Chi-Square MapReduce Model for Agricultural Data

Abstract

Nowadays, agriculture plays a very significant role in economic growth. Decision making, crop selection and crop yield are the important issues in agriculture productions. Agricultural automation has lead to an incredible growth of software and applications to access the information. Agriculture database contains the farmer's details, land details, soil nutrient details, water levels details and etc. When the data set contains irrelevant, redundant and noisy data then it degrades the performance of the classifier model. The feature selection algorithm is used to improve the performance by selecting the relevant attributes and removing the irrelevant attributes from the database. In this paper, a novel idea is proposed by deploying chi-square technique in MapReduce model to handle large amount of agricultural data. The experimental results show that the proposed Chi-Square MapReduce model has high accuracy and less processing time than the existing feature selection methods.

Feature Selection Method based on Fisher’s Exact Test for Agricultural Data

“…The authors considered four feature picking methods; and the investigation was performed to identify the best method for agricultural dataset. The proposed model resulted in high accuracy and less processing time than the existing feature selection methods [13].…”