Evaluating the Potential of Federated Learning for Maize Leaf Disease Prediction

TL;DR

Centralized CNN training for maize leaf disease diagnosis raises data privacy concerns. The paper evaluates Federated Learning with five CNNs on PlantVillage maize leaf images distributed across multiple clients, using FedAvg to aggregate updates and measuring accuracy, training time, and traffic. It provides a short survey of FL in agriculture, a quantitative FL evaluation for maize leaves, a traffic-volume analysis, and insights into CNN performance under distributed training. The results indicate that FL can preserve privacy in heterogeneous domains while guiding practical deployment through trade-offs between model size, communication load, and accuracy.

Abstract

The diagnosis of diseases in food crops based on machine learning seemed satisfactory and suitable for use on a large scale. The Convolutional Neural Networks (CNNs) perform accurately in the disease prediction considering the image capture of the crop leaf, being extensively enhanced in the literature. These machine learning techniques fall short in data privacy, as they require sharing the data in the training process with a central server, disregarding competitive or regulatory concerns. Thus, Federated Learning (FL) aims to support distributed training to address recognized gaps in centralized training. As far as we know, this paper inaugurates the use and evaluation of FL applied in maize leaf diseases. We evaluated the performance of five CNNs trained under the distributed paradigm and measured their training time compared to the classification performance. In addition, we consider the suitability of distributed training considering the volume of network traffic and the number of parameters of each CNN. Our results indicate that FL potentially enhances data privacy in heterogeneous domains.

Figures (3)

• Figure 1: Federated Learning Rationale.
• Figure 2: Proposed Method.
• Figure 3: Confusion matrices for each tested CNN.