FedFusionQuant (FFQ): Federated Learning With Feature Fusion and Model Quantisation for Human Activity Recognition Using CSI

Human Activity Recognition (HAR) using Channel State Information (CSI) enables energy-efficient and non-invasive healthcare monitoring. However, conventional HAR systems rely on centralised model training, which requires the sharing of raw data, leading to privacy risks, excessive bandwidth usage, and high communication latency that limit scalability. This paper proposes FedFusionQuant (FFQ), a federated learning (FL) framework that jointly performs feature fusion, adaptive aggregation, and quantisation-aware compression during training. A novel federated distance (FedDist) mechanism dynamically adjusts parameter updates using neuron dissimilarity metrics, enhancing generalisation across heterogeneous clients. Meanwhile, quantisation-aware training (QAT) reduces model size and transmission cost while preserving accuracy. Extensive experiments on real CSI data from 30 participants demonstrate that FFQ improves multi-class HAR accuracy by 4.29% and binary fall detection by 5.55% compared to raw fusion models. Furthermore, model compression with QAT achieves a 47% reduction in communication overhead while maintaining accuracy comparable to state-of-the-art methods.