IoT and Machine Learning Based Stem Borer Pest Prediction

Global climatic changes have severe impacts on agricultural productivity. Enhanced pest attacks crops are one of the major sustainable developments in agriculture to come up with needs ever-increasing human population. Early warning a attack is important for Integrated Pest Management (IPM) activities be effective. also judicious use pesticides efficient resources minimal environment. Sugarcane cash crop and severely affected by different types pests. This study proposed stem borer prediction sugarcane directly sensed environment conditions from field using Internet Things (IoT). Data-driven machine learning decisions made predict population temperature, humidity, rainfall conditions. Directly data-driven decision Naïve Bays classification approach help accurately occurrence above or below Economic Threshold Level (ETL). The performance solution judged terms model accuracy crop. main objective support IoT capture context make decisions.