Energy-Aware Ensemble Learning for Coffee Leaf Disease Classification

TL;DR

This paper presents an energy-efficient ensemble learning approach using knowledge distillation to enable accurate, on-device coffee leaf disease diagnosis suitable for IoT devices with limited resources.

Contribution

It introduces a novel lightweight ensemble learning method with knowledge distillation tailored for energy-constrained IoT devices in plant disease diagnosis.

Findings

Achieved competitive accuracy with significantly reduced energy consumption.

Demonstrated the effectiveness of dense tiny ensembles for on-device diagnosis.

Reduced carbon footprint compared to traditional models.

Abstract

Coffee yields are contingent on the timely and accurate diagnosis of diseases; however, assessing leaf diseases in the field presents significant challenges. Although Artificial Intelligence (AI) vision models achieve high accuracy, their adoption is hindered by the limitations of constrained devices and intermittent connectivity. This study aims to facilitate sustainable on-device diagnosis through knowledge distillation: high-capacity Convolutional Neural Networks (CNNs) trained in data centers transfer knowledge to compact CNNs through Ensemble Learning (EL). Furthermore, dense tiny pairs were integrated through simple and optimized ensembling to enhance accuracy while adhering to strict computational and energy constraints. On a curated coffee leaf dataset, distilled tiny ensembles achieved competitive with prior work with significantly reduced energy consumption and carbon footprint. This indicates that lightweight models, when properly distilled and ensembled, can provide practical diagnostic solutions for Internet of Things (IoT) applications.