Enhancing Coffee Crop Management with IoT and Machine Learning: Automated Monitoring and Disease Control

EasyChair Preprint 9886

Abstract

A rise in food production is necessary to keep 
pace with the rapid growth of the human population. 
Diseases with a high rate of spreading can severely 
reduce plant yields and even wipe out the entire 
plantation. One cannot overstate the value of early 
disease detection and prevention. Due to the increasing 
use of cell phones, even in the most remote areas, 
researchers have recently turned to automatic feature 
analytics as a technique for diagnosing crop disease. 
The convolutional, activation, pooling, and fully 
connected layers of the CNN have therefore been used 
in this work to create a disease identification approach. 
Predictions of soil factors including pH levels and water 
contents, illnesses, weed identification in crops, and 
species recognition are the sectors that have received 
the most attention. The micro-controller system keeps 
track of meteorological and atmospheric changes and 
uses sensors to estimate how much water should 
circulate in accordance. If a pesticide sprayer is 
attached to the hardware, the technique can also treat 
plant diseases. Data from the system is tracked and 
documented using a mobile application. Future 
farmers will benefit intelligently from the proposed 
methodology.

Keyphrases: Automatic Coffee Disease Prediction, Convolutional Neural, Network (CNN), image processing, machine learning

@booklet{EasyChair:9886,
  author    = {Chris Chettissery and P.S. Rajakumar and S. Geetha},
  title     = {Enhancing Coffee Crop Management with IoT  and Machine Learning: Automated Monitoring  and Disease Control},
  howpublished = {EasyChair Preprint 9886},
  year      = {EasyChair, 2023}}