Publication

Abstract : Agriculture is of vital importance to human life as it is the main source of livestock production and contributes significantly to the country's employment opportunities and economy. Ensuring high standards of production quality is essential. Recent technological advances are merging agricultural and machine learning techniques to help improve crop quality. The main objective of this work is to make use of machine learning approaches to identify the healthy status of the crop. Multi-class classification is applied to the dataset which helps classify crop conditions. As there is an imbalance of data of the 3 classes, Random under- sampling and Tomek under-sampling methods are applied on the dataset. A combination of Tomek undersampling and Smote undersampling has also been performed on this dataset. Various algorithms like Gradient Boosting, Gaussian Naïve Bayes, Neural Network (MLP) and k-Nearest Neighbors were performed on the dataset which helped show that Randomforest was the best model in terms of accuracy and F1 score.