Heterogeneous Sensor Data Acquisition and Federated Learning for Resource Constrained IoT Devices—A Validation

This article focused on applying federated learning (FL) to process heterogeneous sensor data in a fog computing-enabled smart home environment. The fusion of sensor data from vision sensor, digital ambient sensor, and passive infrared sensor (PIR) is done in a distributed manner and the data processing using FL on Raspberry Pi edge nodes. The system uses edge nodes to train the respective machine learning (ML) models using FL without sending data to a centralized server. Instead, results from the training on multiple edge nodes are aggregated at the central node to produce a final machine-learning model. Each edge node deploys the aggregated model to recognize the subjects in the smart home environment and trigger an alert in case unknown subjects are identified. Linear regression model for temperature prediction and logistic regression model for humidity prediction using the ambient parameters are also trained in a federated way on the same edge nodes. The developed system uses the FL Flower framework for training the models. The obtained validation accuracy was 66% for the ML models that were built on the resource constraint server and edge clients through the FL. The developed system can be used in environments, where communication bandwidth is limited or data privacy concerns exist.