Research map / Adversarial robustness and security / Certified and empirical robustness
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| RF-based conditional adversarial model vs previous RF state of the art (Zaffaroni et al.) | Ours · Sleep staging from RF signals, 4-class, subject-independent | accuracy: 0.641 -> 0.798 | Helped |
| same comparison on Cohen's kappa vs Tataraidze et al. | Ours · Sleep staging from RF signals, 4-class, subject-independent | Cohen's kappa: 0.49 -> 0.70 | Helped |
| RF model vs cardiorespiratory-based systems | Ours · Sleep staging from RF signals, 4-class, subject-independent | accuracy: 71% -> 79.8% | Helped |
| RF model vs EEG-based systems | Ours · Sleep staging from RF signals, 4-class, subject-independent | accuracy: 83% -> 79.8% | Hurt |
| evaluate across subjects (leave-subject-out) | Ours · Sleep staging from RF signals, 4-class, subject-independent | per-subject accuracy: 2.9% | No clear effect |
| use adversary to remove source-specific information (ablation) | Ours · same dataset, Figure 5 | source loss and test loss | Helped |
| CNN alone vs adding RNN on top (ablation) | Ours · t-SNE of one subject | separation of Light vs Deep sleep | Helped |
Closest papers by meaning
- SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals (ICML 2024 · similarity 0.87)
- Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.82)
- Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging (NeurIPS 2026 · similarity 0.81)
- Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination (NeurIPS 2024 · similarity 0.81)
- Generalizable Sleep Staging via Multi-Level Domain Alignment (AAAI 2024 · similarity 0.81)
- Sleep-Like Unsupervised Replay Improves Performance When Data Are Limited or Unbalanced (Student Abstract) (AAAI 2024 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.