DC-PFL: A dynamic clustering-based personalized federated learning method for human activity recognition

Human Activity Recognition (HAR) is essential in pervasive computing, healthcare, and human–computer interaction, where accurate interpretation of motion data underpins intelligent decision-making. Federated Learning (FL) enables privacy-preserving model training across distributed clients without sharing raw data, but suffers from degraded performance under Non-Independent and Identically Distributed (Non-IID) data, a common challenge in HAR due to user diversity and device heterogeneity. To address this, Personalized Federated Learning (PFL) introduces client-specific modeling, often via clustering. However, most existing approaches adopt static clustering strategies, lacking adaptability to dynamic changes in client data distributions. In this work, we propose DC-PFL, a Dynamic Clustering-based Personalized Federated Learning framework that performs round-wise client clustering using lightweight statistical features, like Average Peak Frequency (APF), percentiles, and Median Absolute Deviation (MAD) derived from local model parameters. This design ensures efficient and privacy-preserving similarity estimation across clients. By dynamically adjusting clusters during training, DC-PFL enables fine-grained personalization, better generalization, and improved robustness to Non-IID conditions. Experimental results on HAR benchmarks demonstrate that DC-PFL achieves superior performance in both accuracy and convergence speed compared to existing methods, including FedCHAR and standard FL baselines, validating its effectiveness in real-world federated HAR scenarios.