=Paper= {{Paper |id=Vol-2333/paper2 |storemode=property |title=Dynamic Decision Support System for Personalised Coaching to Support Active Ageing |pdfUrl=https://ceur-ws.org/Vol-2333/paper2.pdf |volume=Vol-2333 |authors=Silvia Orte,Paula Subías,Laura Fernández,Alfonso Mastropietro,Simone Porcelli,Giovanna Rizzo,Noemí Boqué,Sabrina Guye,Christina Röcke,Giuseppe Andreoni,Antonino Crivello,Filippo Palumbo |dblpUrl=https://dblp.org/rec/conf/aiia/OrteSMMPRBGRACP18 }} ==Dynamic Decision Support System for Personalised Coaching to Support Active Ageing== https://ceur-ws.org/Vol-2333/paper2.pdf

Dynamic Decision Support System for
personalised coaching to support active ageing

Silvia Orte1 , Paula Subı́as1 , Laura Fernández2 , Alfonso Mastropietro3 ,
Simone Porcelli3 , Giovanna Rizzo3 , Noemı́ Boqué1 , Sabrina Guye4 ,
Christina Röcke4 , Giuseppe Andreoni5 , Antonino Crivello6 , and
Filippo Palumbo6
1
Eurecat, Barcelona, Spain
2
Fundació Salut i Envelliment, Barcelona, Spain
3
Institute of Molecular Bioimaging and Physiology
National Research Council, Milan, Italy
4
University of Zurich, Zurich, Switzerland
5
Department of Bioengineering, Polytechnic of Milan, Milan, Italy
6
Institute of Information Science and Technologies
National Research Council, Pisa, Italy

Abstract. Physiological status and physical activity, social interaction,
cognitive and emotional status, and nutrition in older people are the key
target areas addressed by the NESTORE project. It is aimed at devel-
oping a multi-domain solution for users, able to prolong their functional,
social, and cognitive capacity by empowering, stimulating, and unobtru-
sively monitoring, in other words, “coaching” the user’s daily activities
according to a well-defined “Active and Healthy Ageing” life-style pro-
tocols. Besides the key features of NESTORE in terms of technological
solutions, this work focus on the preliminary research carried out in the
context of algorithms for modelling and profiling target individuals with
the aim of developing an effective dynamic Decision Support System.

Keywords: Decision Support System · Active and Healthy Ageing ·
User Profiling.

1 Introduction

Ageing population is growing faster in EU [9]. In this context, Information and
Communication Technology (ICT) can provide solutions for Active and Healthy
Ageing, however, the success of novel ICT solutions depends on the user per-
ception about their efficacy to support health promotion and global wellness.
Active and Healthy Ageing represents a complex intervention because it tackles
all the human domains: physical, metabolic, cognitive, social, etc. Thus, a multi-
domain system needs to be designed to promote proper healthy strategies. The
project NESTORE1 (Novel Empowering Solutions and Technologies for Older
1
https://nestore-coach.eu/
people to Retain Everyday life activities), funded by EU H2020 programme, has
been designed and developed aiming at this integrated vision.
The objective of NESTORE is to develop a virtual companion that, like the
mythological Nestor, can give advice to older people so that they can main-
tain their well-being and their independence at home, based on experience and
on understanding the current situation. The experience of NESTORE is based
on well-grounded psychological and behavioural theories in conjunction with
relevant know-how on the ageing process, while the current user’s situation is
understood on the basis of a comprehensive system of sensors able to monitor
the different key parameters of the user. An intelligent system, deployed on the
cloud and leveraging Decision Support (DS) logic delivers “advise and coaching”,
which is offered via the companion, embodied in a smartphone or an intelligent
tangible object, according to the user’s preferences and interests. NESTORE
provides coaching and personalisation in five crucial domains (called henceforth
NESTORE target domains) of the Active Ageing process: i) physiological status;
ii) physical activity; iii) social interaction; iv) cognitive and emotional status; v)
nutrition.
In this paper, we present the core component behind the coaching activities
suggested to the user by NESTORE: an intelligent and innovative Decision Sup-
port System (DSS). It is able to analyse the user’s behaviour, tracking its changes
and its compliance to active ageing guidelines, and providing personalized target
behaviours toward the adoption and maintenance of a healthy lifestyle. A DSS
can be defined as a computerized information system used to support decision-
making in which the characteristics of an individual are matched to a computer-
ized knowledge base [18]. DSS lets users sift through and analyse massive reams
of data and compile information that can be used to solve problems and make
better decisions. For such a system to work effectively, person’s goals, overall
cognitive/physical/mental and social status need to be assessed together with a
profile of a person’s daily life activities monitored using technology-based track-
ing systems in order to provide a reference frame and basis for the DSS that in-
cludes an individualized real-life approach rather than a mere population-based
approach based on maximum performance laboratory-based assessments.
The personalisation is built upon dynamic models fed with five well-being
dimensions, while the DSS selects, processes, and updates indicators by learn-
ing from past choices. In particular, NESTORE implements novel algorithms
for detecting and monitoring of important indicators related to user status and
behaviour. These algorithms are able to adapt to personal needs, emotional and
behavioural patterns, thanks to the inclusion of the well assessed Selection, Op-
timization and Compensation (SOC) model strategy [15], which provides the
methodology for releasing an effective interaction tailored to the current phys-
ical, psychological, emotional status of the older person, as captured by the
monitoring system.
The algorithm infrastructure comprises unsupervised and semi-supervised
algorithms for the inference of user’s behavioural profile and the anomaly de-
tection. User’s trends in the five well-being dimensions will be described in one
single semantically annotated model giving the possibility of inferring the nec-
essary information to understand the peculiarities of each user among the other
users and their self in different scenarios thus generating the appropriate feed-
back.
The NESTORE DSS is based on a three-layer structure: i) a short-term
analysis that analyses data on a daily basis; ii) a long-term analysis that looks
at trends and is able to detect change and adapts the coach in the long term,
following the changing needs of people as they age; iii) a combined short- and
long-term analysis to provide a personalized mix of activities for finally sending
personalized plans to the Coach when appropriate. The recognized trends are
combined in the DSS with context reasoning to provide robust recommendations
and correlations. Behavioural theories leveraging SOC and HAPA [26] models
will be embedded in the algorithms. In NESTORE, we will also adopt the so-
called “emergent” modelling perspective. With an emergent approach, the focus
is on the low-level processing: sensory data are augmented with structure and
behaviour, locally encapsulated by autonomous subsystems, which allows an
aggregated perception in the environment [5].
The rest of the paper is structured as follows: Section 2 shows the main com-
ponents of the NESTORE Decision Support System with Section 3 describing
its user profiling process. Section 4 illustrates how the profiles are used in the
DSS, while Section 5 draws the conclusions.

2 The NESTORE Decision Support System
During recent years, various researches have investigated and developed new so-
lutions in the area of DSS. This is due to the emergence of personalised medicine
and the enhanced ability to build tools aimed at predicting personalized risk and
advice systems. Currently, most DSSs provide decision support for particular
diagnostic or therapeutic tasks such as ensuring accurate diagnosis, improved
prognosis and theragnosis, screening for preventable diseases in a timely man-
ner or averting adverse drug events. As regards NESTORE’s field of interest,
there have been attempts to decision support for telecare but few of these have
achieved user-specific personalisation. The current work done in this area can
be classified according to their purpose as systems that:
– Give advice, recommend care plans and trigger alerts. People at this
age require individualised care plans so that they could maintain their health
taking into account the idiosyncrasy of each individual. Care plans can give
details of dietary requirements, activity levels, targets for physical activity,
blood pressure and other tests.
– Are based on daily life activities. Changing routines for people in their
60’s is not the best way to achieve motivation. That is why it is important
to adapt the recommendations to users’ current behaviour. In [20], patient’s
daily life activities, as well as other social elements are used for personaliz-
ing their services. In a similar manner, but with different purposes, Croonen-
borghs et al. [13] proposes to automatically monitor daily activities to detect
abnormal events, like the sudden general absence of activity, or changes in
their activities, which would permit an early detection of problems. Likewise,
an interesting example to extract daily information is presented in [7], where
how TV daily usage can predict mental health change.
– Extend independent living. An interesting analysis is made by [8], au-
thors are able to identify with a DSS any sign of transition from healthy to
pathological status of elderly people living alone. In a more general manner,
[22] demonstrates with a systematic review of current literature that moni-
toring technologies to detect activities of daily life of elderly people prolong
independent living of elderly people.
Most of the DSS analysed before cover only a narrow field of medical knowl-
edge or only part of the relevant factors for preventing the elderly decline are
treated and transferred into the DSS. In other words, so far, the inference tech-
niques cannot represent the rich variety of elements that a professional could
recommend to a specific person. Furthermore, in the analysed works, due to
limitations in the user interface, the advice of DSS relies only on computable
input data, which represent just a small proportion of the information required
to make decisions. It is extremely difficult for the user to determine whether
the input data adequately represent a potential problem. Most of them fail to
represent common-sense knowledge and have no real understanding of the user’s
problem.
In NESTORE, the DSS is intended to help older people to compile useful
information about their lifestyle in order to identify proper actions and make
decisions to improve or maintain a healthy life. One of the primary objectives in
NESTORE project is to develop a DSS so that the users can obtain fast, reliable,
personalised, and directly applicable advice. Suggestions are delivered in form
of coaching plans, which are divided into pathways composed of different coach-
ing activities and training activities. The DSS and, concretely, a user profiling
module will be in charge of proposing the coaching plans and recommendations
that better fit each user based on extracted attributes. The information the final
NESTORE DSS will use is:
– Models describing the NESTORE target domains;
– Recommendations and guidelines;
– Behavioural models and intervention techniques;
– Existing knowledge from domain experts and other evidence-based sources.
User profiling is one of the key steps in the recommendation processes since
it is essential for extracting user characteristics and predicting how much a user
will like an item.
As depicted in Figure 1, the user profile and user preferences feed the DSS
engine with the necessary inputs to select the most convenient coach plan for
each user. In this paper, we focus on the personalisation side of the DSS, mainly
embodied in the user profiling component. It describes the way we will profile
the users with the final aim of selecting the recommendations and coaching plans
that better fit the user.
Fig. 1. Conceptual view of the DSS engine.

3 User Profiling
User profiling can be defined as the process of identifying the data about a
user interest domain. This information can be leveraged by the DSS to better
understand the user needs and, thereby, provide personalized recommendations.
The process to build the user profiling is foreseen as follows:
Step 1. Personas are designed to analyse the different types of information that
we will need to personalize NESTORE recommendations.
Step 2. The final set of Personas is analysed and a list of attributes is extracted
from it.
Step 3. The list of attributes is complemented with other items that NESTORE
domain experts believe that are important for the personalisation pro-
cedure.
Step 4. Different user profiling methods are analysed. A twofold user profile is
implemented: static and dynamic.
Step 5. The data flow for recommending coaching plans is designed and differ-
ent use cases where user profiling will be used are envisaged.
Step 6. User profiling module is implemented and integrated in the NESTORE
DSS.

3.1 The NESTORE Personas
The Inmates Are Running the Asylum [11] introduced the use of personas as
a practical interaction design tool. Personas are hypothetical archetypes of end
users. Although they are imaginary, they are defined with significant rigour and
precision, and they help to base the potential users’ descriptions in real cases to
achieve more realism. The main aims of the Persona methodology are:

– to define simple and real personas’ profiles in an effective way;
– to create end users’ models for representing their life, needs and preferences;
– to build a new understanding about who is the end user to help team mem-
bers feel connected to them, raise empathy and work with the same personas’
cases;
– to work in levels of complexity in function of the depth of definition of each
model, for example from expert users to novice and advance their needs and
requirements if it is possible;
– to have a model to facilitate discussions in cognitive walkthroughs, story-
boarding, role-playing, and other usability activities;
– to create a collection of archetypes to help new team members learn about
the characteristics of users’ profile.

In NESTORE, the process of creating Personas was based not only on pre-
vious research projects prepared for the development of user profiles but also
on an iterative process to facilitate the transversal cooperation between the dif-
ferent NESTORE partners and key agents. All this process was based on the
importance of reflecting the idiosyncrasies and realities to develop useful profiles
for the implementation of the system.
The research was developed consulting the main European demographic pub-
lic resources to detect the core characteristics of the elderly population, but also
to be aware of the possible heterogeneity in this target group. Personas were
designed by the co-design experts and piloting countries to include their privi-
leged view of the real users needs and preferences. There were also taken into
account the co-design experts considerations to include their privileged view of
the real users needs and preferences. Domain experts considerations were also
taken into account in order to introduce valuable information to enrich the global
understanding of the potential NESTORE users. Another valuable feedback was
obtained from the Forum Advisory Stakeholders (FAS). Suggestions and ques-
tions pointed out by FAS members were reflected in a new version of users profile
and personas document. This fruitful cooperation had, as a result, a large list
of profiles (n=24). This contribution aimed to reflect the heterogeneity from the
European contest.
Three tools were created to help in the process of refining profiles. Firstly, it
was created a checklist with key questions to be asked to co-design experts and
pilot teams. The main purpose was to select the final personas systematically
and guide experts in the evaluation of each profile to detect those who have
more capacity to be more informative or descriptive for technical researchers
and developers. Secondly, it was produced a document based on a table with
two tabs, one for comparing and grouping the different profiles and a second
tab for merging and defining 8 contexts. This tool helped to refine the status,
preferences, and attributes. Finally, the third tool was a diagram that presents
three important aspects (personal and environmental characteristics and possi-
ble pathways). This schema was crucial to highlight the needs and preferences of
personas’ profiles which will determine the possible elections of pathways of real
users. Finally, it was proposed to create a card template to reflect the main char-
acteristics of each profile. This task helps to be systematic and gain consistency
to build profiles.

Fig. 2. Diagram of Persona’s profile template.

The use of the diagram tool showed in Figure 2 helped to define two main
aspects to be included in the refinement of Personas, in accordance with the
Cooper definition [10]:

1. End Goals: motivational goals but based on their live preferences. These
goals could be very effective to determine in some way the final acceptance
or user perception of the usefulness of a product or service when it is achieved
a convergence between real users’ needs and product or service features to
answer these needs. When these goals are reflected in profiles, it could help
to understand the cognitive walkthroughs, personal contexts or “a day-in-
the-life of” scenarios. In the NESTORE case, these goals were defined based
on the project domains (physiological, nutrition, cognitive and mental, social
interaction).
2. Life Goals: defined as the Persona’s long-term desires, motivations, self-
image attributes and personal aspirations. This description could help to
explain why the user is trying to accomplish goals. The previous work devel-
oped in NESTORE co-design phase helps to build a better understanding
of real-life facts of the elderly population and to add in the descriptions of
each profile.
In NESTORE’s profiles, it has been suggested indirectly the end goals and
life goals by means of the description of personas’ daily activities and main inter-
ests. For example, in some profiles spending time with family, to be involved in
cultural or voluntary movements, etc. Figure 3 provides an example illustrating
the building process to define each profile.

Fig. 3. Diagram of Persona example.

NESTORE’s card model includes general information such as gender, age,
country or socio-economic status, and more specific details about how many peo-
ple live in the home, the main characteristics of the living space (size, existence
of stairs, balcony or garden), where they live (urban or rural), web connection
level, if they have pet or not. Environmental information (weather and humid-
ity that could affect their activities in daily living) is also provided. Finally,
Personas’ status in relation to the different domains is provided with a level, a
definition of the status and target with a narrative description that includes in-
formation about preferences and values. Figure 4 shows an example of the cards
of NESTORE Personas.
Personas present diversity in relation to the different NESTORE target do-
mains, in order to have a wider spectrum that could enrich the views and un-
derstanding of potential needs and preferences of future end users.
Fig. 4. One of the card from NESTORE Personas.

Physiological status and Physical activity domain Although NESTORE
users are defined as healthy older people, it is relevant to include different type
of health conditions (not severe chronic diseases) very common and prevalent
in the elderly population. There are acute illnesses or health conditions that
could determine behaviours or affect system functionalities, and because of this,
domain experts pointed out the need to consider some conditions in the health
status. Since NESTORE pathways are based on the user needs to maintain or
improve a defined physiological status, Personas included profiles with differ-
ent physical activity levels and several behavioural targets. According to this,
Personas have a wide range of physical activity level and profiles with high (2
profiles), medium (5 profiles), and low activity (3 profiles) are included. Simi-
larly, Personas include profiles who need to improve aerobic activities such as
walking but do not need stretch exercise as well as aerobically fit subjects who
need to increase the frequency of strength activities.

Social interaction domain Personas were defined to describe different living
conditions, even though the majority of profiles are characterized by medium or
high levels of interaction. Personas are retired or working part-time, or taking
care of grandchildren or other family members. Also, there are very active pro-
files, involved in volunteering activities, hobbies (music, reading, travel, etc.),
doing cultural or training activities. But it was decided to also include per-
ceptions of some loneliness in some profiles that could affect the perception of
quality of interactions with others. We also defined the use of social networks.
Pathways considered in the social interaction domain were defined to maintain
or improve a persons social opportunities or skills.

Cognitive and emotional domain Personas were described to include a broad
range of cognitive and emotional status. The majority of profiles (n=7) have a
good cognitive status, but they could be worried to maintain it, or they could be
worried about future memory loss. Because of this, the personas’ profiles have
interest in pathways such as: “maintain cognitive skills”, “maintain/improve
memory” or “maintain/improve daily mental skills”. We introduced three pro-
files with low/medium status that includes: memory loss, depressive symptoms,
emotional or mood problems.

Nutrition domain The majority of participants have a well-balanced diet, but
they want to improve some aspects as the diversity of menus, introduce some
foods and nutrients such as proteins or fibre from vegetables or fruits, or reduce
others as cakes, fats, etc. Some of them need to increase the intake of water.
Also, it was included two profiles with digestive problems, to help identify other
needs and preferences that could affect the diet behaviour or food selections.
Two Personas are overweight, but their target was defined to diversify menus
and balance their diet because it is possible that in existence of overweight
problems the user decides that he/she does not want to reduce body weight or
fat mass. However, the NESTORE System will firstly encourage him/her to lose
weight (explaining the benefits, risk factors, etc.). If users continue interested
in diet, then NESTORE system will understand their needs and preferences in
order to propose a pathway that includes some activities which could encourage
a behaviour change, if possible. Also, four Personas have a different diet profile
because one has food allergies, one has lactose intolerance, and two are vegan or
vegetarian in order to introduce some diversification in profiling.

3.2 Static and dynamic profiling

After analysing Personas and complementing the information with domain ex-
perts, it is proposed a twofold user profile:

– Static profile. It is formed by the status and preferences of the user and it
is characterized by containing non-varying attributes. Concretely it includes
demographic characteristics, attributes regarding the context where the user
lives, physical and physiological aspects and baseline data of the various
domains.
– Dynamic profile. It is built dynamically while receiving data from sensors,
applications and contextual APIs. It is foreseen to receive daily indicators
about the different domains and also contextual information (i.e. current
weather conditions).
Static profiling is the process of analysing a user’s static and predictable
characteristics. Users’ static features comprehend factual data, such as the id-
iosyncrasy of their residence (e.g. do they live in a rural or in an urban area?),
or their diet routines (e.g. is meat part of their diet?), as well as inter-individual
differences in the other NESTORE domains (marital status and perceptions of
loneliness, cognitive functioning, physical fitness, etc.). They also describe the
environment and context of users. One of the uses of static profiling will be the
cluster of users, the resulting groups of which will be inputted into the DSS to
make thoughtful recommendations. Considering that real data will not be avail-
able until the pilots take off, a data simulator has been implemented to cope with
the absence of data creating, thus, solid fundamentals for the clustering process
and the recommender system. Getting into detail, the static profile simulator
generates a population of users who is described by its fact-based properties.
Dynamic profiling is the process of analysing data coming at run-time from
the sensors and applications deployed in the NESTORE user’s ecosystem. It
describes the changing context of the user, which is the element that leads the
personalisation process.

Static features

To build the static profile of a user, not only the three well-known well-being
domains (i.e., physiological status and physical activity behaviour, cognitive and
social behaviour, and nutrition) need to be considered. The user’s context is a
quite new feature in user profiling that will help to characterise the situation
of the user. There are different types of contexts or contextual information that
can be modelled within a user profile [16], but we will focus our attention on the
environmental and the demographic context.
After deciding on the obtainable information to profile the users, a collection
of variables with the values they can take has been defined. Those have been split
per kind of contextual feature (demographic and environmental) and per well-
being domain (physiological status and physical activity behaviour, nutrition,
cognitive and mental status, and social behaviour). Besides, a category called
activities has been added to include the user’s routines and preferences. It should
be noted that the following variables are not all the properties indicated by the
domain experts. This is due to the uncertainty about the setting in the pilots at
the current stage and for this reason, some of the variables have been temporarily
dismissed since they may not be measurable.
Demographic information is to a great degree relevant to group people ac-
cording to their culture and generation. Due to the scope of the DSS, there is
no need of depicting the participant’s culture. Table 1 shows the variables which
best characterize users’ demographic context.
The environmental context captures the entities that surround the user.
These entities can, for instance, be services, temperature, light, humidity, noise,
and people [24]. Table 2 displays a compendium of variables that provide con-
textual information about the environment of users.
Table 1. Demographic variables

VARIABLE DOMAIN
Age [65,75]
Gender F,M

Table 2. Environmental variables

VARIABLE DOMAIN
Household Integer
Marital status Single, couple, divorced, widowed
Living area Urban, rural
Stairs Yes, no
Garden Yes, no
Pet Yes, no
Employment Yes, no
Facilities nearby Beach, theatre, etc.

Routine activities of users, as well as their preferences, should be taken into
account to provide personalized recommendations that adapt to their lifestyle.
The variables that will be considered are shown in Table 3.

Table 3. Variables related to routine activities

VARIABLE DOMAIN
Physical activity duration [min] less than 30; [30,60]; [61,120]; more than 120
Physical activity frequency Daily, 2-3 times per week; weekly
Preferences Walk, bike, swim, golf, dance, extreme sport, etc.

The factual data that best describes the physiological status of users mainly
comes from their anthropometric characteristics, presented in Table 4.
The nutritional domain will basically be characterized by the dynamic profile.
Only the list of refused foods will be considered to create the nutritional static
profile, as it is presented in Table 5.
The variables that describe the cognitive and mental status of users can be
found in Table 6.
Finally, the static social integration level can be characterized by the factual
information contained in Table 7.

Dynamic features: short- and long-term indicators

Various sensors and applications deployed in the NESTORE platform gener-
ate, at run-time, input data to the DSS. An environmental monitoring system is
Table 4. Variables related to the physiological status

VARIABLE DOMAIN
Level Low [0,33]; medium [34,66]; high [67,100]
Aerobic fitness level To improve [0,19]; to retain [20,30]
Strength level To improve [0,35]; to retain [36,50]
Flexibility level To improve [0,5]: to retain [6,10]
Balance level To improve [0,5]; to retain [6,10]
Body height [m]
Body weight [kg]
Body mass index (BMI) [kg/m2 ]
Fat mass [%]
Fat-free mass [%]

Table 5. Variables related to the nutritional domain

VARIABLE DOMAIN
Refused foods Text

Table 6. Variables related to the cognitive, social, and mental status

VARIABLE DOMAIN
Level Good; medium; low
Status Positive and negative affect; life satisfaction; depressive symptoms;
cognitive functioning (test-based); memory failures (self-reported);
loneliness; social integration

Table 7. Variables related to social behaviour

VARIABLE DOMAIN
Level Good; medium; low
Company Friends; volunteering/working; family
Frequency Daily; 2-3 times per week; weekly; monthly; yearly
Community Friends; association; activism; volunteer
deployed in the NESTORE user environment as an ensemble of wireless sensors
able to sense the variables indicated by the domain experts in the relative NE-
STORE target domains. Furthermore, it has the aim of detecting the interaction
of the user with the environment and monitoring the status of the environment
itself (e.g., indoor air quality). Also, an innovative wearable device is expected
to be worn by the NESTORE user. It is able to detect physiological parameters
(e.g., heart rate, steps, distance, sedentariness, stairs, energy expenditure, etc)
while the user performs the activities suggested by the NESTORE virtual coach.
Reflecting the separation of concerns of all the data generator deployed in
the NESTORE environment, we call environmental device any sensor deployed
in the user’s vital space, while wearable the device worn by the user during his
daily activities. As a further source of information about the user’s status, we
have derived data as result of a computation or fusing strategy and data coming
from a direct input of the user, as questionnaires while interacting with the
NESTORE coach. We call the latter soft data. Table 8 describes how the device
types (wearable, environmental, and soft data) cover the variables indicated as
needed by domain experts for each NESTORE target domain.

Table 8. Relationships between device types and domains variables

NESTORE DOMAIN VARIABLES DEVICE TYPE
Physical Activity Behaviour
Cardiorespiratory Exercise Capacity
Wearable
Cardiovascular System
Respiratory System
Physical Activity Strength-Balance-Flexibility Exer-
cise Capacity
Anthropometric Characteristics Environmental
Musculoskeletal System
Sleep Quality
Energy Expenditure
Nutrition
Nutrition Habits
Cognitive Status Soft Data
Mental Status
Cognitive, Mental, Social
Mental Behaviour and States
Social Behaviour Environmental

From the devices point of view, besides the wearable device, in the form of
a smart wristband, we plan to deploy a smart scale to collect anthropometric,
musculoskeletal characteristics and balance [2] and a ballistocardiographic sys-
tem in order to perform sleep monitoring [19, 12, 1]. For social behaviour, we will
use Bluetooth Low Energy (BLE) beacons to detect social interactions among
NESTORE users and their relatives (bringing with them keyfobs equipped with
mobile BLE tags) with their duration, function, location, and number. We will
exploit the capability of calculating the proximity between BLE devices from Re-
ceived Signal Strenght Indicators (RSSIs) [6, 4] also for detecting the interaction
of the user with the pieces of furniture in the house on which fixed beacons are
deployed, giving us insights on the users level of sedentariness [21]. The possi-
bilities offered by BLE beacons of customizing their hardware and firmware will
allow us to advertise, from fixed beacons, additional information like motion (to
increase the level of accuracy in detecting interactions with point of interests in
the house) and temperature and humidity (to calculate the indoor air quality
indicator [23]).

outdoor indoor

Internet
NESTORE
Cloud
Infrastructure

Fig. 5. The WoT approach for environmental and wearable devices

From the architectural and deployment point of view, in order to reduce the
effort needed by the end user to install and use the environmental sensors, we
chose to adopt a Web of Things (WoT) approach. WoT is a computing con-
cept that describes an environment where everyday objects are fully integrated
with the Web. The prerequisite for WoT is for the “things” to have embedded
computer systems that enable communication with the Web. Such smart de-
vices would then be able to communicate with each other using existing Web
standards. Considered a subset of the Internet of Things (IoT), WoT focuses on
software standards and frameworks such as REST, HTTP and URIs to create
applications and services that combine and interact with a variety of network
devices. The key point is that this doesn’t involve the development of new com-
munication paradigms because existing standards are used [17, 14, 3]. Figure 5
shows the adopted WoT approach for environmental and wearable devices.
4 Data flow for recommending coaching plans
A general workflow illustrating how the two types of the previously described
profiles are used in the DSS is depicted in Figure 6. As shown in the picture, we
foresee to generate clusters or groups of users taking into account a number of
static profiles generated with the simulator described in Section 3.2. Afterwards,
experts will select the best type of coaching activities to be recommended to
each group.

Fig. 6. Data flow for recommending coaching plans

The recommendation process carried out in the DSS will follow the Health
Action Process Approach (HAPA) model [25]. In this paper, we summarize the
DSS personalization process in three main steps based on the phases described
in the HAPA model and the three levels of coaching of NESTORE:
Step 1. After acquiring the needed information about the user for building their
static profile (around 2 weeks), the system proposes a list of pathways
that correspond to the detected weaker aspects (this is the result of
the phases 1 and 2 of the HAPA model). The user selects one of the
pathways to focus during the following weeks (this corresponds to phase
3 of the HAPA model).
Step 2. Each pathway has a predefined list of coaching activities, but not all of
them apply to all the users. In this step, the DSS selects the subset of
coaching activities that better fit the group where the user belongs to.
Step 3. Training activities or recommendations related to the different chosen
coaching activities are suggested to the user depending on the dynamic
profile data. The user, finally decides which activities he wants to per-
form.

In the following, we explain all the steps with a concrete example.

After two weeks gathering information about the user through the sensing sys-
tem and the coach, the profiler module in the DSS constructs the static profile
shown in Table 9. It contains the necessary information to characterize the base-

Table 9. Static profile example

Age 67
Demographic
Gender Female
Household 1
Marital status Widowed
Environmental Living area Urban
Pet Dog
Stairs Yes
[...]
Hobbies Cooking
Sport preference Walk, dance
Physical activity duration <30 min.
Activities (average)
Physical activity frequency 2-3 times per week
(average)
[...]
Aerobic Fitness Level 10/30
Strength Level 5/50
Flexibility Level 6/10
Physical Activity (baseline)
Balance Level 4/10
Total PA Level 25/100 (Low)
[...]
Nutrition (baseline) Refused foods Citric fruits
(Objective) Performance Medium
level
Cognitive (baseline) Self-reported cognitive fail- Some
ures
[...]
Loneliness Low

Social network contacts and Medium
Social (baseline) social integration
Frequency Friends (1 per week),
Family (2-3 times
per week)

line of the user in different general aspects and in all NESTORE’s domains of
interest. This information allows the system to infer which pathways to propose
and which groups does the user belong to.
Let’s say that the example user belongs to group A. The system could in-
terpret that the weakest points are physical activity and social domains, so it
proposes the following pathways:

– Improve fitness level
– Improve social activities
– Retain healthy eating
– Retain memory

Assuming that the user selects “Improve fitness level” as their main objective,
the DSS takes the subset of activities of group A that belongs to this pathway
and some other activities from the other pathways (step 2). For example:

– Climb stairs (2 floors)
– Track your steps
– Nordic walk
– Walk on the beach
– Track your nutrition
– Cook new recipes

Then, the coaching phase starts. The DSS creates on a daily or weekly basis
a dynamic profile that will permit to personalize and contextualize the recom-
mendations even more. An example of a dynamic profile is listed in Table 10.

Table 10. Dynamic profile example

Total PA Level Low
Daily/weekly data Nutrition level Low calcium intake
[...]
Location Barcelona
Context Weather Sunny, 26°
[...]

The activities and recommendations proposed to the user throughout the
day could be:

– (At 8:30) Add more milk to your morning coffee!
– Today its sunny, why dont you go for a walk on the beach?
– (Afternoon) Go for a nice long walk with your dog!

Finally, the user can decide which activity he wants to perform.
5 Conclusions
The NESTORE project addresses five important domain affecting their active
and healthy ageing trajectories: physiological status and physical activity, social
interaction, cognitive and emotional status, and nutrition. This is achieved by
designing a multi-domain solution aimed at coaching older people toward an
active and healthy ageing lifestyle protocol.
We presented the core component behind the coaching activities suggested
by NESTORE: an intelligent and innovative Decision Support System. It is able
to analyse the user’s behaviour, tracking its changes and its compliance to active
ageing guidelines, and providing personalized target behaviours for the adoption
and maintenance of a healthy lifestyle.
The system is going to be deployed and validated in 60 pilot sites across
Europe during the next year. At the current stage of the project, the overall
system is under development leveraging the extensive research carried out in the
context of algorithms for modelling and profile the target users. The output of
this process represents the core focus of the paper.

Acknowledgement
This work has been funded in the framework of the EU H2020 project “Novel
Empowering Solutions and Technologies for Older people to Retain Everyday life
activities” (NESTORE), GA769643. The authors wish to thank all the project
partners for their contribution to the project.

References
1. Alfeo, A.L., Barsocchi, P., Cimino, M.G., La Rosa, D., Palumbo, F., Vaglini, G.:
Sleep behavior assessment via smartwatch and stigmergic receptive fields. Personal
and Ubiquitous Computing 22(2), 227–243 (2018)
2. Bacciu, D., Chessa, S., Gallicchio, C., Micheli, A., Pedrelli, L., Ferro, E., Fortunati,
L., La Rosa, D., Palumbo, F., Vozzi, F., et al.: A learning system for automatic berg
balance scale score estimation. Engineering Applications of Artificial Intelligence
66, 60–74 (2017)
3. Barbon, G., Margolis, M., Palumbo, F., Raimondi, F., Weldin, N.: Taking arduino
to the internet of things: the asip programming model. Computer Communications
89, 128–140 (2016)
4. Baronti, P., Barsocchi, P., Chessa, S., Mavilia, F., Palumbo, F.: Indoor bluetooth
low energy dataset for localization, tracking, occupancy, and social interaction.
Sensors 18(12), 4462 (2018)
5. Barsocchi, P., Cimino, M.G., Ferro, E., Lazzeri, A., Palumbo, F., Vaglini, G.: Mon-
itoring elderly behavior via indoor position-based stigmergy. Pervasive and Mobile
Computing 23, 26–42 (2015)
6. Barsocchi, P., Crivello, A., Girolami, M., Mavilia, F., Palumbo, F.: Occupancy
detection by multi-power bluetooth low energy beaconing. In: Indoor Positioning
and Indoor Navigation (IPIN), 2017 International Conference on. pp. 1–6. IEEE
(2017)
7. Billis, A.S., Batziakas, A., Bratsas, C., Tsatali, M.S., Karagianni, M., Bamidis,
P.D.: Enabling active and healthy ageing decision support systems with the smart
collection of tv usage patterns. Healthcare technology letters 3(1), 46–50 (2016)
8. Billis, A.S., Papageorgiou, E.I., Frantzidis, C.A., Tsatali, M.S., Tsolaki, A.C.,
Bamidis, P.D.: A decision-support framework for promoting independent living
and ageing well. IEEE journal of biomedical and health informatics 19(1), 199–
209 (2015)
9. Chloń-Domińczak, A., Kotowska, I.E., Kurkiewicz, J., Abramowska-Kmon, A.,
Stonawski, M.: Population ageing in europe: facts, implications and policies. Brus-
sels: European Commission (2014)
10. Cooper, A., Reimann, R., Cronin, D., Noessel, C.: About face: the essentials of
interaction design. John Wiley & Sons (2014)
11. Cooper, A., et al.: The inmates are running the asylum:[Why high-tech products
drive us crazy and how to restore the sanity]. Sams Indianapolis (2004)
12. Crivello, A., Palumbo, F., Barsocchi, P., La Rosa, D., Scarselli, F., Bianchini, M.:
Understanding human sleep behaviour by machine learning. In: Cognitive Info-
communications, Theory and Applications, pp. 227–252. Springer (2019)
13. Croonenborghs, T., Luca, S., Karsmakers, P., Vanrumste, B.: Healthcare decision
support systems at home. In: Proc. AAAI-14 Workshop on Artificial Intelligence
Applied to Assistive Technologies and Smart Environments (2014)
14. Duquennoy, S., Grimaud, G., Vandewalle, J.J.: The web of things: interconnecting
devices with high usability and performance. In: ICESS 2009 (2009)
15. Freund, A.M., Baltes, P.B.: The orchestration of selection, optimization and com-
pensation: An action-theoretical conceptualization of a theory of developmental
regulation. Control of human behavior, mental processes, and consciousness: Es-
says in honor of the 60th birthday of August Flammer pp. 35–58 (2000)
16. Göker, A., Myrhaug, H.I.: User context and personalisation. In: Workshop pro-
ceedings for the 6th European Conference on Case Based Reasoning (2002)
17. Guinard, D., Trifa, V.: Towards the web of things: Web mashups for embedded
devices. In: Workshop on Mashups, Enterprise Mashups and Lightweight Compo-
sition on the Web (MEM 2009), in proceedings of WWW (International World
Wide Web Conferences), Madrid, Spain. vol. 15 (2009)
18. Holsapple, C.W., Whinston, A.B., Benamati, J.H., Kearns, G.S.: Instructor’s man-
ual with test bank to accompany decision support systems: a knowledge-based
approach. (1996)
19. Inan, O.T., Migeotte, P.F., Park, K.S., Etemadi, M., Tavakolian, K., Casanella, R.,
Zanetti, J.M., Tank, J., Funtova, I., Prisk, G.K., et al.: Ballistocardiography and
seismocardiography: a review of recent advances. IEEE J. Biomedical and Health
Informatics 19(4), 1414–1427 (2015)
20. Khattak, A.M., Pervez, Z., Han, M., Nugent, C., Lee, S.: Ddss: Dynamic decision
support system for elderly. In: Computer-Based Medical Systems (CBMS), 2012
25th International Symposium on. pp. 1–6. IEEE (2012)
21. Palumbo, F., La Rosa, D., Ferro, E.: Stigmergy-based long-term monitoring of in-
door users mobility in ambient assisted living environments: the DOREMI project
approach. In: Bandini, S., Cortellessa, G., Palumbo, F. (eds.) AI*AAL2016 Ar-
tificial Intelligence for Ambient Assisted Living. pp. 18–32. No. 1803 in CEUR
Workshop Proceedings, Aachen (2016), http://ceur-ws.org/Vol-1803
22. Peetoom, K.K., Lexis, M.A., Joore, M., Dirksen, C.D., De Witte, L.P.: Literature
review on monitoring technologies and their outcomes in independently living el-
derly people. Disability and Rehabilitation: Assistive Technology 10(4), 271–294
(2015)
23. Safety, O., Administration, H., et al.: Indoor air quality in commercial and insti-
tutional buildings. Maroon Ebooks (2015)
24. Schiaffino, S., Amandi, A.: Intelligent user profiling. In: Artificial Intelligence An
International Perspective, pp. 193–216. Springer (2009)
25. Schwarzer, R.: Modeling health behavior change: How to predict and modify the
adoption and maintenance of health behaviors. Applied psychology 57(1), 1–29
(2008)
26. Schwarzer, R., Luszczynska, A.: How to overcome health-compromising behaviors:
The health action process approach. European Psychologist 13(2), 141–151 (2008)