AIGC for Wireless Sensing: Diffusion-Empowered Human Activity Sensing

Abstract

Machine learning (ML) for wireless communications and networking requires abundant, high-quality radio frequency (RF) data, yet collecting this data is often challenging and costly. To address this, we propose RF-ACCLDM (Activity Class Conditional Latent Diffusion Model), a framework designed to generate synthetic RF data for human activity sensing. Operating in latent domains, RF-ACCLDM produces RF data conditioned on activity class labels, supporting various RF technologies and modalities, including Radio Frequency Identification (RFID), WiFi Channel State Information (CSI), and Frequency-Modulated Continuous Wave (FMCW) radar. Training of the framework is universal and achieves consistent quality. This approach outperforms plain diffusion on raw RF data in terms of quality, computational efficiency, and scalability. Using the Frechet Inception Distance (FID) metric, we measure and demonstrate the fidelity of the generated data. Through extensive ablation studies, we demonstrate the effects of varying latent dimensions, noise schedules, and training configurations, validating the robustness of RF-ACCLDM. Furthermore, we evaluate the performance of our model in downstream tasks such as RF-based 3D human pose tracking and human activity recognition (HAR), where it can match or even outperform counterparts trained solely on real data. Our approach offers a scalable and cost-effective solution for enhancing ML-based schemes in wireless sensing and communications.