Breathing Volume Monitoring during Sleep fr from Afar Using - - PowerPoint PPT Presentation

breathing volume monitoring during
SMART_READER_LITE
LIVE PREVIEW

Breathing Volume Monitoring during Sleep fr from Afar Using - - PowerPoint PPT Presentation

Continuous and Fine-grained Breathing Volume Monitoring during Sleep fr from Afar Using Wireless Signals Phuc Nguyen , Xinyu Zhang, Ann Habower, and Tam Vu University of Colorado, Denver, University of Wisconsin-Madison University of Colorado


slide-1
SLIDE 1

Continuous and Fine-grained Breathing Volume Monitoring during Sleep fr from Afar Using Wireless Signals

Phuc Nguyen, Xinyu Zhang, Ann Habower, and Tam Vu

University of Colorado, Denver, University of Wisconsin-Madison University of Colorado School of Medicine

slide-2
SLIDE 2

Sleep Study in Hospitals

slide-3
SLIDE 3

Asked to sleep normally

slide-4
SLIDE 4

Noncontact Respiratory Measurement of Volume Change Using Depth Camera (Meng-Chieh Yu et. al.) Laser 3-D measuring system and real-time visual feedback for teaching and correcting breathing (Klemen Povšič et. al.) Smart Homes That Monitor Breathing and Heart Rate (Fadel Adib et. al)

Existing technologies

slide-5
SLIDE 5

We proposed WiSpiro Tx/Rx

slide-6
SLIDE 6

WiSpiro works even with posture changes during sleep

Original Posture New Posture

slide-7
SLIDE 7

Tx/Rx

Idea: WiSpiro analyzes the wireless reflection to compute distance change to the body

dexhale dinhale

  • Phase information:

𝝌 = 2𝜌

𝒆𝒋𝒕𝒖𝒃𝒐𝒅𝒇 𝑥𝑏𝑤𝑓𝑚𝑓𝑜𝑕𝑢ℎ

Distance change (Chest displacement) Breathing Volume

slide-8
SLIDE 8

Challenges

slide-9
SLIDE 9

Body movement causes inaccurate chest movement estimation

Challenges: Body Movements

slide-10
SLIDE 10

Challenges: Non-uniform movement

Different location on the chest move differently while reflecting the same breathing volume

slide-11
SLIDE 11

The wireless signal might be blocked by human body part

Challenges: Occlusion

Tx/Rx

slide-12
SLIDE 12

System Design

slide-13
SLIDE 13

System Design

Radar data Spirometer data

Chest movements Breathing Volume Correlation between chest movement and breathing volume Movement patterns of each area on the chest

Radar data

Radar Navigator Volume Estimator One-time Trainer

Navigating Radar to New Location Chest movements Estimated Breathing Volume Body Movement Detection Area Recognition Posture Detection

slide-14
SLIDE 14

One-Time Trainer

Setup

Tx/Rx Spirometer

slide-15
SLIDE 15

One-Time Trainer

Radar Spirometer Alignment Neural Network Training

Correlation of chest movement and breathing volume

FFT Feature Extraction Breathing Signature

Low pass filter DC Remover

Peaks and Cross Zero Analyzer

Low pass filter

Peaks and Cross Zero Analyzer

slide-16
SLIDE 16

Volume Estimator

Radar

Chest & body movement tracker

Body movement?

Estimating Volume

NO YES

To Radar Navigator Correlation Function from One-Time Trainer

Low pass filter DC Remover

Breathing Volume

slide-17
SLIDE 17

Radar Navigator

Small movement Occlusion Large movement Area Localization Posture Detector

TX RX

Navigation Controller

Machine Learning Technique (Focus on MFCC features) Analyze wireless signal from a scanning process

slide-18
SLIDE 18
  • Human posture can be approximated from angle

between:

  • Human’s back and the bed surface
  • Human body and his legs

Radar Navigator: Posture Estimation

Scanning Path

Tx/Rx

slide-19
SLIDE 19

Putting together

slide-20
SLIDE 20

Putting together

16x

slide-21
SLIDE 21

System Performance

slide-22
SLIDE 22

Volume estimated in stationary case vs. spirometer measurement Mean error of 0.021l, max error of 0.051l

System Performance

Experiment Setup

Experiment Setup

slide-23
SLIDE 23

System Performance

Sensitivity Analysis

The accuracy distribution of area localization technique

slide-24
SLIDE 24
  • Conclusion:
  • Infer breathing volume from chest movement using

wireless signal

  • Estimate human posture using wireless signal
  • Localize where the radar is beaming to
  • Thoroughly evaluate the system
  • Future Work
  • Improve the area localization and posture detection

techniques

  • Conduct a clinical trial to verify the system performance
slide-25
SLIDE 25

Thank You!