Performance Analysis of Machine Learning Techniques for Smart Agriculture: Comparison of Supervised Classification Approaches

Abstract

Agriculture form one of the most important aspects of life necessities, it is responsible to feed 7.7 billion person for the time being, and it is expected to supply more than 9.6 billion individual in 2050, the thing that made classical farming insufficient, and give birth to the notion of smart farming, and the race has begun toward using the latest technologies in the field. They integrate the Internet of Things (IoT), automation, Artificial Intelligence (AI), etc. And as researchers from a country that highly depends on agriculture, we have decided to also contribute to this evolution, and we chose Machine learning (ML) as our entrance to the field to satisfy the need for automated classification of the different products produced by a farm. In this work, we wanted to solve the problem of automatic classification of agricultural products, without the need of any human intervention, and we concentrate on the classification of red fruits, due to our proximity to a location that its product is red fruits. In other words, we are doing a comparative study among the well-known approaches that are used in image classification, and we are applying the best-found method to correctly classify the pictures of red fruits. And this empirically leads us to achieve great results as shown in the numerical result area.