Enabling Machine Learning Across Heterogeneous Sensor Networks with Graph Autoencoders

TL;DR

This paper presents a deep learning framework using graph autoencoders that enables activity recognition models to transfer across heterogeneous sensor networks without retraining, facilitating deployment in diverse smart home environments.

Contribution

The authors introduce a novel graph-based deep learning framework that transfers activity classifiers across different sensor network layouts without requiring labeled data from the target network.

Findings

Achieved about 75% of baseline accuracy on new sensor networks without target labels.

Model adapts quickly to unseen sensor layouts, supporting gradual deployment.

Framework is resilient to suboptimal graph representations.

Abstract

Machine Learning (ML) has been applied to enable many life-assisting appli-cations, such as abnormality detection and emdergency request for the soli-tary elderly. However, in most cases machine learning algorithms depend on the layout of the target Internet of Things (IoT) sensor network. Hence, to deploy an application across Heterogeneous Sensor Networks (HSNs), i.e. sensor networks with different sensors type or layouts, it is required to repeat the process of data collection and ML algorithm training. In this paper, we introduce a novel framework leveraging deep learning for graphs to enable using the same activity recognition system across HSNs deployed in differ-ent smart homes. Using our framework, we were able to transfer activity classifiers trained with activity labels on a source HSN to a target HSN, reaching about 75% of the baseline accuracy on the target HSN without us-ing target activity labels. Moreover, our model can quickly adapt to unseen sensor layouts, which makes it highly suitable for the gradual deployment of real-world ML-based applications. In addition, we show that our framework is resilient to suboptimal graph representations of HSNs.