DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos nucifera

2025-05-15

AI Summary

Coconut tree diseases severely threaten agricultural productivity in developing countries, yet conventional manual diagnosis suffers from low efficiency and poor scalability. To address this, we propose a lightweight, end-to-end deep learning framework tailored for coconut disease identification. Our method introduces a custom lightweight CNN architecture, a novel SGD-Adam hybrid optimization strategy that achieves an optimal trade-off between accuracy and training efficiency, and integrates transfer learning with model compression techniques to enable efficient mobile deployment. Experimental results demonstrate a classification accuracy of 99.5%—a 5-percentage-point improvement over the state of the art—along with an 18% reduction in training time, an 85% decrease in per-image inference latency, and a validation loss of only 2.81%. These advances significantly enhance the real-time capability, scalability, and practical applicability of field-deployable disease monitoring systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Detects diseases in coconut trees automatically using deep learning
• Improves accuracy and reduces computational cost in disease identification
• Provides scalable AI solution for precision agriculture monitoring

Innovation

• Deep learning model for coconut disease detection
• Hybrid SGD-Adam optimizer for optimal performance
• Mobile-friendly design with reduced prediction time