate, type of the soil, geography, biology and economy. Several factors are having an impact of the production of rice, especially the availability of rainfall in riverbeds near to the paddy fields. For low lying region like Kerala, predicting supply of rice is critical due to varying climate over the last couple of decades. Excessive conversion of paddy fields to households and industry especially in Kuttanad (rice bowl of Kerala).Hence to overcome these issues several statistical methods are being used. Applying such methodologies and techniques on historical yield of crops, it is possible to acquire the data and information which can be helpful to farmers and cultivators to improve the production of rice and helps farmers and government sectors to make favorable decisions and policies that lead to increase the production of rice. Here my focus is on literature study on application of data mining techniques to extract information from the rice yield data of previous years to estimate rice yield.

Keywords

Som (Self-Organizing Maps, K- Clustering, Decision Tree, Linear Regression, Rice Yield.
User
Notifications
Font Size

  • . Status paper on rice in kerala (http://www.rkmp.co.in)
  • . Crop wise analysis –economic review 2016, state planning board (spb.kerala.gov.in)
  • . RAS /Paddy cultivation in kerala. (ras.org.in)
  • . Paddy cultivation in kerala- Christ university journal
  • . Indian bureau of statistics, Annual report on agriculture 2016-2017 –department of agriculture
  • . International rice research institute/ India (IRRI)
  • . Fernando Bacao, et al., "Self-organizing Maps as Substitutes for Clustering," Springer Computational Science – ICCS 2005
  • . Teuvo Kohonen . "The Self- Organizing Map", Proceedings of IEEE, Vol.78, No.9, pp.1464- 1480, 1990.[Online]Available: http://www.eicstes.org/EICSTES_PDF/PAPERS/The%20SelfOrganizing%20Map%20(Kohonen).pdf
  • . Shanmuganathan, S.et al., "Data Mining Techniques for Modelling the Influence of Daily Extreme Weather Conditions on Grapevine, Wine Quality and Perennial Crop Yield," IEEE Second International Conference on Computational Intelligence, Communication Systems and Networks(CICSyN),pp90-95,2010.
  • http://www.mathworks.com/help/stats/kmeans.html, accessed last on 20th November, 2014.

Abstract Views: 193

PDF Views: 0




  • An Overview on Data Mining Techniques for Rice Yield Prediction on Clustered Region Of Kerala

Abstract Views: 193  |  PDF Views: 0

Authors

Joslin Joy
School of CSA, REVA University, Bangalore, India
R. Pinaka Pani
School of CSA, REVA University, Bangalore, India

Abstract


Data mining is the process of sorting through large data sets to identify patterns and establish relationships to solve problems through data analysis. Data mining extract knowledge from the historical data. Rice production depends on climate, type of the soil, geography, biology and economy. Several factors are having an impact of the production of rice, especially the availability of rainfall in riverbeds near to the paddy fields. For low lying region like Kerala, predicting supply of rice is critical due to varying climate over the last couple of decades. Excessive conversion of paddy fields to households and industry especially in Kuttanad (rice bowl of Kerala).Hence to overcome these issues several statistical methods are being used. Applying such methodologies and techniques on historical yield of crops, it is possible to acquire the data and information which can be helpful to farmers and cultivators to improve the production of rice and helps farmers and government sectors to make favorable decisions and policies that lead to increase the production of rice. Here my focus is on literature study on application of data mining techniques to extract information from the rice yield data of previous years to estimate rice yield.

Keywords


Som (Self-Organizing Maps, K- Clustering, Decision Tree, Linear Regression, Rice Yield.

References