Rough Set Based Decision Support for Feature Extraction of Rice Data

The use of technology in the agriculture sector makes it more productive. Different technologies are used for quality control, classification, and prediction of grains in agriculture. It is challenging for decision-making with big agricultural data to concentrate more when many features are given in the data. It is difficult for users to scrutinize the market's excellent quality rice. Determining rice quality by the visual judgment of human inspectors is neither practical nor reliable. Therefore, a proven methodology is essential for the rice quality classifying system, which will overcome the manual quality classification process. In this study, the concept of Rough Set Theory is applied to find a set of minimal attributes and generate a set of decision rules for predicting rice type.