ABSTRACT
The detection of plant diseases is crucial for ensuring high crop quality and yields. However, identifying diseases manually, particularly those visible on leaves, can be time-consuming and expensive. In this study, a hybrid model was used to...
ABSTRACT
The detection of plant diseases is crucial for ensuring high crop quality and yields. However, identifying diseases manually, particularly those visible on leaves, can be time-consuming and expensive. In this study, a hybrid model was used to build a cucumber curl leaf detection system. The main objective of the research was to find the best machine learning classification algorithm and identify the most accurate classifier. The proposed hybrid model combines Support Vector Machine (SVM), K-nearest neighbor (KNN), and Decision Tree (DT) classifiers as base classifiers to develop a hybrid model. Real-time generated datasets were used for prediction, where the Support Vector Machine achieved around 96.37% accuracy, the Decision Tree achieved 98%, and the K-nearest neighbor achieved an accuracy of 97%. Additionally, our proposed hybrid model achieved a classification accuracy of 98.4% on the same dataset. The model can be used for early-stage identification of cucumber curl leaf disease, reducing identification time with high accuracy.