RF Vital Sign Sensing Under Free Body Movement
summary
System combines direct RF sensing during static windows with movement power estimation and LSTM predictors to infer heart rate and respiration under ambulant activity. Prototype runs on a commodity radar sensor, uses a baseline-from-static plus instant calibration and adaptive training for cross-subject generalization without labelled data, and reports average errors of 5.57 bpm (HR) and 3.32 bpm (RR) across multiple subjects, substantially outperforming frequency-based baselines.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 0:11Background
- 1:16Current Systems
- 2:07General Model
- 3:02Demonstration
- 4:38Existing Methods
related talks
01h 13mHealth Monitoring with Wireless Sensors and Machine Learning
06mHeartQuake: Accurate Low-Cost Non-Invasive ECG Monitoring Using Bed-Mounted Geophones
06mBodyCompass: Monitoring Sleep Posture with Wireless Signals
20mInteracting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency ...
22mRunning, walking, sitting or biking? - Motion prediction with acceleration and rotation
27mDissecting ActivityRecognition with Multi-Sensor Simulation and Its Practical Deployment
06mRobust Unsupervised Factory Activity Recognition with Body-worn Accelerometer Using Temporal ...
06mVibroSense: Recognizing home activities by deep learning subtle vibrations on an interior ...