=Paper=
{{Paper
|id=Vol-2498/short13
|storemode=property
|title=Senior monitoring: a real case of applying a WiFi fingerprinting-based indoor positioning method for people monitoring
|pdfUrl=https://ceur-ws.org/Vol-2498/short13.pdf
|volume=Vol-2498
|authors=Raul Montoliu,Emilio Sansano,Arturo Gascó,Oscar Belmonte,Antonio Caballer
|dblpUrl=https://dblp.org/rec/conf/ipin/MontoliuSGBC19
}}
==Senior monitoring: a real case of applying a WiFi fingerprinting-based indoor positioning method for people monitoring==
https://ceur-ws.org/Vol-2498/short13.pdf
Senior Monitoring: A Real Case of Applying a
WiFi Fingerprinting-based Indoor Positioning
Method for People Monitoring
R. Montoliu1 , E. Sansano1 , A. Gasco1 , O. Belmonte1 , and A. Caballer1
Institute of New Imaging Technologies
Jaume I University
12071. Castellón. Spain
Email: [montoliu, esansano, agasco, belfern, caballer]@uji.es
Abstract. This paper presents our experience on a real case of applying
a Wi-Fi fingerprinting-based indoor localization system for monitoring
elder people in their own homes. The presented system is part of a broad
project called Senior Monitoring where the main aim is to monitor el-
ders to study behavioural patterns as a tool for early detection of some
cognitive decay diseases. Since the system is used by real users, there are
many situations that cannot be controlled by system developers and can
be a source of errors. This paper presents some of the problems arisen
when real non-expert users use localization systems, and discuss some
strategies to deal with such situations.
Keywords: WiFi fingerprinting · People monitoring · Real case
1 Introduction
In the last years, many Wi-Fi fingerprinting-based approaches have been pre-
sented [2, 6]. In most cases, the experiments have been performed in a very
controlled scenario. In these scenarios, the proposed algorithms usually perform
quite well [1, 5]. Unfortunately, in real-world applications, the conditions are
largely variable and there are a lot of possible sources of errors that can dras-
tically reduce the expected accuracy of the Indoor Positioning System (IPS)
[3].
This paper presents our experience in the development of a Wi-Fi fingerprinting-
based indoor positioning method to be used for monitoring people at their own
houses. In particular, this indoor localization method is part of a bigger project
called Senior Monitoring, where the main aim is to monitor elders to study be-
havioural patterns as a tool for early detection of some degenerative disease such
as Alzheimer.
The experiments presented in this paper were conducted in real scenarios
and by older adults, where the conditions are not controlled by the researchers.
For instance, each user has to create the radio map of his/her own house and,
therefore, there is no way of knowing if the training process has been performed
correctly. We should trust in the ability of the users performing this task.
2 R. Montoliu et al.
In order to introduce a mechanism to obtain a higher degree of certainty
about the quality of the training and, therefore, to know if the indoor localization
algorithm is performing well, a notification system has been developed to collect
validation samples. When the system detects stationary moments, the users are
asked about where they were at this particular interval of time. The answer
is then used to label the samples captured during this period. These labelled
samples can be used to validate the accuracy of the system and therefore can
be also used to improve the positioning system. But, since people using the
application are real users, many non-desirable situations can happen. The user
may not be sure of his/her localization during that interval of time, but still
answer the question, introducing a possible source of error. Situations like this
can produce badly labelled samples that can reduce the accuracy of the classifier.
This paper presents the experience obtained after the system was used by 17
volunteers (mostly elders) for two months on average at their own homes. Users
performed the radio map capturing task on their own and used the system
following the instructions provided by system’s developers. The present work
contributes to a better understanding of the difficulties and problems that arise
when implementing an indoor positioning system in real scenarios with real users.
2 Wi-Fi Fingerprinting-based Problem statement
The Received Signal Strength Indicator (RSSI) fingerprinting localization ap-
proach requires two phases of operation: a training phase, also known as off-line
or survey phase, and a positioning phase, sometimes referred to as online, oper-
ational or test phase. In the training phase, multi-dimensional vectors of RSSI
values (the fingerprints) are collected and associated with known locations. These
measurements are used to build the training data set (also known as radio map)
that covers the area of interest. Later, during the positioning (or test/on-line)
phase, an RSSI vector collected by a device is compared with the stored data to
generate an estimation of its position (see Figure 1a).
In this paper, the position has one dimension, since only the label of the
room is used. In this case, the localization problem can be solved using a pattern
recognition classifier, where the features and the labels of the training set are
the training fingerprints and the locations (room identifiers) where they were
captured, respectively. Therefore, the problem to solve in the positioning phase
is to estimate the location (room) of the user given the test fingerprint captured
at an unknown position.
3 Senior Monitoring
The Indoor Positioning System designed to perform these experiments is part
of the research project Senior Monitoring, which is aimed to provide solutions
for monitoring elderly people behavior and to detect short-term issues (falls),
and long-term issues also (cognitive decay). The IPS consists of a smart-watch,
which is worn by the user who is being monitored, and a paired smart-phone,
Senior Monitoring 3
(a) (b)
Fig. 1: a) An scheme of the on-line phase. b) Senior monitoring IPS overview.
(Icons made by Freepik from www.flaticon.com)
which is used to configure and control the smart-watch behavior and to commu-
nicate with a central cloud server (see Fig. 1b). The server stores the sensory
data gathered through the smart-watch and offers assistance to provide decision
support services by performing analysis tasks such as indoor positioning, activity
recognition or anomaly detection.
The software has been designed to make use of the following sensors:
– Wi-Fi. This sensor constitutes the base of the positioning system. The
smart-watch performs a given number of consecutive Wi-Fi scans every
minute. The default number of scans is 5, but it can be modified.
– Significant motion. It is a virtual sensor that uses the physical accelerom-
eter, but only triggers when it detects a motion that might lead to a change
in the user’s location. Thus, though this sensor does not allow to determine
the activity the user is performing, it provides a way to detect a possible
change in his/her location. Inversely, if it has not been triggered during an
interval of time, it may be assumed that the user has not changed his/her
location during that period.
Since the system is deployed in home, users manually create the radio map
wearing the smart-watch and following the indications of the smart-phone ap-
plication. The software guides the users to collect the training data in certain
points, such as the center or any regularly used location, of each room. When
this process finishes, the collected training data is sent to the server. During the
system’s normal operation, the data acquired by the device’ sensors is sent every
minute to the paired smart-phone, that dispatches it to the server to be stored
and analyzed.
4 R. Montoliu et al.
4 Proposed approach
For training, each participant must use the Senior Monitoring smart phone ap-
plication to create the radio map of his/her home. Users must select the room
and the type of training session to be performed. Then, the application commu-
nicates with the smart watch and it starts to capture fingerprinting samples. It
takes 100 consecutive samples at each training session.
The mobile phone application sends the information to the server, which
stores all the samples of each training session, together with information about
the user who performed it, date, type of training session selected and the room
type.
With this information, the system trains a pattern recognition classifier for
each user. This classifier will predict the room type given a set of several con-
secutive fingerprints as input. A well-known Random Forest (RF) model (using
a voting scheme) is used.
Once the classifier has been trained, the application starts to record a sample
each minute. Five consecutive fingerprints are captured for each sample. They are
sent to the server where the previously trained classifier is used to estimate the
current localization (room) of the user. The number of consecutive samples and
the capturing frequency can be adjusted through the smart phone application.
A validation phase has been introduced to obtain ground truth information
that can be used to get an estimation of the accuracy of the localization system.
For this purpose, the application uses the significant motion sensor to look
for time periods where the user did not move from the same room. A 20 minutes
threshold is used. When a period with no significant movement is found, the
application sends a notification to the user showing the interval of time and a
list of the most probable rooms where the user stayed, being the most probable
the first one. The user should select the room that he/she remembers to have
been staying during this time period.
5 Experiments and results
In order to test our proposed system, 17 volunteers used the Senior Monitoring
application for several weeks. Table 1 shows the ID of each user, his/her age, the
number of Wireless Access Point (WAPs) that can be perceived in their homes,
number of rooms trained, total number training sessions performed (Tr.) and
number of answered notifications (Not.). The last two rows show the median
and the standard deviation. Note that most of the users are more than 60 years
old.
In order to obtain a measure of the accuracy of the IPS for each user, two
ways of estimating the accuracy have been implemented. The first one, called
Notification accuracy is the average of times that the user selected the room that
the localization algorithm selected as the most probable. Assuming that the user
always provides the correct answer, this measure should be a good indication
of the accuracy of the indoor localization system. But, since there is not a way
Senior Monitoring 5
User Id Age # Days # WAPs # Rooms # Tr. # Not. Not. accuracy Test accuracy
1 30 154 100 4 17 21 100.00 95.33
2 48 56 40 6 19 54 40.00 70.25
3 50 75 92 5 15 102 95.76 92.27
4 55 48 11 6 24 98 11.92 27.75
5 55 35 28 5 5 22 54.54 64.03
6 62 21 17 5 5 22 45.45 32.23
7 64 63 89 6 6 50 16.00 61.14
8 64 58 52 5 12 46 87.50 66.51
9 66 127 63 6 14 186 95.03 66.70
10 67 61 16 5 5 181 40.29 40.56
11 68 45 18 6 26 13 36.84 46.43
12 69 60 1 6 13 196 43.60 49.64
13 70 107 22 5 13 46 60.87 38.02
14 73 40 3 5 10 71 21.95 27.31
15 73 37 78 5 5 32 17.95 35.30
16 74 123 52 5 15 164 85.51 81.73
17 79 54 19 5 5 105 11.50 18.96
µ 62.76 68.47 41.24 5.29 12.29 82.88 50.87 53.77
σ 12.05 37.10 32.76 0.59 6.72 63.35 31.37 23.24
Table 1: For each user, each row shows the ID, his/her age, the number of WAPs
that can be perceived in their homes, number of rooms trained, total number
training session performed and number of answered notifications. # stands for
number of. Last two columns show both ways of estimating the accuracy of the
IPS.
of knowing if the users did the task correctly a second way of estimating the
accuracy has been also tested. It is called Test accuracy. In this case, all the
samples belonging to the time periods of the answered notifications are labelled
using the room label provided by the user as ground truth and then, the classifier
estimates the label and compares it with the one provided by the user to estimate
the accuracy. Note that in both cases, we are assuming that the user provides
reliable information.
The last two columns of the Table 1 show both accuracy measures. It shows
that the localization system is working very well for some users, such as for
instance the users 1, 3 and 16, but very bad for others, such as users 4, 14 and
17. There are some surprising results as for instance users 2 and 7 that obtain
quite better results in the test accuracy than in the notification one and users 8
and 9 where the opposite happens.
6 Discussion
There are many different scenarios according to the number of WAPs that can
be perceived. Figure 2a shows that there is a relationship between the number
of WAPs and the two accuracy measures estimated. The blue points and the
6 R. Montoliu et al.
(a) (b)
(c)
Fig. 2: Relationship between the estimated accuracy and a) the number of WAPs
perceived in a scenario, b) the number of training sessions performed and c) and
the silhouette estimated after applying the T-SNE technique to the training set.
Blue points and the blue line are related to the notification accuracy and the
red crosses and red line are related to the test accuracy.
blue line are related to the notification accuracy and the red crosses and red
line are related to the test accuracy. Pearson’s correlation coefficients are 0.48
and 0.71, respectively. Figure 2a and Table 1 clearly show that the users 7 and
15 do not follow the regression line, i.e. they are scenarios with a big number
the WAPS but obtaining low accuracy. The Pearson’s correlation coefficients
have been recalculated without the data for these two users obtaining 0.86 and
0.88 showing that the most of cases follow the rule that when more WAPs are
perceived in the scenario, better accuracy can be obtained. According to this
fact, it is not surprising the bad results of users 12 and 14, with just 1 and 3
perceived WAPs, respectively.
Figure 2b shows the relationship between the number of training sessions
and the two accuracy measures estimated. Pearson’s correlation coefficients are
0.21 and 0.27, respectively, showing a very weak relationship. There are two
users (user 4 and 11) that despite the fact that they performed several training
Senior Monitoring 7
sessions, their estimated accuracy is quite low. Pearson’s correlation coefficients
without these two users are 0.65 and 0.68, respectively. Therefore, it seems that
better accuracy values could be obtained in most of the cases if users had per-
formed more training sessions. In particular, this could be crucial for the users
having performed just one training session of each room, i.e. for users 5, 6, 7,
10, 15 and 17.
Figure 2c shows the relationship between the silhouette measure[4] and the
two accuracy measures estimated. The silhouette is a well-known measure fre-
quently used in clustering analysis to study the quality of the results of the
clustering process. It provides, for each sample, a value from -1 to 1, where val-
ues close to 1 mean that the sample has been correctly classified. In our case, the
average of the silhouette measure for all samples has been estimated. The hy-
pothesis is that the better the silhouette measure, and therefore better separated
are the classes, the better accuracy should be obtained. Pearson’s correlation co-
efficients are 0.31 and 0.56. Similar to the previous cases, there are two users (7
and 15) that seem to be outliers, since despite having a good silhouette value,
the accuracy is not good. Pearson’s correlation coefficients, without these two
users, are 0.69 and 0.70. Note that users 7 and 15 are the same outliers detected
when studying the relationship between the number of WAPs and the accuracy.
Some conclusions that can be derived from the previous discussion is that
a good scenario should have many WAPS, a large number of training sessions
and the training samples should be well separated. In these conditions, it is
expected to obtain good accuracy results. But even in those cases, there are
exceptions, i.e. scenarios where the conditions seem to be quite good but the
accuracy obtained does not confirm this fact. Some possible sources of problems
may be the following:
– The Significant Motion Sensor used to determine static time periods some-
times needs some significant time to detect user motion. Therefore, it is pos-
sible that the user moves for some small period to other rooms and comes
back to the original position (for instance to go to the bathroom). The sys-
tem does not detect this movement and throws a notification to the user.
When the user labels the samples belonging to this time period, the samples
belonging to the room where the user stood just for a while are incorrectly
labelled.
– Sometimes the user does not remember well the place where he/she stayed.
But instead of using the ”I do not remember” option, he/she select the one
that thinks is the correct one since he/she wants to collaborate with the
study and thinks that this is the correct way of behaving. This introduces
incorrectly labelled samples.
– Users are high motivated volunteers but not always behave as they should.
Sometimes they do not perform correctly the training sessions since they do
not understand that there are many ways of introducing significant errors in
the training set.
– There are some special cases that are very difficult to deal with. For instance,
in many cases the bathroom is inside the bedroom or in other ones, the living
8 R. Montoliu et al.
room and the dining room are the same room. These special cases introduce
samples very similar in the feature space but with different labels. This fact
impacts negatively on the performance of the classifier.
7 Conclusion
This paper has presented our experience on a real case of applying a Wi-Fi
fingerprinting-based indoor localization system for monitoring of elder people
in their own homes. Since the system is used by real users, there are many
situations that cannot be controlled by system developers and that can be a
source of errors. From the results obtained, it seems that a good scenario should
have many WAPs, a large number of training sessions and the training samples
should be well separated. Under these conditions, good accuracy results can be
obtained. But even in those cases, there are exceptions. This paper has discussed
the possible causes of such low accuracy results. Future work will be focused on
improving the estimation of the static time period of the users and to improve
the information provided to the users about how to perform the training sessions.
Acknowledgment
This paper has been partially funded by projects: UJI-B2017-45 and RTI2018-
095168-B-C53. The authors would like to thank the volunteers for helping us in
the developing of the Senior Monitoring project.
References
1. Belmonte-Fernández, O., Puertas-Cabedo, A., Torres-Sospedra, J., Montoliu, R.,
Trilles, S.: An indoor positioning system based on wearables for ambient-assisted
living. Sensors 17(1) (2017)
2. Khalajmehrabadi, A., Gatsis, N., Akopian, D.: Modern wlan fingerprinting indoor
positioning methods and deployment challenges. IEEE Communications Surveys
Tutorials 19(3), 1974–2002 (2017)
3. Pérez-Navarro, A., Torres-Sospedra, J., Montoliu, R., Conesa, J., Berkvens, R.,
Caso, G., Costa, C., Dorigatti, N., Hernández, N., Knauth, S., Lohan, E.S., Machaj,
J., Moreira, A., Wilk, P.: Challenges of fingerprinting in indoor positioning and nav-
igation. In: Conesa, J., Pérez-Navarro, A., Torres-Sospedra, J., Montoliu, R. (eds.)
Geographical and Fingerprinting Data to Create Systems for Indoor Positioning and
Indoor/Outdoor Navigation, pp. 1 – 20. Intelligent Data-Centric Systems, Academic
Press (2019)
4. Rousseeuw, P.J.: Silhouettes: A graphical aid to the interpretation and validation
of cluster analysis. Journal of Computational and Applied Mathematics 20, 53 – 65
(1987)
5. Torres-Sospedra, J., Belmonte, O., Montoliu, R., Trilles, S., Calia, A.: How feasi-
ble is wifi fingerprint-based indoor positioning for in-home monitoring? In: 12th
International Conference on Intelligent Environments (IE’16) (2016)
6. Xia, S., Liu, Y., Yuan, G., hu, Z., Wang, Z.: Indoor fingerprint positioning based on
wi-fi: An overview. ISPRS International Journal of Geo-Information 6(5) (2017)