Scholarlink

<p>Continuous, clinically reliable non-contact monitoring of multiple patients’ vital signs remains a significant technological challenge in care settings. This paper introduces a systematically constructed radar-based dataset designed to test methods for simultaneous multi-patient vital sign monitoring. Developed with Ostrava University Training Hospital, the dataset includes recordings from two-three advanced medical simulation mannequins (SimMan 3G Plus), emulating a wide range of physiological states—from healthy resting to acute emergencies (apnea, cardiac arrest, severe respiratory distress). We varied sensor geometry (top, frontal, lateral views at 1-4 m, 0°/45° angles) and radar parameters (ADC samples, chirp loops, ramp times, frame rates, gains), yielding over 100 uniquely configured sessions. Preliminary beamforming-based processing achieves mean heart-rate and breathing-rate errors near clinical thresholds (MAE &#xa0;≈&#xa0;6.6 bpm for HR, 1.47 bpm for RR), demonstrating the dataset’s utility for developing advanced signal processing and machine-learning pipelines. In keeping with FAIR principles, all data are fully documented and publicly accessible, supporting reproducible research toward noninvasive multi-patient monitoring systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SiViS: Simulated multi-patient physiological clinical states for advanced vital sign radar monitoring research

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月6日

查看全文
  • Karla Miriam Reyes,
  • Ankit Gupta,
  • Arthur Grosmaire,
  • Silvie Procházková,
  • Petr Matouch,
  • Ivona Závacká,
  • Josef Škroch,
  • Martin Cerny

摘要

Continuous, clinically reliable non-contact monitoring of multiple patients’ vital signs remains a significant technological challenge in care settings. This paper introduces a systematically constructed radar-based dataset designed to test methods for simultaneous multi-patient vital sign monitoring. Developed with Ostrava University Training Hospital, the dataset includes recordings from two-three advanced medical simulation mannequins (SimMan 3G Plus), emulating a wide range of physiological states—from healthy resting to acute emergencies (apnea, cardiac arrest, severe respiratory distress). We varied sensor geometry (top, frontal, lateral views at 1-4 m, 0°/45° angles) and radar parameters (ADC samples, chirp loops, ramp times, frame rates, gains), yielding over 100 uniquely configured sessions. Preliminary beamforming-based processing achieves mean heart-rate and breathing-rate errors near clinical thresholds (MAE  ≈ 6.6 bpm for HR, 1.47 bpm for RR), demonstrating the dataset’s utility for developing advanced signal processing and machine-learning pipelines. In keeping with FAIR principles, all data are fully documented and publicly accessible, supporting reproducible research toward noninvasive multi-patient monitoring systems.