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.
Ying-Ying Zhao, Tie Qiu, Ning Chen et al.· IEEE Transactions on Mobile...· 0 citations
Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.
Yihao Wu, Chen-Yi Xu, Li-Qi Yan et al.· arXiv.org· 0 citations
This work proposes RAVEL-FCL, a generative replay-based framework for federated continual learning that integrates an improved generative model based on Rebooting ACGAN with multi-level feature alignment to ensure consistency and employs Elastic Variational Continual Learning on the server to probabilistically regularize the global model and preserve past knowledge.
Yurui Zhou, Jia Hu, G. Min et al.· ACM Transactions on Autonomo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
