Energy-Aware Ensemble Learning for Coffee Leaf Disease Classification

2026-01-09

Consumer Communications and Networking Conference

AI Summary

This work proposes an energy-aware lightweight ensemble learning framework to address the challenge of deploying high-accuracy AI models on resource-constrained edge devices. The approach leverages knowledge distillation to transfer knowledge from a large convolutional neural network (CNN) into multiple compact sub-models and employs an optimized ensemble strategy to fuse their predictions. Experimental results on a self-collected coffee leaf disease dataset demonstrate that the proposed method achieves classification accuracy comparable to existing approaches while significantly reducing computational overhead, energy consumption, and carbon footprint. These advantages make the framework particularly suitable for sustainable edge deployment in Internet of Things (IoT) scenarios.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• coffee leaf disease
• energy-aware
• on-device diagnosis
• resource-constrained devices
• IoT applications

Innovation

• Energy-Aware
• Knowledge Distillation
• Ensemble Learning
• Tiny CNNs
• On-Device AI