Dynamic Meta-Ensemble Framework for Efficient and Accurate Deep Learning in Plant Leaf Disease Detection on Resource-Constrained Edge Devices

TL;DR

The paper introduces a Dynamic Meta-Ensemble Framework that adaptively combines lightweight CNNs to achieve high-accuracy plant disease detection on resource-limited edge devices, balancing accuracy and efficiency.

Contribution

It proposes a novel adaptive ensemble method that dynamically weights lightweight CNNs for improved accuracy and efficiency in plant disease detection on edge devices.

Findings

Achieved 99.53% accuracy on potato disease dataset.

Reduced inference latency to less than 75ms.

Model footprint is under 1 million parameters.

Abstract

Deploying deep learning models for plant disease detection on edge devices such as IoT sensors, smartphones, and embedded systems is severely constrained by limited computational resources and energy budgets. To address this challenge, we introduce a novel Dynamic Meta-Ensemble Framework (DMEF) for high-accuracy plant disease diagnosis under resource constraints. DMEF employs an adaptive weighting mechanism that dynamically combines the predictions of three lightweight convolutional neural networks (MobileNetV2, NASNetMobile, and InceptionV3) by optimizing a trade-off between accuracy improvements (DeltaAcc) and computational efficiency (model size). During training, the ensemble weights are updated iteratively, favoring models exhibiting high performance and low complexity. Extensive experiments on benchmark datasets for potato and maize diseases demonstrate state-of-the-art classification accuracies of 99.53% and 96.61%, respectively, surpassing standalone models and static ensembles by 2.1% and 6.3%. With computationally efficient inference latency (<75ms) and a compact footprint (<1 million parameters), DMEF shows strong potential for edge-based agricultural monitoring, suggesting viability for scalable crop disease management. This bridges the gap between high-accuracy AI and practical field applications.