Comparative Analysis of Machine Learning Methods for Plant Disease Identification

Recently, agriculture domain has shown a digital shift that has automated various managerial task. The development of precision-based farming systems has overcome many challenges. Agriculture and collaborative activities contributed to almost 59% of the total public compensation. Plant diseases can cause major losses in agricultural product output, economy, quality, and quantity under certain conditions. It is possible to predict plant illnesses at early stage and take the necessary safeguards to avoid losses by utilizing machine learning methods. In this study, variety of machine learning techniques are used to identify plant diseases. The comparative analysis are performed using Naive Bayes, K- Nearest Neighbor, Artificial Neural Networks (ANN) and Support Vector Machines (SVM) algorithms. According to performance, the quality measures are computed by determining accuracy, precision, recall, and fl-score.