Research Focus

Developed an automated papaya disease classification study using a hybrid Deep Learning + Machine Learning framework.

Literature Review

Reviewed existing research on plant disease detection, CNNs, transfer learning, and machine learning classifiers to identify key limitations and establish the research gap.

Methodology

Designed a complete research pipeline covering image preprocessing, augmentation, deep feature extraction, model development, classification, and comparative evaluation using CNN, ResNet50, DenseNet121, VGG16, SVM, XGBoost, and Random Forest.

Results

Evaluated models using accuracy, precision, recall, F1-score, loss, and confusion matrices. ResNet50 + SVM achieved 99.6% accuracy, delivering the strongest overall performance.

Deliverables

Research paper • Literature review • Research gap analysis • Methodology • Model comparison • Data visualizations • Results & discussion

Future Scope

Proposed larger datasets, improved real-world generalization, Explainable AI, and IoT-based real-time deployment. Full Research Paper: For further details, methodology, analysis, and results, view the published research paper: https://doi.org/10.5281/zenodo.19727283