Using MLPA for smart mushroom farm monitoring system based on IoT

Abstract

Mushroom has turned out to be a standout amongst the most fundamental consumable items in our everyday life. To increase mushroom production and to reduce manual work smart mushroom monitoring has been proposed with the assistance of internet of things (IoT) and machine learning (ML) algorithms called machine learning with prediction analysis (MLPA) technique. In this proposed MLPA technique, sensors mounted in the mushroom farm collect moisture, temperature and humidity data from soil and air, which is used to predict disease for mushroom from past history data. Based on the sensor value and prediction by ML algorithm, the farmer can predict weekly irrigation plan. The sensors are connected to IoT device, which sends collected data for analysis using ML algorithms. Three main tasks of ML algorithms are regression, classification and clustering. The main objective of our research work is to compress sensor data using kalman filter and classify using decision tree algorithm. Our proposed MLPA technique shows better accuracy than any other normal ML algorithms.