=Paper=
{{Paper
|id=Vol-1724/paper1
|storemode=property
|title=Third Generation Teleassistance: Intelligent Monitoring Makes the Difference
|pdfUrl=https://ceur-ws.org/Vol-1724/paper1.pdf
|volume=Vol-1724
|authors=Xavier Rafael-Palou,Carme Zambrana,Stefan Dauwalder,Enrique de la Vega,Eloisa Vargiu,Felip Miralles
|dblpUrl=https://dblp.org/rec/conf/ecai/PalouZDVVM16
}}
==Third Generation Teleassistance: Intelligent Monitoring Makes the Difference==
https://ceur-ws.org/Vol-1724/paper1.pdf
Third Generation Teleassistance:
Intelligent Monitoring Makes the Difference
Xavier Rafael-Palou1 and Carme Zambrana1 and Stefan Dauwalder1 and
Enrique de la Vega2 and Eloisa Vargiu1 and Felip Miralles1
Abstract. Elderly people aim to preserve their independence and a IoT-based teleassistance system (namely, eKauri3 ), help in pro-
autonomy at their own home as long as possible. However, as they viding better assistance and support to people that need assistance.
get old the risks of disease and injuries increase making critical to eKauri is a teleassistance system composed of a set of wireless sen-
assist and provide them the right care whenever needed. Unfortu- sors connected to a gateway (based on Raspberry-pi) that collects
nately, neither relatives, private institutions nor public care services and securely redirects them to the cloud. It is worth noting that
are viable long-term solutions due to the large amount of required eKuari is composed by the following kinds of sensors: one presence-
time and cost. Thus, smart teleassistance solutions must be investi- illumination-temperature sensors (i.e., TSP01 Z-Wave PIR) for each
gated. In particular, IoT paradigm helps in designing third generation room, and one presence-door-illumination-temperature sensor (i.e.,
teleassistance systems by relying on sensors to gather the more data TSM02 Z-Wave PIR) for each entry door. Intelligent monitoring in
as possible. Moreover, we claim that providing IoT solutions of in- eKauri allows to detect the following events: leaving home; going
telligent monitoring improves the overall efficacy. In this paper, we back to home; receiving a visit; remaining alone after a visit; go-
presents an intelligent monitoring solution, fully integrated in a IoT- ing to the bathroom; going to sleep; and awaking from sleep. In this
based teleassistance system, showing how it helps in giving better paper, we focus on the contribution of the intelligent monitoring in
support to both end-users and carers. Thanks to intelligent monitor- eKauri, the interested reader may refer to [23] for a deep description
ing, carers can instantly access to the relevant information regard- of the system.
ing the status of the end-user, also receiving alarms in case of any The rest of the paper is organized as follows. In Section 2, we
anomaly or emergency situations have been detected. briefly recall IoT solutions to teleassistance. Section 3 illustrates how
intelligent monitoring improves teleassistance in the eKauri system.
In Section 4, the main installations of eKauri are presented together
1 Introduction with users’ experience. Section 5 ends the paper summarizing the
In the last decade, the Internet of Things (IoT) paradigm rapidly grew main conclusions.
up gaining ground in the scenario of modern wireless telecommu-
nications [6]. Its basic idea is the pervasive presence of a variety of 2 Related Work
things or objects (e.g, tags, sensors, actuators, smartphones, everyday
Teleassistance remotely, automatically and passively monitors
objects) that are able to interact with each other and cooperate with
changes in people’s condition or lifestyle, with the final goal of man-
their neighbors to reach common goals. IoT solutions have been in-
aging the risks of independent living [9] [2]. In other words, thanks
vestigated and proposed in several fields [7], such as automotive [17],
to teleassistance, end-users are connected with therapists and care-
logistics [19], agriculture [31], entertainment [18], and independent
givers as well as relatives and family, allowing people with special
living [12].
needs to be independent.
Several research issues are still open: standardization, networking,
There are several of efforts to utilize IoT-based systems for mon-
security, and privacy [27]. We claim that research might also focus
itoring elderly people, most of which target only certain aspects of
on intelligent techniques to improve IoT solutions thus making the
elderly requirements from a limited viewpoint. Gokalp and Clarke
difference with respect to classical systems. In other words, artificial
reviewed monitoring activities of daily living of elderly people com-
intelligence algorithms and methods may be integrated in IoT sys-
paring characteristics, outcomes, and limitations of 25 studies [15].
tems: to allow better coordination and communication among sen-
They found that adopted sensors are mainly environmental, except
sors, through adopting multi-agent systems [1]; to adapt the sensor
for accelerometers and some physiological sensors. Ambient sensors
network according to the context, by relying, for instance, on deep
could not differentiate the subject from visitors, as opposed to wear-
learning techniques [16]; as well as to provide recommendations to
able sensors [8] [5]. On the other hand, the latter could only distin-
the final users, by using data fusion and semantic interpretation [4].
guish simple activities, such as walking, running, resting, falling, or
Considering the dependency care sector as a case study, in this
inactivity [3]. Moreover, wearable sensors are not suitable for cogni-
paper we show how intelligent monitoring techniques, integrated in
tively impaired elderly people due to the fact that they are likely to
1 eHealth Unit, EURECAT, Barcelona, email: {xavier.rafael, be forgotten or thrown away [11] [14]. Their main conclusion regard-
carme.zambrana, stefan.dauwalder, eloisa.vargiu, fe- ing sensors is that daily living activity monitoring requires use of a
lip.miralles}@eurecat.org combination of ambient sensors, such as motion and door sensors.
2 Technology Transfer Unit, EURECAT, Barcelona, email: en-
rique.delavega@eurecat.org 3 www.ekauri.com
1
3 Intelligent Monitoring Makes the Difference
Filtering and analyzing data coming from teleassistance systems is
becoming more and more relevant. In fact, a lot of data are continu-
ously gathered and sent through the sensors. The role of therapists,
caregivers, social workers, as well as relatives (hereinafter, carers) is
essential for remotely assisting monitored users. On the one hand,
the monitored user (e.g., elderly or disabled people) needs to be kept
informed about emergencies as soon as they happen and s/he has to
be in contact with therapists and caregivers to change habits and/or
to perform some therapy. On the other hand, monitoring systems are
very important from the perspective of carers. In fact, those systems
allow them to become aware of user context by acquiring heteroge-
neous data coming from sensors and other sources. Thus, intelligent
solutions able to understand all those data and process them to keep
carers aware about their assisted persons are needed, providing also
users empowerment.
In the following, we show how intelligent monitoring helps in: im-
proving sensors reliability allowing better activity recognition; pro-
viding useful information to carers; and inferring quality of life of
users.
Figure 1. The hierarchical approach to presence detection.
3.1 Improving Sensors Reliability
Performance of IoT systems depends, among other characteristics,
been opened. This implies that the system may register that the user
on the reliability of the adopted sensors. In the case of teleassistance,
is away and, in the meanwhile, activities are detected at user’s home.
binary sensors are quite used in the literature and also in commercial
On the contrary, the system may register that the user is at home and,
solutions to identify user’s activities. Binary sensors do not have the
in the meanwhile, activities are not detected at user’s home. To solve,
ability to directly identify people and can only present two possible
or at least reduce, this problem, we built a supervised classifier able
values as outputs (“0” and “1”). Typical examples of binary sensors
to recognize if the door sensor is working well or erroneous events
deployed within smart environments include pressure mats, door sen-
have been detected. First, we revise the data gathered by the sensor-
sors, and movement detectors. A number of studies reporting the use
based system searching for anomalies, i.e.: (1) the user is away and
of binary and related sensors have been undertaken for the purposes
at home some events are detected and (2) the user is at home and
of activity recognition [26]. Nevertheless, sensor data can be consid-
no events are detected. Then, we validated those data by relying on
ered to be highly dynamic and prone to noise and errors [25]. In the
Moves, an app installed and running on the user smartphone4 . In fact,
following, we present two solutions that rely on machine learning
Moves, among other functionality, is able to localize the user. Hence,
to improve reliability of sensors in presence detection and sleeping
using Moves as an “oracle” we build a dataset in which each entry
recognition, respectively.
is labeled depending on the fact that the door sensor was right (label
“1”) or wrong (label “0”).
3.1.1 Presence Detection The goal of the classifier at the lower level is to identify whether
the user is alone or not. The input data of this classifier are those that
Detecting user’s entering/leaving home can be done by relying on has been filtered by the upper level, being recognized as positives. To
door sensors. Fusing data from door- and motions-sensors could help build this classifier, we rely on the novelty detection approach [20]
also in recognizing if the user received visits. Unfortunately, as said, used when data has few positive cases (i.e., anomalies) compared
sensors are not 100% reliable: sometimes they loose events or detect with the negatives (i.e., regular cases); in case of skewed data.
them several times. When sensors remain with a low battery charge The hierarchical approach was part of the EU project BackHome5 .
they get worse. Moreover, also the Raspberry pi may loose some data To train and test it, we consider a window of 4 months for training
or the connection with Internet and/or with the sensors. Also the In- and evaluation (training dataset) and a window of 1 month for the
ternet connection may stop working or loose data. Finally, without test (testing dataset). Experiments have been performed at each level
using a camera or wearable sensors we are not able to directly recog- of the hierarchy. First, we performed experiments to identify the best
nize if the user is alone or if s/he has some visits. supervised classifier to be used at the upper level of the hierarchy.
In order to solve this kind of limitations with the final goal of im- The best performance has been obtained by relying on the SVM (with
proving the overall performance of our IoT-based system that uses γ = 1.0 and C = 0.452). Subsequently, we applied the novelty
only motion and door sensors, we defined and adopt a two-levels hi- detection algorithm on the data filtered by the classifier at the upper
erarchical classifier (see Figure 1) [24]: the upper level is aimed at level, to validate the classifier at the lower one. Finally, we measure
recognizing if the user is at home or not, whereas the lower is aimed the performance of the overall approach. We compared the overall
at recognizing if the user is really alone or if s/he received some vis- results with those obtained by using the rule-based approach in both
its. levels of the hierarchy. Results are shown in Table 1 and point out
The goal of the classifier at the upper level is to improve perfor-
mance of the door sensor. In fact, it may happen that the sensor reg- 4 https://www.moves-app.com/
isters a status change (from closed to open) even if the door has not 5 www.backhome-fp7.eu
2
2
that the proposed approach outperforms the rule-based one with a
significant improvement.
Table 1. Results of the overall hierarchical approach with respect to the
rule-based one.
Metric Rule-based Hierarchical Improv.
Accuracy 0.80 0.95 15%
Precision 0.68 0.94 26%
Recall 0.71 0.91 20%
F1 0.69 0.92 23% Figure 2. Comparison between the ground truth and the machine-learning
(SVM) one.
3.2 Providing Feedback to Carers
3.1.2 Sleep Recognition
The role of carers is essential for remotely assisting people that need
We defined the sleeping activity as the period which begins when the assistance. Thus, intelligent monitoring able to understand gathered
user goes to sleep and ends when the user wakes up in the morning. data and process them to keep carers aware about their assisted per-
Sleep recognition is aimed at reporting the following information: (i) sons are needed [13].
the time when the user went to sleep and woke up; hereinafter we
will refer to them as go to sleep time and wake up time, respectively;
(ii) the number of sleeping activity hours; and (iii) the number of
rest hours, which are sleeping activity hours minus the time that the
user spent going to the toilet or performing other activities during the
night.
Let us note that the simplest way to recognize sleeping activities
is relying on a rule-based approach. In particular, the following rules
may be adopted: the user is in the bedroom; the activity is performed
at night (e.g., the period between 8 pm to 8 am); the user is inactive;
and the inactivity duration is more than half an hour. Unfortunately,
when moving to the real-world, some issues arise: user movements in
the bed might be wrongly classified as awake; rules assumed all users
Figure 3. The main information given to carers through the healthcare
wake up before 8 A.M., which is a strong assumption; and the ap- center.
proach cannot distinguish if the user is, for instance, in the bedroom
watching TV or reading a book, thus classifying all those actions as
sleeping. Thanks to the user-centered approach from the above-mentioned
In order to overcome those limitations, an SVM (Radial Basis projects, we designed friendly and useful interfaces for accessing and
Function kernel, with C = 1.0, γ = 1.0) has been adopted to clas- visualizing relevant data and information. In particular, carers iden-
sify the periods between two bedroom motions in two classes, awake tified as the most relevant the following information (see Figure 3,
and sleep [32]. Let us note that awake corresponds to the period in first line on the top): time spent making activities, time spent sleep-
which the user goes to another room; performs activities in the bed- ing, number of times the user leaves the home (during both day and
room; or stays in the bedroom with the light switched on. Otherwise, night), and number of times the user goes to toilet (during both day
the activity is sleep. and night). Moreover, they considered relevant to visually show the
Experiments, performed from May 2015 to January 2016 in 13 rooms where the user stayed time after time during a day (see Figure
homes in Barcelona, show that the adopted machine learning solu- 3, central part) or during a period (e.g., the last month, as shown in
tion is able to recognize when the user is performing her/his sleeping Figure 4). They also want to be informed about all the notifications,
activity. In particular, the proposed approach reaches an F1 of 96%. chronologically ordered (see Figure 3, on the bottom). Finally, they
Moreover, the adopted classifier is able to easily detect the go to sleep want to access to some statistics to be aware about the evolution of
time, the wake up time, the number of sleeping activity hours and the user’s habits in order to act accordingly.
number of rest hours. Figure 2 shows the comparisons between the
ground truth (obtained by questionnaires answered by the users) and
the results obtained with the machine learning approach (based on an
SVM classifier). The plot has as temporal axis (axis x) and each co-
ordinate in axis y represents nights in the dataset. The figure shows,
in red, the sleep activity hours according to the ground truth and, in
blue, the sleep activity hours calculated by the system. As both sleep
activity hours of the same night are plotted in the same y coordinate,
if the ground truth and the results coincide the color turns purple. If
the go to sleep time and/or wake up time do not coincide, there is a Figure 4. 1 month reporting.
text next to the corresponding side with the difference between the
time coming from the ground truth and that coming from the results.
In the middle of each bar there is the total time which results differ
from the baseline. To highlight the relevance of providing suitable information to car-
3
3
ers, let us mention here two cases that happened during Barcelona in- the bedroom during the night, number of sleeping hours the day
stallations in collaboration with Centre de Vida Independent6 . Case- before, number of sleeping hours in the five days before.
1. A woman with Alzheimer and heart problems needs continuously • MOOD: number of received visits, total time performing outdoor
assistance and, thus, a caregiver visits her daily. One day, eKauri de- activities, total time performing activities (both indoors and out-
tected that no visits were received, an alarm was generated and the doors), total time of inactivity, covered distance, number of per-
caregiver called. The caregiver confirmed that she did not go to visit formed steps, number of burned calories, hour the user went to
the user that day. Case-2. During the afternoon, a user is accustomed sleep, hour the user woke up, number of times the user went to
to go out for a walk. One day, she stayed in the bedroom. eKauri de- the toilet during the night, time spent at the toilet during the night,
tected the change in her habit and a caregiver called her. Actually, she number of time the user went to the bedroom during the night,
had a problem with a knee and she could not walk. A physiotherapist time spent at the bedroom during the night, number of sleeping
was asked to go to visit her. hours the day before, number of sleeping hours in the five days
before. The Classifier is a supervised multi-class classifier built
by using data previously labeled by the user and works on five
3.3 Assessing Quality of Life of Users
classes, Very Bad, Bad, Normal, Good, and Very Good.
In the dependency care sector, analyzing data gathered by sensors
may help in improving teleassistance systems in becoming aware of Under the umbrella of BackHome, we tested our approach with
user context. In so doing, they would be able to automatically in- 3 users with severe disabilities (both cognitive and motor) living at
fer user’s behavior as well as detect anomalies. In this direction, we their own real homes [30]. Although the system was evaluated by
studied a solution aimed at automatically assessing quality of life of using as ground truth answers given to QoL questionnaires that is
people [29]. The goal is twofold: to provide support to people in need an approach completely subjective that depends on the particularity
of assistance and to inform therapists, carers and families about the of each monitored user, after only 3 weeks of testing, the approach
improvement/worsening of quality of life of monitored people. seemed convincing. Results presented in this paper show that MO-
First, we defined a Visual Analogic Scale (VAS) QoL question- BILITY, SLEEPING, and MOOD can be inferred with a high accu-
naire composed of the following items: MOOD, HEALTH, MOBIL- racy (0.76, 0.72, and 0.81, respectively) by relying on an automatic
ITY, SATISFACTION WITH CARE, USUAL ACTIVITIES (which in- QoL assessment system. Let us note that SLEEPING was the method
cludes SLEEPING), and PAIN/DISCOMFORT. Those items have with the lowest performance. This is due to the fact that, currently,
been categorized in two families: monitorable and inferable. Mon- the system uses only motion sensors. Higher performances could be
itorable items can be directly gathered from sensors without relying expected when combining motion sensors with other ones, such as
on direct input from the user. Inferable items can be assessed by an- mat-pressure or light sensors. MOBILITY achieved higher perfor-
alyzing data retrieved by the system when considering activities per- mance results than SLEEPING especially when outdoor and indoor
formed by the user not directly linked with the sensors. features are merged together. In fact, using only outdoor features was
We performed experiments on two monitorable items (i.e., MO- not as reliable as combining with indoor. This can be due to the re-
BILITY and SLEEPING) and one inferable (i.e., MOOD). In partic- liability of the GPS system embedded in the smartphone that made
ular, we are able to detect and acknowledge the location of the user some errors in identifying when the user was really away. Let us also
over time as well as the covered distance in kilometers and the places note that this is an important result because disable people in gen-
where s/he stayed. At the same time, we can detect when the user is eral spend a lot of time at their home. Finally, MOOD reported the
sleeping as well as how many times s/he is waking up during the highest performances. Although at a first instance this could be sur-
night. Merging and fusing the information related to MOBILITY and prising, this fact might be explained considering the intrinsic correla-
SLEEPING, we may also infer the overall MOOD. tion between SLEEPING and MOBILITY, as highlighted by the ques-
The corresponding QoL assessment system is composed of a set tionnaire compiled daily by the users. It is worth noting that higher
of sub-modules, each one devoted to assess a specific QoL item; performances could be expected considering also social networking
namely: MOBILITY-assessment module; SLEEPING-assessment activities performed by the user.
module; and MOOD-assessment module. Each sub-module is com-
posed of two parts: Feature Extractor and Classifier. The Feature Ex-
tractor receives as input the list of notifications {n} and the list of ac- 4 Users’ Experience
tivities {a} and extracts the relevant features {f } to be given as input
The proposed solution has been developed according to a user-
to the Classifier. The Classifier, then, uses those features to identify
centered design approach in order to collect requirements and feed-
the right class Cl. This information will be then part of the overall
back from all the actors (i.e., end-users and their relatives, profes-
summary Σ.
sionals, caregivers, and social workers). For evaluation purposes, the
Each Feature Extractor works with its proper list of features:
system has been installed in two healthy-user homes in Barcelona
• MOBILITY: number of times the user left home, total time per- (control users).
forming outdoor activities, total time performing activities (both The system has been used in the EU project BackHome to monitor
indoors and outdoors), total time of inactivity, covered distance, disabled people. BackHome was an European R&D project that fo-
number of performed steps, number of visited places, number of cuses on restoring independence to people that are affected by motor
burned calories. impairment due to acquired brain injury or disease, with the over-
• SLEEPING: total sleeping time, hour the user went to sleep, hour all aim of preventing exclusion [21] [22]. In BackHome, informa-
the user woke up, number of times the user went to the toilet dur- tion gathered by the sensor-based system is used to provide context-
ing the night, time spent at the toilet during the night, number of awareness by relying on ambient intelligence [10]. Intelligent mon-
time the user went to the bedroom during the night, time spent at itoring was used in BackHome to study habits and to automatically
assess QoL of people. The BackHome system ran in 3 end-user’s
6 http://www.cvi-bcn.org/en/
home in Belfast.
4
4
In collaboration with Centre de Vida Independent7 , from May REFERENCES
2015 to January 2016, eKauri was installed in Barcelona in 13 el-
derly people’ homes (12 women) over 65 years old [28]. To test [1] Charilaos Akasiadis, Evaggelos Spyrou, Georgios Pierris, Dimitris
eKauri, monitored users were asked to daily answer to a question- Sgouropoulos, Giorgos Siantikos, Alexandros Mavrommatis, Costas
naire composed of 20 questions (12 optional). Moreover, they daily Vrakopoulos, and Theodoros Giannakopoulos, ‘Exploiting future in-
ternet technologies: the smart room case’, in Proceedings of the 8th
received a phone-call by a caregiver who manually verifies the data. ACM International Conference on PErvasive Technologies Related to
All detected events were shown in the Web applications and revised Assistive Environments, p. 85. ACM, (2015).
by therapists and caregivers. Feedback from them has been used to [2] Stelios Andreadis, Thanos G Stavropoulos, Georgios Meditskos, and
improve the interface and add functionality. Ioannis Kompatsiaris, ‘Dem@ home: Ambient intelligence for clinical
Although, at least at the beginning, users were a little bit reticent, support of people living with dementia’, in Proc. 1st Workshop on Se-
mantic Web Technologies in Pervasive and Mobile Environments (SEM-
during the monitored period they felt comfortable with the services PER2016), (2016).
provided by eKauri. In particular, they really appreciated the fact that [3] Urs Anliker, Jamie A Ward, Paul Lukowicz, Gerhard Tröster, Francois
it is not-intrusive and that it allows them to follow their normal lives. Dolveck, Michel Baer, Fatou Keita, Eran B Schenker, Fabrizio Catarsi,
In the case of CVI, people also be grateful for being called by phone. Luca Coluccini, et al., ‘Amon: a wearable multiparameter medical mon-
itoring and alert system’, Information Technology in Biomedicine, IEEE
In other words, it is important to provide a system that may become Transactions on, 8(4), 415–427, (2004).
part of the home without losing social interactions. Thus, a teleassis- [4] Alexander Artikis, Panagiotis D Bamidis, Antonis Billis, Charalampos
tance system does not substitute the role of caregivers. On the other Bratsas, Christos Frantzidis, Vangelis Karkaletsis, Manousos Klados,
side, carers recognized eKauri as a support to detect users’ habits Evdokimos Konstantinidis, Stasinos Konstantopoulos, Dimitris Kos-
helping in diagnosing user’s conditions and her/his decline, if any. mopoulos, et al., ‘Supporting tele-health and ai-based clinical decision
making with sensor data fusion and semantic interpretation: The use-
Currently, eKauri is installed in 40 elderly people’s homes in the fil case study’, in International Workshop on Artificial Intelligence and
Basque Country in collaboration with Fundación Salud y Comu- NetMedicine, p. 21, (2012).
nidad8 . [5] Louis Atallah, Benny Lo, Raza Ali, Rachel King, and Guang-Zhong
Yang, ‘Real-time activity classification using ambient and wearable
sensors’, Information Technology in Biomedicine, IEEE Transactions
on, 13(6), 1031–1039, (2009).
5 Conclusions [6] Luigi Atzori, Antonio Iera, and Giacomo Morabito, ‘The internet of
things: A survey’, Computer networks, 54(15), 2787–2805, (2010).
Considering the dependency care sector as a case study, in this paper [7] Debasis Bandyopadhyay and Jaydip Sen, ‘Internet of things: Applica-
tions and challenges in technology and standardization’, Wireless Per-
we highlighted how intelligent monitoring techniques, integrated in sonal Communications, 58(1), 49–69, (2011).
eKauri, an IoT-based teleassistance system, allow to better provide [8] NP Bidargaddi, A Sarela, et al., ‘Activity and heart rate-based mea-
assistance and support to people that need assistance. In particular, sures for outpatient cardiac rehabilitation’, Methods of information in
we focused on the power of intelligent monitoring in improving sen- medicine, 47(3), 208–216, (2008).
sor reliability, activity recognition, feedback provided to carers, as [9] Peter Bower, Martin Cartwright, Shashivadan P Hirani, James Barlow,
Jane Hendy, Martin Knapp, Catherine Henderson, Anne Rogers, Car-
well as quality of life of final users. As a matter of fact, results about oline Sanders, Martin Bardsley, et al., ‘A comprehensive evaluation of
independent home evaluation of eKauri show a good acceptance of the impact of telemonitoring in patients with long-term conditions and
the system by both home users and caregivers. Being promising, the social care needs: protocol for the whole systems demonstrator cluster
potential socio-economic impact of the exploitation of the system, randomised trial’, BMC health services research, 11(1), 184, (2011).
[10] Eloi Casals, José Alejandro Cordero, Stefan Dauwalder, Juan Manuel
as well as barriers and facilitators for future deployment, have to be Fernández, Marc Solà, Eloisa Vargiu, and Felip Miralles, ‘Ambient in-
analyzed before going to the market. telligence by atml: Rules in backhome’, in Emerging ideas on Informa-
Summarizing, our main conclusion is that time is ripe to adopt IoT tion Filtering and Retrieval. DART 2013: Revised and Invited Papers;
in the real world and that intelligent monitoring makes the difference C. Lai, A. Giuliani and G. Semeraro (eds.), (2014).
in providing feedback to the users. However, to become pervasive, in [11] Marie Chan, Eric Campo, and Daniel Estève, ‘Assessment of activity of
elderly people using a home monitoring system’, International Journal
particular in the dependency care sector, solutions must be taken into of Rehabilitation Research, 28(1), 69–76, (2005).
account the role of the final users in each phase of the development. [12] Angelika Dohr, R Modre-Opsrian, Mario Drobics, Dieter Hayn, and
Moreover, even if users at home and caregivers give a positive feed- Günter Schreier, ‘The internet of things for ambient assisted living’, in
back, one step ahead might be performed to allow that stakeholders 2010 Seventh International Conference on Information Technology, pp.
804–809. Ieee, (2010).
will take value from third generation teleassistance systems. It means [13] Juan Manuel Fernández, Marc Solà, Alexander Steblin, Eloisa Vargiu,
that, as technological providers, we must put into effect concrete so- and Felip Miralles, ‘The relevance of providing useful information to
lutions that give a twist in adapting innovative strategies. therapists and caregivers in tele*’, in DART 2014: Revised and Invited
Papers; C. Lai, A. Giuliani and G. Semeraro (eds.), (in press).
[14] Céline Franco, Jacques Demongeot, Christophe Villemazet, and Nico-
las Vuillerme, ‘Behavioral telemonitoring of the elderly at home: De-
Acknowledgments tection of nycthemeral rhythms drifts from location data’, in Advanced
Information Networking and Applications Workshops (WAINA), 2010
This research was partially funded by the European Community, un- IEEE 24th International Conference on, pp. 759–766. IEEE, (2010).
[15] Hulya Gokalp and Malcolm Clarke, ‘Monitoring activities of daily liv-
der the BackHome project (grant agreement n. 288566 - Seventh
ing of the elderly and the potential for its use in telecare and telehealth:
Framework Programme FP7/2007-2013), and the CONNECARE a review’, TELEMEDICINE and e-HEALTH, 19(12), 910–923, (2013).
project (grant agreement n. 689802 - H2020-EU.3.1). This paper re- [16] Jayavardhana Gubbi, Rajkumar Buyya, Slaven Marusic, and
flects only the authors’ views and funding agencies are not liable for Marimuthu Palaniswami, ‘Internet of things (iot): A vision, ar-
any use that may be made of the information contained herein. chitectural elements, and future directions’, Future Generation
Computer Systems, 29(7), 1645–1660, (2013).
[17] Wu He, Gongjun Yan, and Li Da Xu, ‘Developing vehicular data cloud
7 http://www.cvi-bcn.org/en/
services in the iot environment’, Industrial Informatics, IEEE Transac-
8 https://www.fsyc.org/
tions on, 10(2), 1587–1595, (2014).
5
5
[18] Chih-Lin Hu, Hung-Tsung Huang, Cheng-Lung Lin, Nguyen
Huu Minh Anh, Yi-Yu Su, and Pin-Chuan Liu, ‘Design and implemen-
tation of media content sharing services in home-based iot networks’,
in Parallel and Distributed Systems (ICPADS), 2013 International Con-
ference on, pp. 605–610. IEEE, (2013).
[19] Stephan Karpischek, Florian Michahelles, Florian Resatsch, and Elgar
Fleisch, ‘Mobile sales assistant-an nfc-based product information sys-
tem for retailers’, in Near Field Communication, 2009. NFC’09. First
International Workshop on, pp. 20–23. IEEE, (2009).
[20] Markos Markou and Sameer Singh, ‘Novelty detection: a review?part 1:
statistical approaches’, Signal processing, 83(12), 2481–2497, (2003).
[21] Felip Miralles, Eloisa Vargiu, Stefan Dauwalder, Marc Solà, Ger-
not Müller-Putz, Selina C. Wriessnegger, Andreas Pinegger, Andrea
Kübler, Sebastian Halder, Ivo Käthner, Suzanne Martin, Jean Daly,
Elaine Armstrong, Christoph Guger, Christoph Hintermüller, and Han-
nah Lowish, ‘Brain computer interface on track to home’, The Scientific
World Journal - Advances in Brain-Computer Interface, (submitted).
[22] Felip Miralles, Eloisa Vargiu, Xavier Rafael-Palou, Marc Solà, Stefan
Dauwalder, Christoph Guger, Christoph Hintermüller, Arnau Espinosa,
Hannah Lowish, Suzanne Martin, et al., ‘Brain computer interfaces on
track to home: Results of the evaluation at disabled end-users’s homes
and lessons learnt’, Frontiers in ICT, 2, 25, (2015).
[23] Xavier Rafael-Palou, Eloisa Vargiu, Stefan Dauwalder, and Felip Mi-
ralles, ‘Monitoring and supporting people that need assistance: the
backhome experience’, in DART 2014: Revised and Invited Papers; C.
Lai, A. Giuliani and G. Semeraro (eds.), (in press).
[24] Xavier Rafael-Palou, Eloisa Vargiu, Guillem Serra, and Felip Miralles,
‘Improving activity monitoring through a hierarchical approach’, in The
International Conference on Information and Communication Tech-
nologies for Ageing Well and e-Health (ICT 4 Ageing Well), (2015).
[25] Anand Ranganathan, Jalal Al-Muhtadi, and Roy H Campbell, ‘Rea-
soning about uncertain contexts in pervasive computing environments’,
IEEE Pervasive Computing, 3(2), 62–70, (2004).
[26] Emmanuel Munguia Tapia, Stephen S Intille, and Kent Larson, Activity
recognition in the home using simple and ubiquitous sensors, Springer,
2004.
[27] Chun-Wei Tsai, Chin-Feng Lai, and Athanasios V Vasilakos, ‘Future
internet of things: open issues and challenges’, Wireless Networks,
20(8), 2201–2217, (2014).
[28] Eloisa Vargiu, Stefan Dauwalder, Xavier Rafael-Palou, Felip Miralles
amd Alejandra Millet Pi-Figueres, Lluı̈sa Pla i Masip, and Cèlia Ri-
era Brutau, ‘Monitoring elderly people at home: Results and lessons
learned’, in 16th International Conference for Integrated Care 2016,
Barcelona, May 23-25, (2016).
[29] Eloisa Vargiu, Juan Manuel Fernández, and Felip Miralles, ‘Context-
aware based quality of life telemonitoring’, in Distributed Systems and
Applications of Information Filtering and Retrieval. DART 2012: Re-
vised and Invited Papers. C. Lai, A. Giuliani and G. Semeraro (eds.),
(2014).
[30] Eloisa Vargiu, Xavier Rafael-Palou, and Felip Miralles, ‘Experimenting
quality of life telemonitoring in a real scenario’, Artificial Intelligence
Research, 4(2), p136, (2015).
[31] Duan Yan-e, ‘Design of intelligent agriculture management information
system based on iot’, in Intelligent Computation Technology and Au-
tomation (ICICTA), 2011 International Conference on, volume 1, pp.
1045–1049. IEEE, (2011).
[32] Carme Zambrana, Xavier Rafael-Palou, and Eloisa Vargiu, ‘Sleeping
recognition to assist elderly people at home’, Artificial Intelligence Re-
search, 5(2), 64–70, (2016).
6
6