EAS Publisher | Cassava Disease Detection Using Machine Learning Techniques

Cassava Disease Detection Using Machine Learning Techniques

DOI : https://doi.org/10.36344/ccijavs.2025.v07i03.002

54 Downloads 47 Views

Abstract: This study examines cassava disease detection using four convolutional neural network (CNN) models: ResNet50, InceptionV3, AlexNet, and VGG16. Cassava, a staple crop in Africa, is threatened by Cassava Mosaic Disease (CMD) and Cassava Brown Streak Disease (CBSD). A dataset from the Lacuna Project, collected in Ugandan farmer fields, was used to train and evaluate these models, yielding accuracies of 90 percent, 88 percent, 85 percent, and 87 percent, respectively. A Flask web application was developed for practical deployment. This work builds on prior SVM and CNN approaches, offering a detailed comparison to enhance agricultural diagnostics for smallholder farmers.

TOP EDITORS

Dr. T. Selvankumar
Chief Editor
EAS Journal of Biotechnology and Genetics

Dr. James Kay, PhD
Chief Editor
EAS Journal of Psychology and Behavioural Sciences

Dr. Rejeesh Menon
Chief Editor
EAS Journal of Medicine and Surgery

Dr. S. Jayachandran
Chief Editor
EAS Journal of Dentistry and Oral Medicine

Dr. Md. Habibur Rahman
Chief Editor
EAS Journal of Pharmacy and Pharmacology

Dr. Benard Chemwei, PhD
Chief Editor
East African Scholars Multidisciplinary Bulletin

NFI Joseph Lon
Chief Editor
EAS Journal of Humanities and Cultural Studies

Prof. Dr. Nazir Ahmad Suhail
Chief Editor
East African Scholar Journal of Engineering and Computer Sciences

Dr. Hamid Osman Hamid
Chief Editor
EAS Journals of Radiology and Imaging Technology

Dr. BOUCENNA Mounir
Chief Editor
EAS Journal of Veterinary Medical Science

OPEN ACCESS JOURNALS

Dr. Afroza Begum

Lecturer, Dept. of Pharmacology and Therapeutics, Shaheed Monsur Ali Medical College & Hospital, Uttara, Dhaka-1230, Bangladesh

BEST AUTHOR

Of The Month

TRACK YOUR ARTICLE

Enter the Manuscript Reference Number (MRN)

Get Details