Intelligent agricultural information monitoring using data mining techniques

Abstract

Farmers usually select crops for cultivation based on their previous experiences, the better the profit margin of a crop achieved in the past, probability of choosing that crop increases. However, the lack of information about scientific factors that can affect the output and precise knowledge about cultivation, they end up cultivating crops that do not meet the desired profit margin. To help the farmers take decisions that can make their farming more efficient and profitable, this research tries to establish an intelligent information prediction analysis on farming in Bangladesh. Also, it provides an interface to this analysis for the farmers through an android app which also provides necessary information on cultivation procedure, irrigation and fertilization process. The research suggests area based beneficial crop rank before the cultivation process. It indicates the crops that are cost effective for cultivation for a particular area of land. To achieve these results, we are considering six major crops which are Aus, Aman, Boro rice, Potato, Jute and Wheat. The prediction is based on analyzing a static set of data using Supervised Machine Learning techniques. This static data set contains previous years’ data taken from the Yearbook of Agricultural Statistics and Bangladesh Agricultural Research Council of those crops according to the area. The research intents to do a comparative analysis on Decision Tree Learning, K-Nearest Neighbors and Multiple Linear Regression algorithms to obtain these predictions. The past ten years (20042013) of Bangladesh have been considered making this data set to ensure learning and training of the algorithms and increasing the accuracy rate of the prediction and for testing we used three years (2014-2015) for computing accuracy.