Welcome to the InfoSci Platform
Reference Hub5
Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques

Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques

Arindam Chaudhuri
Copyright: © 2013 |Volume: 4 |Issue: 4 |Pages: 24
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781466658936|DOI: 10.4018/ijaeis.2013100104
Cite Article Cite Article

MLA

Chaudhuri, Arindam. "Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques." IJAEIS vol.4, no.4 2013: pp.68-91. http://doi.org/10.4018/ijaeis.2013100104

APA

Chaudhuri, A. (2013). Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 4(4), 68-91. http://doi.org/10.4018/ijaeis.2013100104

Chicago

Chaudhuri, Arindam. "Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 4, no.4: 68-91. http://doi.org/10.4018/ijaeis.2013100104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Forecasting rice production is a challenging problem in agricultural statistics. The inherent difficulty lies in demand and supply affected by many uncertain factors viz. economic policies, agricultural factors, credit measures, foreign trade etc. which interact in a complex manner. Since last few decades, Statistical techniques are used for developing predictive models to estimate required parameters. Determination of nature of rice production time series data is difficult, expensive, time consuming and involves tedious tests. In this paper, we use Interval Type Fuzzy Auto Regressive Integrated Moving Average (ITnARIMA), Adaptive Neuro Fuzzy Inference System (ANFIS) and Modified Regularized Least Squares Fuzzy Support Vector Regression (MRLSFSVR) for prediction of Productivity Index percent (PI %) of rice production time series data and compare it with traditional Statistical tool of Multiple Regression. The accuracies of ITnARIMA and ANFIS techniques are evaluated as relatively similar. It is found that ANFIS exhibits high performance than ITnARIMA, MRLSFSVR and Multiple Regression for predicting PI %. The performance comparison shows that Computational Intelligence paradigm is a promising tool for minimizing uncertainties in rice production data. Further Computational Intelligence techniques also minimize potential inconsistency of correlations.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.