Open AccessFeature Selection towards Soil Classification in the context of Fertility classes using Machine Learning
Author(s) -
Janmejay Pant,
Puspha Pant,
Ashutosh Kumar Bhatt,
Harsh V. Pant,
Nirmal Pandey
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.l3487.1081219
Subject(s) - soil fertility , fertility , agriculture , agricultural engineering , computer science , feature selection , population , context (archaeology) , soil survey , machine learning , geography , soil science , environmental science , soil water , engineering , sociology , demography , archaeology
Soil is recognized as one of the most valuable entity which is responsible for sustaining life on the earth. It is clear that Indian economy is largely dependent on agriculture. In India, for a large section of the population the sole or major source of earnings is agriculture. There are many factors which are responsible in yield production and also affect agriculture. Soil is one of them and plays a crucial role in yield production. Soil nutrients are important aspects that contribute to soil fertility. In this paper we classify soil in the form of fertility index level using machine learning. We induced rule model on training data and apply this model on test data for making predictions for fertility level classes. In this paper we have used Rough Set method to classify the data based on fertility level class and calculate the accuracy of the used classifier.