Publication Type : Book Chapter
Publisher : Information Management and Machine Intelligence.,ICIMMI 2019
Source : Information Management and Machine Intelligence.,ICIMMI 2019. Algorithms for Intelligent Systems. Springer, Singapore. pp.169-175.
Url : https://doi.org/10.1007/978-981-15-4936-6_18
Keywords : Agriculture, Machine learning, Support vector machine
Campus : Amritapuri
School : School of Engineering
Department : Computer Science
Year : 2019
Abstract : This paper is carried on predicting the rainfall pattern in our country using machine learning. India is an agrarian economy, and the agricultural sector contributes to 18% of the total GDP and is responsible for 50% of employment. The role of rainfall in this sector is immense, and in order to sustain growth, in this sector we need methods for predicting the amount of rainfall in different regions of the country. This paper measures the efficiency of different SVM kernels in predicting the amount of rainfall. In order to make the study more effective, we have used the real dataset for past year’s rainfall measures [1]. Results of this application will help farmers to decide the right crop for the season based on the amount of precipitation.
Cite this Research Publication : Kiran Kumar M., Divya Udayan J., Ghananand A. (2021) Efficiency of Different SVM Kernels in Predicting Rainfall in India, Information Management and Machine Intelligence.,ICIMMI 2019. Algorithms for Intelligent Systems. Springer, Singapore. pp.169-175.