Are you ready to amplify your academic presence and connect with a global network of researchers? Join the Scholar Indexing Society and elevate your research to new heights!
Disease Detection in CCN-51 Cocoa Fruits through Convolutional Neural Networks A Novel Approach for the Ghana Cocoa Board
Article Number: SIS321967AI090724
9th July, 2024
Author(s):
Miracle A. Atianashie
Abstract:
The study explores the
significant challenge of diagnosing diseases in CCN-51 cocoa fruits within
Ghana, a key concern for the agricultural sector. This model aims to
revolutionize the accuracy of disease detection in cocoa fruits, a crucial step
toward bolstering the sustainability of Ghana's agricultural sector. By
significantly improving detection rates, the project anticipates providing a
solid foundation for more effective disease management strategies, ensuring the
health and productivity of cocoa crops, and, by extension, supporting the
economic stability of the farming communities reliant on cocoa production. The
methodology is designed with a dual focus: ensuring the model's robustness to handle
real-world agricultural complexities and verifying its adaptability to the
diverse conditions encountered in cocoa farming environments. A comprehensive
series of experiments were meticulously designed to evaluate the CNN model's
diagnostic capabilities. These experiments were structured to assess the
model's precision in identifying various diseases across different stages of
infection, environmental conditions, and fruit varieties. The research aims to
rigorously test the model's effectiveness and reliability by simulating a wide
array of real-world scenarios, ensuring its practical applicability for farmers
and agricultural professionals. The experimental findings paint a promising
picture, showcasing the CNN model's exceptional performance across key metrics
such as accuracy, precision, recall, and F1 scores. These results highlight a
significant leap forward in disease detection capabilities, surpassing the
benchmarks set by conventional methods. The high level of accuracy not only
validates the model's effectiveness and signals its potential to transform
disease management practices in cocoa agriculture. The implications of these
findings are profound, with the potential to catalyze a paradigm shift in how
disease detection is approached in the cocoa farming sector. The study
elaborates on the multifaceted benefits of the CNN model, emphasizing its role
as a cost-effective, efficient, and scalable tool for disease management. By
significantly reducing crop losses and enhancing production sustainability, the
model promises to bolster the economic well-being of cocoa farmers and
contribute to the broader goals of agricultural innovation and food security in
Ghana.