Decentralized Federated Deep Learning Image Recognition Models

In the era of IoT, numerous frameworks and cutting-edge models have been introduced to enhance user experience and privacy and reduce the risk of data breaches. Over time, IoT device usage has grown tremendously, and a flood of data has been sent to servers for processing. Federated learning has been deployed for efficient decentralization while preserving privacy. Federated learning has been applied in various IoT-related applications such as image classification, object segmentation, object detection, and sensor analytics. Existing centralized image recognition models fall short of providing accurate image classification with acceptable processing time for real-time deployment while preserving privacy. In this paper, we designed two decentralized deep learning models using federated learning, the CNN-TFF and the VGG16-TFF. With around 250 training iterations, we achieved a high accuracy rate of up to 90% with a decrease in the loss value for the CIFAR-100 dataset using the VGG16-TFF model while maintaining data privacy using federated learning.