Realizing real time monitoring and controlling bio-signals · Realizing real time monitoring and controlling bio-signals Daniel Berckmans M3 – BIORES Katholieke Universiteit Leuven

Realizing real time monitoring and controlling bio-signals

Daniel BerckmansM3 – BIORES

Katholieke Universiteit LeuvenBelgium

Philips EindhovenApril 11 2008

M3-BIORES, K.U.LEUVEN2

Ing. KAREL DE BODT

2

Head: Prof. Daniel Berckmans

K.U.Leuven DIVISION M3-BIORESMeasure, Model and Manage Bioresponses

Ir. VO TAN THANH

Ir. NILA ALBAN

Dr. TADIWOS ZERIHUN DESTA

Ir. SEZIN EREN OZCAN

Ir. SARA FERRARI

Ir. JAN DEKOCK

Ir. TOON LEROY

Ir. JORIS LEFEVER

Ir. GUIDO DE BRUYNE

Ir. KRISTIEN VAN LOON

Prof. JEAN-MARIE AERTS

Prof. ERIK VRANKEN

Ir. OZLEM CANGAR

Ir. SONG XIANGYU

Ir. X

Ir. X

Dr. Claudia Bahr

Technical assistance

PRIVATE COMPANIES

LUDO HAPPAERTS

Ing. JEAN-LOUIS LEMAIRE

Imperfectly mixed fluids Bioresponses 1 Process output & environment

SecretaryANN VAN

GINDERACHTER

Ir. DRAGANA MILJKOVIC

Ir. PIETER SCHIEPERS

Dr. STIJN QUANTEN

CoordinatorsBioresponses 2

Ir. SEBASTIAN DE BOODT

BioRICS NV, Belgium

Ir. X

BioRICS NVIr. KIM BATSELIER

Ir. FREDERIK JANSEN

Ing. MIHAJLO MILUTINOVIC

Ir. X

Ir. X

Ir. X

Ir. X

Dr. VASILEIOS EXADAKTYLOS

Ir. MITCHELL SILVA

Sound analysis and bioresponses

Ir. X


BioRICS n.v.

- 2006:

- K.U. Leuven, LRD (o1972): 56 spin-offse.g. LMS, Ubizin, Thromb-X, ....


Problem• Livestock farming in the past …

Farmer had the time to use audio-visual scoring


•Today however…

Low price of product

High number of animals

More welfare problemsLess available time per animal


Market numbers

258 million ton meat/year

7 billion pigs

40 billion chicken


A living organism:Complex


Complex Individual

Hea

rtbe

at (b

pm)

Time (s)

A living organism:


Identical Individually different


Complex Individual Time-Varying

A living organism:

TIME (HOURS)

0 1 2 3 4 5

HEA

T PR

OD

UC

TIO

N (W

/KG

)

11

12

13

14

15

16

17

MEASUREDMODELLED (1ST ORDER)MODELLED (2ND ORDER)

5 days old

TIME (HOURS)

0 1 2 3 4 5

HEA

T PR

OD

UC

TIO

N (W

/KG

)7

8

9

10

11

12

13

MEASUREDMODELLED (1ST ORDER)

30 days oldExample: Heat production of broiler chickens

Different model order


Complex Individual Time-Varying Dynamic

A living organism:

Measure

Model

Manage

In an on-line way

Living organism = CITD - system

Complex Individual Time-Varying Dynamic

M3-BIORES


What happens today in other process control


Desired direction

General methodology: Conditions for process control

1FEEDBACK

2PREDICTION

MODEL-BASED CONTROLLER

3

ProcessPosition Steering

wheel Direction

MEASUREMEASURE


Control of “Biological Responses”

MODEL BASED CONTROLLER

DESIRED BIORESPONSE

DYNAMICBIORESPONSE

MICRO-ENVIRONMENT

Process

1FEEDBACK

PREDICTION

2

3


Examples


Control of the crawl trajectory of larvae of Calliphora vicina


Light intensity crawl trajectory

Control of the crawl trajectory of larvae of Calliphora vicina


t t

y(t)u(t)

Response of crawl direction to variations in ligth


MEASURE MEASURE


-45.00

0.00

45.00

90.00

135.00

180.00

225.00

270.00

315.00

360.00

0 3 6 9 12 15 18 21 24 27 30 33 36

Time

Cra

wl d

irect

ion

(°)

270.00 180.00 12.55

315.00 270.00 9.72

45.00 90.00 13.59

90.00 180.00 15.77

225.00 90.00 12.77

135.00 270.00 9.60

0.00 0.00 15.60

180.00 0.00 15.61

Responses of crawl direction to steps in light direction


PREDICTION


FEEDBACK

MODEL-BASED CONTROLLER

Active control of crawl direction of larvae

MEASURE MEASURE


Active control of crawl direction of 6 larvae


Control of the growth trajectory of chickens


Day 1

Day 42

Weight

40 g

> 2000 g

Problems!

Leg disordersAscitesSudden death syndrome…

Active on-line growth trajectory control• Chickens


Possible solution:Growth restriction + compensatory growth

= growth control

Day 1 Day 42

Weight

Growth restrictionCompensatory growth


Control diagram

TemperatureLight scheduleFeed quantityFeed quality

Weight trajectory

t

Prediction

Model

Model based controller

Feedback


EXP2001-3 - afdeling2

Tijd (dagen)0 10 20 30 40

Gew

icht

(gra

m)

0

500

1000

1500

2000

2500

Gestuurd groeitrajectReferentie groeitrajectGroeitraject controle groep

Time (days)

Wei

ght (

gram

s)

Controlled growth trajectoryReference growth trajectoryGrowth trajectory of control group

PLF control results in reduction of mortality (12 exp, 2900 animals each) of 4%

∆ = 3.7% - 6.0%


Optimisation of physicaltraining of race horses


v

Heart rate

Lactate conc.

VO2

Running speed Heart rate

Optimisation of physical training of race horses


Polar equine HR monitor

Sensors

Garmin forerunner GPS


Velocity and Heart rate - Kyrielle (Bert) 01-01

0

5

10

15

20

25

30

0:00:00 0:05:00 0:10:00 0:15:00 0:20:00 0:25:00

time (u:mm:ss)

velo

city

(km

/u)

0

20

40

60

80

100

120

140

hear

t rat

e (b

pm)

VelocityHeart rate



40

50

60

70

80

90

100

110

120

0:00:00 0:10:00 0:20:00 0:30:00 0:40:00 0:50:00 1:00:00

time(h:mm:ss)

hear

t rat

e (b

pm

Controlled heart rateTarget heart rate



Time-constant of HR over time

0

10

20

30

40

50

60

70

Week 0 Week 1 Week 2 Week 3 Week 4Time (date)

TC (s

ec)

TC



Model based monitoring of physical & mental performance

(AC Milan)


Physical trainingPhysical

performance

Perf

orm

ance

Total performance = a. Mental performance + b. Physical performance

Mental performance

Mental training

Process

CITD

CITD


Training exercises Performance

Body

Process

MEASURE(Inmotio)

MEASURE(Inmotio + Hosand)


Heart Rate

Physical Activity

Reference mental status

???

Time

On-line mental monitor

Mental algorithm

Mental monitoring


MINDROOM

Reference mental status


Demo: mental monitoring


Mindroom data (1133 and 1156)

-1.5

-1

-0.5

0

0.5

1

1.5

27/0

3/20

06

31/0

3/20

06

3/4/

2006

7/4/

2006

13/4

/200

6

19/4

/200

6

24/4

/200

6

27/4

/200

6

1/5/

2006

2/5/

2006

3/5/

2006

4/5/

2006

10/5

/200

6

27/0

3/20

06

31/0

3/20

06

7/4/

2006

11/4

/200

6

Date (ddmmyy)

Men

tal s

tatu

s [

pos,

neg

or n

eutr

al]

MINDROOM

11561133

Mindroom vs. Mental algorithm


Mindroom vs. Mental algorithmMental algo vs Mindroom

-1.5

-1

-0.5

0

0.5

1

1.5

27/0

3/20

06

31/0

3/20

06

3/4/

2006

7/4/

2006

13/4

/200

6

19/4

/200

6

24/4

/200

6

27/4

/200

6

1/5/

2006

2/5/

2006

3/5/

2006

4/5/

2006

10/5

/200

6

27/0

3/20

06

31/0

3/20

06

7/4/

2006

11/4

/200

6

Date (ddmmyy)

Men

tal s

tatu

s [

pos,

neg

or n

eutr

al]

MINDROOM

MENTAL ALGO

11561133


Physical trainingPhysical

performance

Perf

orm

ance

Total performance = a. Mental performance + b. Physical performance

Mental performance

Mental training

Real-time process control

CITD

BioRICS

BioRICSCITD


Application Examples


Stressmonitoring

AccelerometerECGMobile phone

BioRICS serverUSB

transceiver


Monitoring and control of physical performance


BioRICS serverUSB

transceiver


Weight Control


BioRICS serverUSB

transceiver


Driver Sleepiness

Temperature sensorECG

BioRICS serverUSB

transceiver

Pedal + steer input


Bidirectional Wireless link 2

Bidirectional Wireless link 1

Sensor Modules Central ModuleECG module

Accelerometer module1

Accelerometer module 3

…PDA

orMobile w

ww

.bio

rics.

com

Temp. module

Central Module :

• Transceiver connected to PDA or mobile (mini-USB)

• Responsible for synchronization of the signals from the different sensor modules

General hardware scheme

2m


ECG sensor module : sampling freq : 300 Hz

Temperature module : sampling freq : 1/60Hz (1 sample/minute)

Accelerometer modules : sampling freq : 200 Hz

g – range : 6g ; 10g ; 25g

└ Strongly dependent on application field

Bidirectional Wireless link 1 : wireless range : 2m

low power (e.g. recharging after 1 week)

Central Module : USB transceiver

Synchronization of the different signals form the sensor modules

Data transmission via mobile network to BioRICS server

Specifications


Complex Algorithms (high level language, e.g. Matlab)

Low level language (C)

Translation

Compiler


10 Products

11 Patents

applications

Bicycle helmets

Race horses

Chickens

Mussels

Professional Cyclists

Intensive Care

ESA

Daphnia

Tubifex


Thank you for your attention…

• For more information you can always check our website:

• http://www.m3-biores.be• http://www.biorics.com

Documents

Realizing real time monitoring and controlling bio-signals · Realizing real time monitoring and controlling bio-signals Daniel Berckmans M3 – BIORES Katholieke Universiteit Leuven