DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos nucifera
Miit Daga, Dhriti Parikh, Swarna Priya Ramu
TL;DR
This work tackles the critical problem of coconut tree disease detection at scale, addressing the limitations of manual diagnosis and resource-intensive models. It introduces DeepSeqCoco, a mobile-friendly deep learning framework that leverages EfficientNet-B3 as a feature extractor with data augmentation and a seven-layer architecture to classify five coconut diseases from images. Through experiments with Adam, SGD, and hybrid optimizers on a 5,798-image dataset, DeepSeqCoco achieves near-perfect validation accuracy (up to 99.5%) while offering fast inference suitable for deployment on mobile and edge devices, outperforming several mainstream baselines. The approach demonstrates the practical potential of AI-driven, real-time disease monitoring to support precision agriculture, especially in resource-constrained settings, and outlines directions for dataset expansion and live mobile applications.
Abstract
Coconut tree diseases are a serious risk to agricultural yield, particularly in developing countries where conventional farming practices restrict early diagnosis and intervention. Current disease identification methods are manual, labor-intensive, and non-scalable. In response to these limitations, we come up with DeepSeqCoco, a deep learning based model for accurate and automatic disease identification from coconut tree images. The model was tested under various optimizer settings, such as SGD, Adam, and hybrid configurations, to identify the optimal balance between accuracy, minimization of loss, and computational cost. Results from experiments indicate that DeepSeqCoco can achieve as much as 99.5% accuracy (achieving up to 5% higher accuracy than existing models) with the hybrid SGD-Adam showing the lowest validation loss of 2.81%. It also shows a drop of up to 18% in training time and up to 85% in prediction time for input images. The results point out the promise of the model to improve precision agriculture through an AI-based, scalable, and efficient disease monitoring system.