Services of Ambient Assistance for Elderly and/or Disabled Person

in Health Intelligent Habitat

Amina Makhlouf

, Nadia Saadia

and Amar Ramdane-Cherif

LRPSI Laboratory, University of Science and Technology Houari Boumediene, Algiers, Algeria

LISV Laboratory, University of Versailles-Saint-Quentin-en-Yvelines, Versailles, France

Keywords: Ambient Assistance, Services of Ambient Assistance, Intelligent Habitat Health, Petri Net.

Abstract: The life expectancy of people is increasing and related to that is an increase in the elderly population. The

idea is to ensure that the elderly stay longer in their homes. A lot of projects work on ways allowing elderly

persons to stay at home, these projects has focused to assess how a person copes by continuous monitoring

of his/her activities through sensors measurements. The objective of this paper is to design a multimodal

software system for managing two services of ambient assistance for elderly and/or disabled person in

intelligent habitat health: Symptom Detection Service and Comfort Service. These services use several

sensors installed in the home and on the persons, to collect information at any time about location and state

of the person, and to ensure his comfort in the home. For helping decision maker choose appropriate

assistance for these persons. This multimodal software platform is modeled by Colored Timed and

Stochastic Petri nets (CTSPN) simulated in CPNTools.

1 INTRODUCTION

The world’s older population has been growing

more numerous for centuries, but the pace of growth

has accelerated. The global population age 65 or

older was estimated at 17.5% in 2011, an increase of

3.6% just since 1991. By 2060, this proportion is

projected to increase to 29.5% (Dupaquier, 2006). In

Algeria the older population (60 or more) is growing

at a rapid pace. It was 5.7% of the total population in

1987; it reached to 7.4% in 2013. In 2050, it will

reach 20.5% (Nkoma, 2011).

Today, the trend of older population in the world

yields a lack of places and workers in institutions

able to take care of elderly people. Especially as the

elderly population is prone to several diseases of old

age, like diabetes, rheumatism, hypertension, and

especially Alzheimer’s disease. Researcher teams all

over the world try to tackle this issue by working on

ways to maintain elderly people in their own home

as long as possible; they proposed the ambient

assistance. Ambient Assistance is a concept

focused on the use of technology as a way to

improve the independence and welfare of elderly or

disabled people, at their homes. For example, some

of them aim at detecting and handling emergency

situations, helping the target users to accomplish

activities of daily living (Perriot, 2013). Remote

health monitoring functionalities and activity

recognition (Fleury 2010), (Fleury, 2011) (Murdoch,

2013); are also considered, in particular for patients

with Chronic Obstructive Pulmonary Disease

(COPD) (Noury, 2013).

Objective of ambient assistance is to achieve

three major goals; (1) The first is to assess how a

person copes by continuous monitoring of his/her

activities through sensors measurements, (2) The

second is to ease daily living by compensating one’s

disabilities, (3) The third is to ensure security by

detecting situations that is like a fear for the elderly

persons.

In this paper, we contribute to the field of

automatic monitoring by conducting a study of the

daily activities of elderly people in their own home,

in order to collect information at any time about

location and state of the person, and to ensure his

comfort at home, offering several ambient assisted

services. For helping decision maker choose

appropriate assistance for these persons. In the next

section; we will define the ambient assistance for the

elderly and/or disabled persons. Section 3; presents

an overview of ambient assistance. We present in

section 4, our architecture. Discussions and results

225

Makhlouf A., Saadia N. and Ramdane-Cherif A..

Services of Ambient Assistance for Elderly and/or Disabled Person in Health Intelligent Habitat.

DOI: 10.5220/0005147202250231

In Proceedings of the International Conference on Agents and Artiﬁcial Intelligence (ICAART-2015), pages 225-231

ISBN: 978-989-758-074-1

 2015 SCITEPRESS (Science and Technology Publications, Lda.)

are presented in section 5.

2 AMBIENT ASSISTANCE

Ambient Assistance is an intelligent environment in

which technology is used as a way to improve the

welfare and independence of elder or disabled

people living alone at their homes (Lauterbach,

2013). Among the prominent goals of ambient

assistance are:

 Improve the quality of life of care giving

persons.

 Reduce the need for external assistance.

 Reduce health care costs for the individual and

society.

Ambient Assistance includes several categories

of support application as: Information assistance,

Intelligent environment behavior, Emergency case

prediction, Security and Privacy. Technologies to

develop Ambient Assistance application in these

domains are: (1) Sensing, (2) Reasoning, (3) Acting,

(4) Security, and (5) Interaction. (Foko, 2013)

Ambient Assistance aims to deliver a

professional support in cases where personalized

solutions are needed. It performs intelligent services

that correspond to activities based on the application

of professional knowledge to process a particular

case. It is divided into many types, such as: (Rosas,

2014)

 Emergency treatment Services;

 Autonomy enhancement Services;

 Comfort Services.

3 OVERVIEW OF AMBIENT

ASSISTANCE

In recent years, there has been an increase in the

number of new technologies to improve security and

to monitor the health of resident, using sensors and

other devices.

Taking the activity of daily living (ADL) is an

important parameter for monitoring the person

(Wood, 2008). At the University of Lyon in France,

they have developed a project "AILISA" as showed

in figure 1, which is based on four smart homes

placed in: (Noury, 2013)

1. CHU La Grave (Toulouse)

2. Hospital Charles Foix (Ivry-Sur-Seine)

3. Centre Geriatrique Sud-CGS (Grenoble)

4. HIS at Notre Dame (Grenoble)

The goal of this project is to ensure the home

support for elderly people. Fleury (Fleury, 2010)

used the infrared sensors for detecting presence,

door contacts and the posture detectors (Noury

2013). Vacher (Vacher, 2008) used sound sensors

for speech recognition classify the sound as speech

or sound of everyday life and detect the distress

sentences. Mascolo (Mascolo, 2007) proposed scales

(ADL of Katz, IADL of Lawton and AGGIR) for

detecting the degree of dependency of the person in

their habitat.

Figure 1: AILISA project.

EMUTEM platform (figure 2) (Souidene, 2008) is a

muti-modal platform for medical televigilance

(Medjahed, 2011), it contains:

1. Portable terminal RFPat: two terminals, one

fixed and one mobile (on the person) for

measuring physiological data, detecting

movement and the fall. (Medjahed, 2008)

2. Smart sound sensor ANASON: contains four

modules for the detection of sound events,

classifying son / speech and analyzing of

speech (speech recognition). (Medjahed, 2009)

3. Movement infrared detectors GUARDIAN: to

detect the location and posture of the person at

home. (Guettari, 2010)

Figure 2: EMUTEM Architecture.

Our architecture is based on the collection of

location information and status of persons in their

home and ensure their comfort. Services offered in

this article are among many services that can be put,

adding more sensors and collect more information

about the person.

ICAART2015-InternationalConferenceonAgentsandArtificialIntelligence

226

Figure 3: Global system architecture

4 ARCHITECTURE

The objective of our work is to design a system to

manage two services of ambient assistance for

elderly and/or disabled person in intelligent habitat

health (HIS): Symptom Detection Service and

Comfort Service. This system has as input many

sensors information: the presence, command, heart

rhythm, blood pressure, ambient temperature and

luminosity... etc. Figure 3 shows the general aspect

of our global architecture.

4.1 Symptom Detection Service

In this section, we will focus on data concerning the

elderly and/or disabled person to identify his/her

physical condition. The sensors used are:

Presence: to detect if there is a person in the

home.

Heart Rhythm: an ECG sensor which will

monitor the heart rhythm.

Blood Pressure: a blood pressure sensor.

Body temperature: a temperature sensor.

Location: a GPS for the location of the person

in the home.

4.2 Comfort Service

In this section, we focus on the data relating to the

environment and their setting. So we use:

a. Presence:

presence sensor to detect if there is a

person in the home.

b. Command:

a choice if the command is manual

or automatic.

c. Ambient Temperature:

temperature sensor to

control the temperature in home.

Luminosity: a luminosity sensor.

5 APPLICATION

The system response is the result obtained after

treatment and fusion of inputs data, using Colored

Timed and Stochastic Petri nets. Colored Timed and

Stochastic Petri nets (CTSPN), is a language for the

modelling and validation of systems in which

concurrency, communication, and synchronization

play a major role (Jensen, 2007). In the case of our

application, we have proposed a formalization of the

solution; we consider that inputs the sensor data:

If sensor 1 and sensor 2 then system response

5.1 Symptom Detection Service

For the control of physiological state of the elderly

and/or disabled person, we proposed to control:

heart rhythm is represented by ECG, body

temperature is represented by Tm, and blood

pressure is represented by Pr. For localization, we

determined the location of the person in the home

using GPS. These three sensors randomly generate

two values 0 or 1. A value of 0 indicates that the

person has a physiological problem, and the value 1

indicates that it is in good physiological condition.

For localization, we determined the location of the

person in the home using GPS, for our architecture

Location

Heart rhythm

Temperature

Blood Pressure

Presence

Command

Ambient

Temperature

Luminosity

Services of ambient assistance

Symptom Detection

Service

Comfort Service

Fusion Unit

Decision

in HI

Sensor

ServicesofAmbientAssistanceforElderlyand/orDisabledPersoninHealthIntelligentHabitat

227

we proposed to break up the habitat in four zones

and each zone has a code 1, 2, 3, 4 respectively. As

shown in the table 1 (Bates, 2010) and figure 4:

Table1: Codes Retrieved by the sensors.

Codes 0 1

Presence No person

Person in the

home

Command Manual command

Automatic

Command

Heart

Rhythm

ECG < 55 beats per

minute or

ECG >75 beats per

minute

ECG = 65 +/- 10

beats per minute

Body

Temperature

Tm < 35.9°C

Tm > 37.3°C

Tm = 36.6 +/-

0.7°C

Blood

Pressure

Pr S < 110 mmHg ou Pr

S>150 mmHg ou

Pr D < 70 mmHg ou Pr

D >90 mmHg

Pr S = 130+/- 20

mmHg

Pr D = 80+/-10

mmHg

Figure 4: Representation of environments zones.

The table below shows all combinations of the

proposed inputs in our architecture and the

designation of each case after fusion:

Table 2: Result of the fusion of first service.

Pres

ence

(ECG, Tm,

Pr)

GPS

Result

of the

fusion

Designation

0 (-, -, -) - 0 No person

(1, 1, 1) 1 1

Person in normal

physiological

condition

Person in zone 1

(1, 1, 1) 2 2

Person in normal

physiological

condition

Person in zone 2

(1, 1, 1) 3 3

Person in normal

physiological

condition

Person in zone 3

Table 2: Result of the fusion of first service. (Cont.)

Pres

ence

(ECG, Tm,

Pr)

GPS

Result

of the

fusion

Designation

(1, 1, 1) 4 4

Person in normal

physiological

condition

Person in zone 4

ECG =0

Tm = 0

Pr= 0

1 5

Alarm (heart

rhythm or

temperature or

pressure)

Person in zone 1

2 6

Alarm (heart

rhythm or

temperature or

pressure)

Person in zone 2

3 7

Alarm (heart

rhythm or

temperature or

pressure)

Person in zone 3

4 8

Alarm (heart

rhythm or

temperature or

pressure)

Person in zone 4

5.2 Comfort Service

Two parameters were monitored in the environment:

room temperature which is represented by tm, and

luminosity that represented by lu. It has a scale with

three degrees, suggesting that the degree 2 is

reserved for the ambient temperature and the

ambient luminosity. Values of the temperature and

luminosity are compared with this value if it is less

or greater than 2, depends on this comparison, we

will heat or cool the habitat; we will rise or reduce

the luminosity. The setting of these two parameters

is made after the decision of the person if it is

automatic or manual encoded by two values 1 and 0

respectively (Cmd). As shown in the tables 1and 3:

Table 3: Codes retrieved by the sensors (*).

Codes 1 2 3

Ambient

temperature

Tm < 17°C

Tm = 19

+/- 3°C

Tm > 21°C

Luminosity Lu < 150 lux

Lu = 200

+/- 50 lux

Lu > 250

lux

The table below shows all combinations of the

proposed inputs in our architecture and the

designation of each case after fusion:

ICAART2015-InternationalConferenceonAgentsandArtificialIntelligence

228

Figure 5: Implementation of architecture on CPNTools.

Table 4: Result of the fusion of second service.

Pres

ence

Cmd (tm, lu)

Result

of the

fusion

Designation

0 - (-, -) 0 No person

1 0 (-, -) 1 Manual command

(1, 1) 2

Automatic Command

Heating, raising

the luminosity

(1, 3) 3

Heating, reducing

the luminosity

(1, 2) 4

Heating, ambient

luminosity

(2, 2) 5

Ambient

temperature,

ambient

luminosity

(2, 1) 6

Ambient

temperature,

raising the

luminosity

(2, 3) 7

Ambient

temperature,

reducing the

luminosity

(3, 1) 8

Cooling, raising

the luminosity

(3, 3) 9

Cooling, reducing

the luminosity

(3, 2) 10

Cooling, ambient

luminosity

6 IMPLEMENTATION ON

CPNTOOLS

To evaluate the performance of this architecture

based on Petri nets, we present in this section the

simulation results obtained after running these

programs using the software CPNTools.

A CPN model of a system is an executable

model representing the states of the system and the

events (transitions) that can cause the system to

change state. The CPN language makes it possible to

organize a model as a set of modules, and it includes

a time concept for representing the time taken to

execute events in the modelled system. A license for

CPN Tools can be obtained free of charge, also for

commercial use (Jensen and al, 2007).

Figure 5 shows the results of the simulation

using CPNTools. Indeed, the results are obtained

after fusion of proposed agents: The presence,

location, command, heart rhythm, temperature and

blood pressure, ambient temperature and luminosity.

For each simulation the result is a message that

indicates the status of the person or his environment,

as for sample 3 the message displayed is “Alarm

(heart rhythm or temperature or pressure) zone 2”.

ServicesofAmbientAssistanceforElderlyand/orDisabledPersoninHealthIntelligentHabitat

229

7 RESULTS VALIDATION ON

MATLAB

7.1 Symptom Detection Service

To further verify the results of our simulation, we

recovered the input and output codes for 50 samples

generated by the proposed architecture for both

services.

Each sample is assigned a message

corresponding to the action performed.

Figure 6 shows the fusion agents: presence, heart

rhythm, body temperature, blood pressure and

location. We note, for example the sample 11

(indicated by a dotted line in figure 6), code output

is 3 and the accompanying message is “Person in

normal physiological condition, person in zone 3”.

In the second example the sample 6, 22 or 38, the

code is 0; the message is “No person”. Indeed, the

message “Alarm (heart rhythm or temperature or

pressure), person in zone 3” accompanying the

sample 17, it indicates that the person is in zone 3

and he has a problem at the blood pressure.

Figure 6: Graphical representation of the results of first

service.

7.2 Comfort Service

Figure 7 shows the fusion agents: presence,

command, ambient temperature and luminosity. We

note, for example the sample 11 (indicated by a

dotted line in figure 7), code output is 4 and the

accompanying message is “Automatic command,

heating, ambient luminosity”. In the second example

the sample 28, the code is 1; the message is “Manual

command”.

After checking all the samples, we can conclude

that our architecture is able to handle the proposed

services: Symptom Detection Service and Comfort

Service of elderly and/or disabled person in their

habitat.

Figure 7: Graphical representation of the results of second

service.

8 CONCLUSIONS

In this article we presented the ambient Assistance

of the elderly and/or disabled person, it allows

monitoring, comfort and security of people in their

habitats, ensuring the intimacy of the inhabitants.

The ambient assistance consists of several services:

emergency service, service of taking medication and

alarm trigger service...etc. As against in our

architecture we interested by two services: Symptom

Detection Service and Comfort Services. We chose

these services because an elderly person should

always supervise his health and at the same time

assure a comfortable life for him.

The validation of the proposed structure is done

using CPN Tools and Matlab. We used the Colored

Timed and Stochastic Petri nets (CTSPN) for

modeling the proposed structure. The obtained

results show than the proposed architecture collect

information at any time about location and state of

the person, and ensure his comfort in the home. The

goal is to help decision maker choose appropriate

assistance for these persons.

Sample 38 Sample 17

Sample 11

F=3 F=7 F=0

Sample 11

Sample 28

F=4 F=1

ICAART2015-InternationalConferenceonAgentsandArtificialIntelligence

230

REFERENCES

Dupaquier, J., 2006. Le vieillissement de la population

dans le monde. Bulletin Rayonnement du CNRS, no

42.

Nkoma, M., 2011. La sécurité sociale des personnes âgées

en question. Actes du Colloque international de

Meknès.

Perriot,B., Argod, J. , Pepin, J.-L., and Noury, N., 2013. A

Network of Collaborative Sensors for the Monitoring

of COPD Patients in their Daily Life. 2013 IEEE 15th

International Conference on e-Health Networking,

Applications and Services.

Murdoch, O., Wan, J., Abdalla, S., and al. 2013. Sensor

Infrastructures for Ambient Assisted Living. In

Handbook of Medical and Healthcare Technologies

(pp. 435-452). Springer New York.

Fleury, A., Noury, N., & Vacher, M. 2011. Improving

supervised classification of activities of daily living

using prior knowledge. International journal of E-

Health and medical communications, 2(1), 17-34. ISO

690.

Fleury, A., Vacher, M., & Noury, N. 2010. SVM-based

multimodal classification of activities of daily living in

health smart homes: sensors, algorithms, and first

experimental results. Information Technology in

Biomedicine, IEEE Transactions on, 14(2), 274-283.

Noury, N., Perriot, B., Argod, J., & Pepin, J. 2013.

Characterization of physical activity in COPD

patients: validation of a robust algorithm for

actigraphic measurements in living situations. IEEE

Journal of Biomedical and Health Informatics.

Lauterbach, C., Steinhage, A., & Techmer, A. 2013. A

large-area sensor system underneath the floor for

ambient assisted living applications. In Pervasive and

mobile sensing and computing for healthcare (pp. 69-

87). Springer Berlin Heidelberg.

Foko, T. E., Dlodlo, N., & Montsi, L. 2013. An integrated

smart system for ambient-assisted living. In Internet of

Things, Smart Spaces, and Next Generation

Networking (pp. 128-138). Springer Berlin

Heidelberg.

Rosas, J., Camarinha-Matos, L. M., and al. 2014.

Development of an Ecosystem for Ambient Assisted

Living. In Innovative and Creative Developments in

Multimodal Interaction Systems (pp. 200-227).

Springer Berlin Heidelberg.

Wood, A., Stankovic, J. A., Virone, G., et al, 2008.

Context-aware wireless sensor networks for assisted

living and residential monitoring. Network, IEEE, vol.

22, no 4, p. 26-33.

Noury, N., and Hadidi, T. 2013. Simulation of Human

Activity in a Health Smart Home with HMM. 2013

IEEE 15th International Conference on e-Health

Networking, Applications & Services (Healthcom).

Fleury, A., Vacher, M., Portet, F., and al. 2010. A

multimodal corpus recorded in a health smart home. In

Proceedings of the Workshop on Multimodal Corpora:

Advances in Capturing, Coding and Analyzing

Multimodality in conjunction with LREC 2010 (pp. 99-

105).

Noury, N., Perriot, B., Collet, J., Grenier, E., Cerny, M.

and al. 2013. ActimedARM-Design of a wearable

system to monitor daily actimetry. In Engineering in

Medicine and Biology Society (EMBC), 2013 35th

Annual International Conference of the IEEE (pp.

1851-1854). IEEE.

Vacher, M., Fleury, A., Serignat, J. F., Noury, N., &

Glasson, H. 2008. Preliminary evaluation of

speech/sound recognition for telemedicine application

in a real environment. In Proceedings of the

Interspeech 2008 conference (pp. 496-499).

Mascolo, M., Gouin, A., & Noury, N. 2007. Habitat

Intelligent pour la Santé-Vers un outil d'aide à

l'évaluation automatique de la dépendance d'une

personne âgée. Actes des 2èmes Journées

Doctorales/Journées Nationales MACS JD-JN-MACS,

10.

Souidene, W., Istrate, D., Medjahed, H., Boudy, J. and al.

2008. Une plateforme multimodale pour la

télévigilance médicale. 4th ws AMINA, Tunis.

Medjahed, H., Istrate, D., Boudy, J., Baldinger, J. L., &

Dorizzi, B. 2011. A pervasive multi-sensor data fusion

for smart home healthcare monitoring. In Fuzzy

Systems (FUZZ), 2011 IEEE International Conference

on (pp. 1466-1473). IEEE.

Medjahed, H., Istrate, D., Boudy, J., Baldinger, J. and al.

2008. A Multimodal Platform for Database Recording

and Elderly People Monitoring. In BIOSIGNALS (2)

(pp. 385-392).

Medjahed, H., Istrate, D., Boudy, J., & Dorizzi, B. 2009.

Human activities of daily living recognition using

fuzzy logic for elderly home monitoring. In Fuzzy

Systems, 2009. FUZZ-IEEE 2009. IEEE International

Conference on (pp. 2001-2006). IEEE.

Guettari, T., Aguilar, P. A. C., Boudy, J., Medjahed, H.

and al. 2010. Multimodal localization in the context of

a medical telemonitoring system. In Engineering in

Medicine and Biology Society (EMBC), 2010 Annual

International Conference of the IEEE (pp. 3835-

3838). IEEE.

Jensen, K., Kristensen, L. M., and Wells, L., 2007.

Coloured Petri Nets and CPN Tools for modelling and

validation of concurrent systems. International

Journal on Software Tools for Technology Transfer,

vol. 9, no 3 4, p. 213-254.

Bates, B., 2010. Guide de l'examen clinique. Wolters

Kluwer France.

(*) http://temperatureideale.fr/post/temperature-ideale-

piece-maison-appartement (consulté en Aout 2013).

ServicesofAmbientAssistanceforElderlyand/orDisabledPersoninHealthIntelligentHabitat

231