Action Recommendation Model Development for Hydromon Application Using Deep Neural Network (DNN) Method

Abstract

Controlling hydroponic plants, which is currently being carried out
manually, can be said to be less effective because it still involves the
hard work of farmers to continuously monitor the condition of the
hydroponic plants. Therefore, the general objective of this research is
to develop a model that can be used as a recommendation system for
actions that farmers need to take based on hydroponic crop conditions.
The model formed with this machine learning method will then be
used in the Hydromon application which allows farmers to manage
and monitor the condition of hydroponic plants and take action based
on the recommendations given. This model was developed using a
deep neural network algorithm consisting of five layers with the help
of the TensorFlow framework. The results show that the model is
accurate with an accuracy value of 96.47% on the test data to classify
plant conditions so that it can be used in the Hydromon application.