RoVi: Robust Vital Sign Reconstruction With Generative AI Under Irregular Body Motions
Abstract
Wireless vital sign sensing extracts respiratory features from signal phase variations induced by chest movements. However, motions of other body parts produce superimposed signals, resulting in indistinguishable anomalous segments that obscure respiratory extraction. Existing approaches primarily rely on regular motion classification to specifically restore degraded respiratory features, but struggle with irregular body movements, which are characterized by interdependence of body parts and diverse motion amplitudes. These challenges make vital sign recovery highly susceptible to motion variations. In this paper, we propose a robust vital sign reconstruction method with Generative AI under irregular body motions (RoVi). RoVi using WiFi signals operates through four key components: Revelation, Identification, Elimination, and Restoration. Revelation establishes a Magnifier model, leveraging spatial and temporal information to segment and amplify signal characteristics. Identification applies contrastive learning to enhance motion representations and anomaly separability in clustering. Elimination removes anomalous segments before restoration, avoiding dependency on specific motion contents. Restoration employs GAN to recover missing segments from normal respiration features, enabling subject-agnostic restoration under stable conditions and subject-specific prediction for non-stationary respiration. Experiments on 16 subjects demonstrate RoVi achieves 94.5% reconstruction accuracy under irregular body motions, surpassing existing approaches and demonstrating strong robustness across diverse unknown motions and subjects.
