Abstract
The inefficiency of manual detection methods makes diagnosing banana crop diseases a serious threat to the agricultural sector. In this paper, we introduce ensemble deep learning of ResNet50, InceptionV3, and LeNet for complete diagnosis of the six most revalent banana leaf diseases. Our hybrid solution combines the mobile ease-of-use built with Flutter and TensorFlow Lite, allowing offline disease diagnosis with instant treatments for organic remedies. Our field testing showed remarkable reduction in diagnosis time compared to the traditional methods, and enhances sustainable farming through green treatment alternatives. The framework builds a new model for farm disease management that is simple, cost-efficient, and eco-friendly, and especially helpful to farmers in areas with poor internet access and low means.
Abstract from the paper’s OpenAlex record, shown for indexing and research. Copyright remains with the authors or the publisher. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 1
Claim · model-written summary
Field testing found that the mobile framework reduced banana disease diagnosis time compared with traditional methods.
Verbatim
t0“Banana”
e0“Our field testing showed remarkable reduction in diagnosis time compared to the traditional methods”