Towards Smart Health Monitoring System for Elderly People Achraf - - PowerPoint PPT Presentation

▶
towards smart health monitoring system for elderly people
SMART_READER_LITE
LIVE PREVIEW

Towards Smart Health Monitoring System for Elderly People Achraf - - PowerPoint PPT Presentation

Aug 23, 2022 568 likes •1k views

The 4th International Conference on Awareness Science and Technology August 21-24, 2012, Korea University, Seoul, Korea Towards Smart Health Monitoring System for Elderly People Achraf Ben Ahmed, Yumiko Kimezawa, Abderazek Ben Abdallah

slide-1
SLIDE 1

The 4th International Conference on Awareness Science and Technology August 21-24, 2012, Korea University, Seoul, Korea

Towards Smart Health Monitoring System for Elderly People

Achraf Ben Ahmed, Yumiko Kimezawa, Abderazek Ben Abdallah Graduate School of Computer Science and Engineering, Adaptive Systems Laboratory The University of Aizu, Aizu-Wakamatsu ,Japan Email:m5151161@u-aizu.ac.jp

9/27/2012 1

slide-2
SLIDE 2
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 2

slide-3
SLIDE 3
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 3

slide-4
SLIDE 4

Background

  • Electrocardiography is a well known method for heart

diagnosis – Used as one of major diagnosis for conventional health monitoring

  • Electrocardiography main processing challenges arise

from: – High computational demand for processing huge amount of data under:

  • Strict time constraints
  • Relatively high sampling frequency
  • Life critical conditions

9/27/2012 4

slide-5
SLIDE 5

Background

  • Most ECG systems use Pan-Tompkins approach

based on QRS complex

– Usage of R-peak as a reference point – Accurate detection of R-peak is a must

  • R-peak detection might be inaccurate
  • Traditional techniques may fail in detecting

serious heart problems

9/27/2012 5

slide-6
SLIDE 6

Background

s mV

Heart period detection

R R R Heart period

9/27/2012 6

slide-7
SLIDE 7

Background

Problems of period detection

R R’

R-R’ Interval

R T

R-T Interval

t mV

Faulty analysis

True Interval True Interval

False Interval False Interval

9/27/2012 7

slide-8
SLIDE 8

Background

  • The monitoring part is crucial for the real time

diagnosis that characterized the ECG signals

  • Existing Methods :
  • manually-intensive work flow for data acquisition,

formatting, and visualization

  • most often relying on multiple serial processes and

several software packages

9/27/2012 8

slide-9
SLIDE 9

Background :contributions

  • We propose an efficient ECG heart period

detection algorithm, Period Peak Detection (PPD)

  • A hardware implementation (MPSoC) to deal with

the high requirement of biomedical data : real time analysis, high accuracy, portability

  • An interactive real time interface for the

monitoring of the ECG signal targeted for elderly people

9/27/2012 9

slide-10
SLIDE 10
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 10

slide-11
SLIDE 11
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 11

slide-12
SLIDE 12
  • Based on autocorrelation function (ACF).

Period detection Peak detection

Reading data Derivation Autocorrelation Find interval Calculate threshold Find peaks Store results

PPD Algorithm

9/27/2012 12

slide-13
SLIDE 13

PPD Algorithm- Derivation

  • Emphasis of the signal peaks
  • Implementation with simple operations (-)

] [ ] 1 [ ) 1 ( ] [ ] 1 [ ) ( n y n y n n n y n y t t y          

(step) me current ti : , signal) ECG

  • rignal

(filtered data sampling current : ] [ n t n y

9/27/2012 13

slide-14
SLIDE 14

Time(sec) Derivative of the ECG signal

PPD Algorithm- Derivation

Signal peaks P, Q, R, S, T, and U Derivative amplifying R peaks

9/27/2012 14

slide-15
SLIDE 15

PPD Algorithm- Autocorrelation

  • Measures the degree of association between

values in a series separated by some lags

  • Periodicity analysis of signals

  

N n y

L n y n y L R ] [ ] [ ] [

ation autocorrel the

  • f

lags

  • f

number the : L period get the

  • t

ns calculatio for the needed times

  • f

number the : signals ECG Filtered : ] [ function ation autocorrel the : N n y Ry

9/27/2012 15

slide-16
SLIDE 16

Derivative of the ECG signal The ACF on the derivative Derivative amplifying R peaks AC of the derivative characterized by significant periodic peaks having the same value as the period of the ECG signal

PPD Algorithm- Autocorrelation

9/27/2012 16

slide-17
SLIDE 17

Period detection- Find interval

Find maximum value Reduce negative value Peak detection from ACF result Find base points Sort base points Calculate interval Renew next start index

9/27/2012 17

slide-18
SLIDE 18

Period detection- Find interval

Reduce negative value Peak detection from ACF result Find base points Sort base points Calculate interval Renew next start index

9/27/2012 18

Find maximum value

used to determine a threshold

slide-19
SLIDE 19

Period detection - Find maximum value

9/27/2012 19

slide-20
SLIDE 20
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 20

slide-21
SLIDE 21

System architecture

9/27/2012 21 ADC 1 ADC 12 FIR 1 FIR 12

SDRAM

MPSoC ECG Analysis Signal reading Filtering Analysis Server side Client side

System architecture IRI

slide-22
SLIDE 22

9/27/2012 22 ADC 1 ADC 12 FIR 1 FIR 12

SDRAM

MPSoC ECG Analysis

Signal reading Filtering Analysis

System architecture

slide-23
SLIDE 23

Hardware prototyping

9/27/2012 23

slide-24
SLIDE 24
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture

  • System architecture
  • The interactive real-time interface (IRI)
  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 24

slide-25
SLIDE 25

System architecture

9/27/2012 25 ADC 1 ADC 12 FIR 1 FIR 12

SDRAM

MPSoC ECG Analysis Signal reading Filtering Analysis Server side Client side

Hardware prototyping IRI

slide-26
SLIDE 26

interactive real-time interface (IRI)

9/27/2012 26

Server side Client side

slide-27
SLIDE 27

The interactive real-time interface (IRI)

9/27/2012 27

slide-28
SLIDE 28
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture – The interactive real-time interface (IRI)

  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 28

slide-29
SLIDE 29

Hardware Prototyping Results

9/27/2012 29

slide-30
SLIDE 30

Performance evaluation

9/27/2012 30

slide-31
SLIDE 31

9/27/2012 31

Performance evaluation

slide-32
SLIDE 32

9/27/2012 32

Performance evaluation

slide-33
SLIDE 33
  • Background
  • Contributions

– Period-Peak Detection (PPD) Algorithm – System architecture – The interactive real-time interface (IRI)

  • Design and evaluation results
  • Conclusion and future work

Contents

9/27/2012 33

slide-34
SLIDE 34
  • Period-Peak Detection (PPD) Algorithm
  • Scalable Multiprocessor Implementation for

ECG Analysis in Multi-lead Records

  • Sufficient processing speed & 69 % accuracy
  • Interactive real-time interface (IRI)

Conclusion

9/27/2012 34

slide-35
SLIDE 35

Calculation process of ACF

  • Assumption
  • The ECG signals are 9 samples.

] [ ] [ ] [

8

L n y n y L

n y

R

  

is y , When   L n

1 2 3 4 5 6 7 8 1 2 1 2 1 2

] [n y Signal t Time

9/27/2012 35

slide-36
SLIDE 36

1 2 3 4 5 6 7 8 15 6 4 10 4 2 5 2

Calculation process of ACF

Ry

L

  • Results

1 2 1 2 1 2

] [n y

Ry

L

9/27/2012 36

slide-37
SLIDE 37

1 2 3 4 5 6 7 8 15 6 4 10 4 2 5 2

Calculation process of ACF

Ry

L

Ry

L

Period Period

  • Results

1 2 1 2 1 2

] [n y

9/27/2012 37

slide-38
SLIDE 38

1 2 3 4 5 6 7 8 15 6 4 10 4 2 5 2

Calculation process of ACF

9/27/2012 38

Ry

L

Ry

L

Period Period Every 3 samples are periodic

  • Results

1 2 1 2 1 2

] [n y

slide-39
SLIDE 39

Calculation process of ACF (2/6)

] [ ] [ ] [ ] [ ] [

8 8

n y n y n y n y

n n y

R

    

 

 

1 2 1 2 1 2

] [n y Signal

1 2 1 2 1 2

] [n y Signal

× × × × × × × × ×

15 ] [ 

y

R

Calculation

9/27/2012 39

slide-40
SLIDE 40

Calculation process of ACF (3/6)

] 1 [ ] [ ] 1 [

8

  

n y n y

n y

R

1 2 1 2 1 2 1 2 1 2 1 2 × × × × × × × ×

6 ] 1 [ 

y

R

] [n y ] [n y

Zero (n-L < 0) No calculation (n > 8) Calculation

9/27/2012 40

slide-41
SLIDE 41

Calculation process of ACF (4/6)

] 2 [ ] [ ] 2 [

8

  

n y n y

n y

R

1 2 1 2 1 2 1 2 1 2 1 2 × × × × × × ×

4 ] 2 [ 

y

R

] [n y ] [n y

Zero (n-L < 0) No calculation (n > 8) Calculation

9/27/2012 41

slide-42
SLIDE 42

Calculation process of ACF (5/6)

] 3 [ ] [ ] 3 [

8

  

n y n y

n y

R

1 2 1 2 1 2 1 2 1 2 1 2 × × × × × ×

10 ] 3 [ 

y

R

] [n y ] [n y

Zero (n-L < 0) No calculation (n > 8) Calculation

9/27/2012 42