Indoor Position Detection Using Smartwatch and Beacons

Full text

1
Sensors and Materials, Vol. 32, No. # (2020) ##–##
MYU Tokyo
S & M ####
*Corresponding author: e-mail: sittichai.s@mail.kmutt.ac.th
https://doi.org/10.18494/SAM.2020.2386
ISSN 0914-4935 © MYU K.K.
https://myukk.org/
Indoor Position Detection Using Smartwatch and Beacons
Sittichai Sukreep,* Chakarida Nukoolkit, and Pornchai Mongkolnam
School of Information Technology, King Mongkut’s University of Technology Thonbu ri,
Thung Khru, Bangkok 10140, Thailand
(Received April 1, 2019; accepted October 31, 2019)
Keywords: indoor positioning, beacon, smartwatch, Bluetooth Low Energy, smart home system,
classication
Nowadays, the number of elderly and other people living alone is increasing. Although
living alone allows more independence, it raises the risk of serious or even fatal accidents. To
help assist those who live alone, we propose a monitoring system to detect indoor position by
using a smartwatch and beacons, which are effective and low cost, easy to install, convenient,
and unobtrusive in daily life. Data mining techniques were applied to classify indoor
positioning zones. A noise reduction process combining two data smoothing techniques was
incorporated. The best model for indoor positioning was chosen from various algorithms and
different window sizes of data to achieve the best usage in a real-time classification. Both
the number and positioning of beacons were also considered in this research. Various useful
screens with easy-to-understand visualizations are provided for monitoring subject behaviors
and time spent in certain areas, giving a summary of indoor positioning. Finally, the system
allows users to manage indoor positioning by combining the marked spots as zoning areas. The
management of different numbers of beacons and their locations is also provided to users.
1. Introduction
Currently, the world demographics is changing towards ageing societies. More elderly
people are now living alone rather than with their families. The number of people living alone
globally rose from 153.5 million in 1996 to 202.6 million in 2006 and is expected to further
increase by around 80% by 2026.(1) One-person households account for 28.9% of all households
in Western Europe, 26.7% in North America, and 25.7% in Australia.(2) In Japan, the most
rapidly ageing society in the world, around 30000 people die alone each year.(3)
Living alone could mean having more freedom, but could also mean degeneration into
unhealthy habits, which increase the risk of accidents, serious illness, and mortality. The risk
of hospitalization could be reduced by 26% and death by 80% if an immediate notification of
health problems is given to doctors or caregivers.(4)
Recent advances in sensing, networks, devices, and ambient intelligence have resulted in the
rapid emergence of smart environments. These technologies have attracted a lot of attention
This version has been created for advance publication by formatting the accepted manuscript.
Some editorial changes may be made to this version.

2 Sensors and Materials, Vol. 32, No. # (2020)
for the provision of enhanced healthcare services and user positioning for elderly people
living alone. Therefore, the deployment of an automatic, reliable, and cost-effective efficient
healthcare service and indoor positioning systems has become a significant research topic
during the past decade.
There are various technologies available for indoor positioning, such as Wi-Fi, Zig-
Bee, RFID, ultrawideband-radio, and Bluetooth, which are described in Refs. 5 and 6. The
specification for the Bluetooth 4.0 technology(7) was released in June 2010, which was named
“Bluetooth Low Energy” (BLE) or “Bluetooth Smart”, and major benefits of using the BLE
technology are low power consumption, cost, complexity, and bandwidth. However, the main
advantage of BLE technology is high penetration through obstacles. Indoor positioning is
commonly used in medium-size or large areas, such as in shopping malls, hospitals, airports,
museums, and other buildings.(8,9) It is mostly used for detection in wide areas such as
departments, floors, and rooms.(10 ,11) Larger areas have to simultaneously use more transmitters
to transmit the signal. Most previous researchers used smartphones, which are inconvenient in
terms of portability and wearability compared with smartwatches, which are more convenient
for use in real life.
Therefore, the approach presented in this paper can detect indoor locations using a
combination of beacons and a smartwatch. Furthermore, this proposed approach enables the
user to wear a smartwatch that interacts with beacons in a real environment, to adjust the
number of beacons and their setup positions, and to utilize our provided easy-to-understand
visualization. The first major contribution of this paper is to propose and demonstrate a high-
accuracy and cost-effective indoor positioning system that is suitable and unobtrusive for
elderly people and others living alone through the integration of a smartwatch and beacons.
The second major contribution is to provide an insightful and easy-to-understand visualization
of the whereabouts and timeline of the tracked subject. These visualizations allow caregivers to
better interact with and give behavior suggestions to the subject. The third major contribution is
to investigate and provide an adaptive system setup in terms of the number of beacons and their
locations, as well as merging areas into zones.
The proposed system was installed in a real environment with the aim of identifying
and tracking a person using the minimum number of devices while being convenient and
unobtrusive in daily life. Finally, a real-time prototype system was developed using a
smartwatch and beacons as a proof of concept. The system provides an easy-to-understand
visualization for monitoring and tracking subject behaviors.
2. Related Work
There are several available indoor positioning systems using different transmitter and
receiver devices. However, these systems or methods require rather sophisticated hardware or
infrastructure. This limitation motivated us to overcome their shortcomings. Previous indoor
positioning systems were developed with various techniques and transmitters as follows.

Sensors and Materials, Vol. 32, No. # (2020) 3
2.1 Wi-Fi-based technique
This indoor positioning technique uses a Wi-Fi access point (AP) to estimate the possible
position of the user. The rapid growth of APs has made it possible to develop this technique,
which has become popular for indoor positioning since it was first used in 2002. Many
researchers have used Wi-Fi-based methods. For instance, Maneerat and Kaemarungsi(12)
presented a robust floor determination algorithm called Robust Mean of Sum-RSS (RMoS)
using mobile objects to identify the location assuming either a fault-free scenario or reference
node (RN) failure. Qiyue et al.(13) proposed a Wi-Fi indoor location method based on the
collaboration of fingerprint and assistant nodes of the receiver signal strength indicator (RSSI)
to improve the positioning accuracy. Li et al.(14) developed an indoor mobile locator based on
important APs by selecting the highest RSSI and using their proposed important AP fingerprint
(IAP-FP) to identify the location in a classroom. Ji et al.(15) analyzed a practical path loss model
of the BLE signal compared with Wi-Fi signals for indoor positioning in line-of-sight (LOS)
communication. They used four beacons and two APs for comparison. Gu et al.(16) presented
a reduced fingerprint using APs and a smartphone. Their algorithm combined both sparsity
regularized singular value decomposition (SRSVD) and the k-nearest neighbor (KNN) (k =
4) algorithm with 10 locations. Razavi et al.(17) proposed a k-means-based method for floor
estimation via the fingerprint clustering of Wi-Fi. Seitz et al.(18) proposed a system that utilizes
a hidden Markov model that combines Wi-Fi positioning and dead reckoning for pedestrian
navigation optimized for smart mobile platforms. Liu et al.(19) proposed a technique and system
for surveying wireless indoor positioning.
Wi-Fi is suitable for longer distances (about 50 m), although it is difficult to set up. Wi-
Fi devices consume a large amount of energy and are relatively large, which makes them
impractical.
2.2 RFID-based techniques
RFID is a simple technology using radio frequency readers and tags that became popular
for indoor positioning in 2009. This technique has a high detection rate. However, RFID is
an expensive technology and obtrusive to the subject. Moreover, the effective communication
range of RFID is very short (about 1 m).
Huang et al.(20) proposed a real-time RFID indoor position system with the Kalman filter
and Heron-bilateration to filter noise for location estimation. Kung et al.(21) presented an
indoor location-aware application using the received signal strength indicator value of RFID for
identifying tag positions in a room and provided a calibration algorithm with a backpropagation
neural network (BPNN). Zou et al.(22) proposed cost-efficient RFID using cheaper active RFID
tags, sensors, and readers. Two location algorithms, namely, weighted path loss (WPL) and
extreme learning machine (ELM), have been proposed. Xiong et al.(23) designed and evaluated
a hybrid indoor positioning service that combined WSN and RFID technologies into a general-
purpose IoT environment. Ruiz et al.(24) presented a new method to accurately locate people
indoors using inertial navigation system (INS) techniques and active RFID technology.

4 Sensors and Materials, Vol. 32, No. # (2020)
2.3 BLE-based techniques
Basically, a beacon is used for transmitting data over short distances (about 10 m) and
transmits small advertising packages. This latest technology became popular as an indoor
positioning approach in 2014. The BLE beacon technology has several practical advantages
over other indoor positioning approaches, because the beacons have long battery lives and
are known for their low energy consumption and cost. The battery energy does not degrade
usage for proximity detection and provides indoor positioning throughout an entire indoor
environment. Previous researchers’ use of BLE can be grouped into three different categories
as follows.
First, floor and room type: Wang et al.(25) proposed a novel positioning method called
IWKNN (isomap-based weighted KNN) to measure the distance of RSSI vectors from beacons.
Liu and Liu(26) implemented a distributed system for collecting radio fingerprints by a mobile
device using iBeacon and WiFi APs to identify the location. Alletto et al.(27) proposed an
indoor location-aware system for an IoT-based smart museum using BLE signal strength
and combined it with image recognition to provide contents related to the observed artwork.
Similarly, Mainetti et al.(28) used the same devices and provided a tool for the implementation of
location awareness, and Budina et al.(29) used a heat map to measure and locate different rooms.
Thakkar et al.(30) developed an indoor position tracking system using a beacon and smartphone
to identify the beacon with the minimum distance for five different rooms. Similarly,
Ya n g et al.(31) proposed an intelligent in-room presence detection system to identify the location
of the user (inside or outside of the room) from different positions of the user’s smartphone.
Ya n g et al.(32) presented an iBeacon-based indoor system for hospitals. The system was
designed with a three-layer architecture, and the Floyd algorithm was used to recommend the
nearest department in a hospital.
Second, zoning area type: Fard et al.(33) developed the indoor positioning of mobile devices
with an agile iBeacon to identify the minimum distance among nine beacons for 18 locations
on the second floor of a building. Lin et al.(34) proposed a localization method to estimate
a patient’s location using RSSI from 12 beacons and using two filters to select the nearest
beacon. Ji et al.(15) developed an indoor location system using iBeacons with 18 zones, and
the KNN (k = 2) algorithm and a decision tree were used for evaluation. Li et al.(35) applied
the iBeacon model to identify the location of newborns in a hospital, where five beacons were
used in comparing the performance between the cumulative distribution function (CDF) and
the distance measure error (DME). Lee et al.(36) developed an indoor navigation system for
automatic guided vehicles based on relative distance estimation. Frontoni et al.(37) proposed an
analysis of human movement based on active beacons and AVM digital footprints. Posdorfer
and Maalej(38) developed a context-aware system to identify the locations in a room with four
levels (i.e., immediate, near, far, and unknown).
Third, distance and pedestrian type: Faragher and Harle(39) developed location fingerprinting
with BLE beacons to compare six Wi-Fi fingerprinting and 19 BLE beacons. In another
study using BLE, Rida et al.(40) designed and implemented an indoor location system based on
Bluetooth signal strength. The beacons were placed every 6 m and used to identify the three

Sensors and Materials, Vol. 32, No. # (2020) 5
nearest nodes with 12 locations. Liang and Krause(41) proposed a real-time indoor location
tracking system to identify a patient’s real-time location in a home environment, where the
Kalman filter was used for noise reduction. Chen et al.(42) proposed an indoor location system
that combined a smartphone and iBeacon to detect pedestrian steps and locations using a fusion
algorithm.
The proposed method belongs to the third category. Moreover, it can handle a larger
coverage area than the other methods of this type with a smaller number of beacons. In
addition, the proposed method has a higher precision as it can pinpoint a position within an area
of 1 × 1 m2 (with three beacons), while previous methods could only identify a position within
an area of 2 × 2 m2 (with four beacons). Most of the previous researchers used a smartphone as
a receiver, which could be obtrusive and inconvenient for the subject, for example, when taking
a shower or sleeping.
For these reasons, we used a smartwatch as a receiver instead of a smartphone, and beacons
were used as transmitters. Furthermore, we also investigated the potential minimum number of
beacons. In addition, the potential locations of the beacons were compared. Finally, a proposed
indoor positioning management function allowed the combination of the marked spots to define
zoning areas as they were more informative.
3. Methodology
3.1 System architecture
In this section, the requirements and functions of the system for indoor position detection
are introduced, and user subject feedback is provided with several easy-to-understand
visualizations.
An overview of the indoor positioning system is shown in Fig. 1. The smartwatch obtains
RSSI data from three beacons and sends the data to the server via Wi-Fi to classify indoor
positions. The system provides three key functions. First, an indoor positioning system and
an algorithm used for indoor location detection are proposed. Second, easy-to-understand
visualizations are proposed to illustrate subject positioning. Finally, a positioning management
function lets the user position the beacons as desired.
Fig. 1. (Color online) Architecture of proposed indoor positioning system.

6 Sensors and Materials, Vol. 32, No. # (2020)
The Android Wear smartwatch application was developed to collect the RSSI signal strength
levels from three beacons, and they were placed on the first-floor ceiling of a home. Machine
learning techniques were used to create the indoor positioning model and classify positions
in real time. The system provided summary reports to track users’ behaviors, such as which
areas they frequently spent time and for how long. Moreover, the system provided the users
with many interface screens to manage the areas or zones such as the living room, kitchen, and
bedroom.
3.2 Experimental setup
A two-story home was used for the indoor positioning experiment. The floor area was
approximately 3.5 × 10.6 m2. The middle area was split into three partitions, each with a size of 1.17
× 3.5 m2 in order to place the beacons. In our experiment, all beacons were placed on the first
floor only. The first beacon was placed at the end of the first partition, the second beacon at
the end of the second partition, and the last one on the opposite side in the middle of the second
partition. All beacons were placed on the ceiling as shown in Fig. 2.
Fig. 2. (Color online) (a) Beacons on the rst oor, (b) rst-oor plan and positions of three beacons, and (c)
second-oor plan.
(a)
(b)
(c)

Sensors and Materials, Vol. 32, No. # (2020) 7
Fig. 3. (Color online) Grids drawn on both oors with area of 1 × 1 m2.
Grids were drawn on both floors with one cell equivalent to 1 × 1 m2 as shown in Fig. 3.
There were 30 marked spots for the first floor and 33 for the second floor. The different
numbers of marked spots are due to the different areas of the floors (first floor: 10.5 × 3.5 m2
and second floor: 12 × 3.5 m2). The total number of marked spots in our experiment was 63.
A smartwatch was used to receive the BLE signal strength from the three beacons, and
it was placed on the user’s wrist, either on the left or right side, as shown in Fig. 4. The
specifications of the smartwatch were as follows: brand name: Moto 360 Gen 1; processor: TI
OMAP™ 3; memory: 4 GB internal storage + 512 MB RAM; connectivity: Bluetooth 4.0 Low
Energy; operating system: Android Wear™.(43)
3.3 Process model
In this section, an integrative model for detecting an indoor position is described. The
system is divided into five phases consisting of data collection, data preprocessing, data
transformation, model evaluation, and indoor positioning classification, as shown in Fig. 5.
3.3.1 Data collection
BLE signal strength was obtained from the smartwatch for the entire area of the two-story
home with 63 marked spots. The smartwatch was used as a receiver to collect the BLE signal
Fig. 4. (Color online) (a) Beacon, (b) smartwatch, and (c) smartwatch scans for beacons’ signal strengths.
(a) (b) (c)

8 Sensors and Materials, Vol. 32, No. # (2020)
strength, known as RSSI, from the three beacons installed on the first f loor. The data was
continually collected for 50 data points at each marked spot, which was repeated 10 times to
create the classifier model. A total of 63 × 50 × 10 = 31500 data points were used for training
and 63 × 50 × 3 = 9450 data points were used for testing, and the data underwent a normal
data mining process. It was cleaned because of a few occurrences of missing data, which were
caused by signal dropping and preprocessing before feature extraction. WEKA(4 4) software
was used to train the data with four chosen algorithms, including decision tree (J48), random
forest, naïve Bayes, and KNN (k = 3, 5, and 7) using 10-fold cross-validation. Subsequently, the
performance characteristics of all classifiers were compared among these four algorithms, and
the best one was selected for the real-time classification phase.
3.3.2 Data preprocessing
In data mining, the phase of preprocessing plays a crucial role, and the first concern is
to check for outlier data, which was carried out. This second phase in Fig. 5 is important
when dealing with different data scales. In this paper, the standard min-max normalization
technique(45) was selected to convert raw BLE signal strength data into the range of [0, 1].
3.3.3 Data transformation
There is a relationship between the BLE signal strength and the distance from the receiver to
the transmitter station: the shorter the distance, the stronger the signal. Moreover, the RSSI of
the transmitter is always fluctuating because of environmental effects, resulting in an error in
the obtained distance.
In this study, the noise from the beacons needed to be eliminated to make the data as smooth
as possible. For the data smoothing technique, the basic techniques of three median values
and their moving average values were combined. The three median values were obtained by
arranging the set of data values in ascending and selecting the three middle values as shown in
Fig. 6.
Fig. 5. Integrated phases of the proposed indoor positioning system using a smar twatch and beacons.

Sensors and Materials, Vol. 32, No. # (2020) 9
The moving average technique requires that, at each point in time, the average of the
observed values that surround a particular time is determined as
1
n
i
i
D
average n
=
=
∑
. (1)
Here, Di is the data in the ith period and n is the number of periods in the moving average,
which is set to 3 in our experiment.
Noise reduction techniques were compared among four approaches: raw data, moving
average, median, and hybrid noise reduction (combining three-median and moving average
approaches). In Fig. 7, it is shown that the three-median method (hybrid approach) is the
most robust and can eliminate the noise, making the data smoother than for the other three
approaches.
Four algorithms were used for testing and evaluating the model: decision tree (J48), random
forest, KNN (k = 3, 5, and 7) and naïve Bayes. Each of the four algorithms plus two more
options of KNN has 10 models, making a total of 60 models.
Every model was trained with 31500 data points, as shown in Table 1, using 10-fold cross-
validation to select the best classifier model to use in real time. Moreover, the best classifier
was tested with 9450 additional unseen data points to compare accuracy, precision, and recall
among the model-evaluating methods.
3.3.4 Model evaluation
In this study, the indoor positioning detection was carried out in an offline phase. Moreover,
every marked spot had an equal number of data points. Hence, accuracy, precision, and recall
were used to evaluate each model to find the best classifier as shown in Eqs. (2)–(4).
Fig. 6. (Color online) Examples of a three-median calculation.

10 Sensors and Materials, Vol. 32, No. # (2020)
To evaluate the performance of a classifier model, it is necessary to select suitable metrics to
measure the performance of the model. Researchers typically use a common set of metrics in
the literature including i) accuracy, ii) precision, recall, and accuracy, iii) accuracy, specificity,
and sensitivity, and iv) sensitivity and specificity. The results of a classifier are commonly
stored in an array known as a confusion matrix. This allows the learning algorithm’s
performance to be visualized in a specific table, and the model’s performance is evaluated using
Eqs. (2)–(4). An example of a confusion matrix is depicted in Table 2.
The accuracy of the system is the most extensively used performance indicator in
classification problems. It is defined as
TP TN
accuracy TP FN FP TN
+
=
+ ++
. (2)
The recall or sensitivity, or true positive rate, is the ratio of the number of correctly classified
positive instances to the total number of positive instances.
TP
recall TP FN
=
+
(3)
The precision or positive predicted value is the ratio of the number of correctly classified
positive instances to the total number of instances classified as positives.
TP
precision
TP FP
=
+
(4)
Fig. 7. (Color online) Comparison among the data smoothing techniques.
Tab le 1
Examples of marked spot and zoning area data.
Sample Input (RSSI from 3 beacons) Output
(class of marked spots: L01–L63)
Output
(class of zoning areas: 7 areas)
B1 B2 B3
Sample_1 0. 37161 0.26548 0. 24778 L01 Living room
Sample_2 0.35398 0.22123 0. 28318 L04 Living room
Sample_3 0.4 4247 0.23893 0.33628 L13 Bathroom
Sample_4 0. 2 8318 0.25663 0.36283 L38 Bedroom
⁝ ⁝ ⁝ ⁝ ⁝ ⁝
Sample_n0.45132 0.33628 0.40707 L63 Home oce

Sensors and Materials, Vol. 32, No. # (2020) 11
We not only evaluated the entire area but also compared the results for the first and second
floors of the home. The number of beacons was considered when comparing arrangements of
two beacons and three beacons. Moreover, for the arrangements of two beacons, the differences
among the possible arrangements of the two beacons were compared as shown in Fig. 8.
The data were compared using various window sizes, and the results are shown in Table 3.
These results show that the random forest model with a window size equal to 15 was the best
model for indoor positioning testing in the entire home.
The same data set was separated between the first and second f loors to ensure that the best
model would be used to detect the indoor positioning in real time. Both floors were tested
among the four algorithms plus two more options of KNN (a total of 60 models) and the same
eight window sizes as before, and the results are shown in Table 4 for the first floor and in Table
5 for the second floor. The results show that the first floor achieved a slightly higher accuracy
than the second f loor, with the ten random forest models having the best result for each window
size.
Among the four algorithms trained with 10-fold cross-validation, the best model is the
random forest. It gave the best accuracy of indoor positioning detection with 95.37% [standard
deviation (S.D.) = 0.045] for the entire home, 96.17% (S.D. = 0.063) for the first floor, and
95.24% (S.D. = 0.062) for the second floor.
In summary, the random forest model clearly had the highest accuracy for the entire house,
first floor, and second floor. Consequently, it was used to build our model for classifying the
indoor position in real time, as shown in phase 5 of Fig. 5.
4. Experimental Results
4.1 Testing data collection
Three BLE signal strength data sets were collected from the three beacons with 63 marked
spots in the same experimental environment as for training. The smartwatch was used as a
receiver. At each marked spot, 50 data points were continuously collected, and this was carried
out three times for the three beacons, providing a total of 63 × 50 × 3 = 9450 data points.
Tab le 2
Confusion matrix.
Predicted
True False
Actual Tr ue TP FN
False FP TN
True positives (TP): Number of posit ive instances that were classied as positive.
True negatives (TN): Number of negative instances that were classied as negative.
False positives (FP): Number of negative instances that were classied as positive.
False negatives (FN): Number of positive instances that were classied as negative.

12 Sensors and Materials, Vol. 32, No. # (2020)
Fig. 8. (Color online) Classication process for experiments with dierent placements of beacons.
Tab le 3
Results of indoor positioning testing for the entire home.
Algorithm/Accuracy (%)
Random
forest
Decision
tree (J48)
KNN
(k = 3)
KNN
(k = 5)
KNN
(k = 7)
Naïve
Bayes
Raw data 60.90 58.89 56.91 57.5 4 5 7.54 2 2. 55
Window size (s)
372.75 60.48 56.35 56.99 57. 31 22.75
584.06 75.22 76.30 75. 46 74 .67 31.3 3
788 .31 80.26 8 0. 61 79.65 78.63 31.4 8
991.14 84.09 84.48 83.26 81.88 31.52
11 92 .74 8 6.7 9 86.94 85.68 83.96 31.19
13 95.22 89.10 8 9.8 2 88.14 86.84 30.85
15 95.37* 90.82 91.8 0 89. 99 88.42 30.63
Tab le 4
Results of indoor positioning testing for the rst oor.
Algorithm/Accuracy (%)
Random
forest
Decision
tree (J48)
KNN
(k = 3)
KNN
(k = 5)
KNN
(k = 7)
Naïve
Bayes
Raw data 70.81 66.67 64.89 65.14 65.45 29.71
Window size (s)
376.37 68.65 72.52 72 .41 72.13 34.71
585.96 7 7.47 79.94 79.43 77. 2 6 37.73
789.75 82.36 82 .72 81.49 81.09 37.6 6
992 . 31 86.58 87. 2 5 85.94 85.19 37.36
11 94.15 88 .73 89.86 88.37 87. 0 4 37. 35
13 95.50 90.34 92.09 90.13 89.0 4 36.97
15 96 .17 * 91.8 9 93.65 91.77 90.29 3 6.7 3

Sensors and Materials, Vol. 32, No. # (2020) 13
4.1.1 Location detection evaluation
The indoor positioning data of the 63 marked spots from the two-story home was collected,
and then cleaned, preprocessed, and evaluated using the best model from the random forest
algorithm, with the noise reduced by different window sizes. Each marked spot (L01–L63)
was evaluated with three beacons, and an accuracy of 94.87% was obtained. In addition, with
the best model from the random forest algorithm, our method achieved both sensitivity and
specificity of about 0.95.
The marked spots on the first f loor, second floor, and entire home (both floors) were
comparatively evaluated with the same arrangement of the three beacons. The results are shown
in Table 6. The first f loor, where the three beacons were placed, had the highest accuracy of
classification using the best model from the random forest algorithm with various window sizes,
although the other accuracies were not significantly different.
To reduce the number of beacons, one beacon was removed, and the accuracies of only two
beacons were compared for three different arrangements: stations B1 and B2, stations B1 and
B3, and stations B2 and B3, as shown in Fig. 9.
The results of our experiment showed that the different arrangements of the two beacons
were not significantly different in terms of accuracy as shown in Table 7, although the accuracy
of any two-beacon arrangement was about 20% less than that of the three-beacon arrangement.
Our final comparison experiment was a comparison of indoor positioning detection accuracy
between the marked spots and the zoning areas. In real life, the caregiver would want to know
the whereabouts of the human subject in terms of zones such as the living room, bathroom,
kitchen, or bedroom.
Therefore, in our experiment, the home environment was separated into seven areas. The
first floor consisted of four zoning areas [i.e., living room (L01–L12), dining room (L13–L21),
kitchen (L22–L28), and bathroom (L29–L30)], and the second floor consisted of three areas [i.e.,
bedroom (L31–L47), bathroom (L48–L49), and home office (L50–L63)].
The results showed that, with the raw data (window size of 1) and the window size of 3, there
was a large difference in accuracy between marked spot detection and zoning area detection;
however, for window sizes of more than 3, the accuracy gap decreases and is less than 1% when
the window size is 15 as shown in Table 8 and Fig. 10.
Tab le 5
Results of indoor positioning testing for the second oor.
Algorithm/Accuracy (%)
Random
forest
Decision
tree (J48)
KNN
(k = 3)
KNN
(k = 5)
KNN
(k = 7)
Naïve
Bayes
Raw data 60.30 58.33 56.00 56.92 56 .76 22.25
Window size (s)
372.03 64.13 64.88 65.67 65.15 27.61
583.22 75.91 76.62 75.70 74.96 30.38
787. 4 4 81.39 81.90 80.87 79.66 30.37
990.24 83.83 8 4.70 83.00 81.57 30.57
11 91.82 86.47 8 7. 25 85.41 83.50 30 .17
13 94.27 89. 44 89.75 88.35 86.91 30.02
15 95.24* 90.82 91.63 90.19 88.64 29.75

14 Sensors and Materials, Vol. 32, No. # (2020)
There have been several indoor localization methods proposed with applications and services
using beacon devices. Our experiment was compared with other works in terms of the number
of beacons, the transmitting device, the type of detection, and the accuracy as shown in Table 9.
The noise reduction techniques with a window size of 15 used in the proposed method
achieved high accuracies (94.87% for the marked spots and 96.58% for the zoning areas) while
using only three beacons. Moreover, a data mining technique was applied with four algorithms
to test the classifiers and select the best model. On the other hand, none of the previous similar
works applied different window sizes or noise reduction techniques to remove data fluctuations
to improve accuracy.
Tab le 6
Results of the accuracy rate (%) among rst oor,
second oor, and entire home (both oors).
Floor/Accuracy (%)
1st oor 2nd oor Ave r age
both oors
Raw
data 70.056 58.207 60.635
Window
si ze (s)
369.583 59.268 63.082
583.139 82.929 82.037
788.500 86.237 86.534
990.778 88.257 88.942
11 91.861 90.202 90.529
13 94.278 93.662* 93.492
15 95.948* 93.167 94.866*
Fig. 9. (Color online) Arrangements of beacon stations: (a) beacon stations B1 and B2, (b) beacon stations B1 and
B3, and (c) beacon stations B2 and B3.
(a) (b)
(c)
Tab le 7
Results of dierent arrangements of two beacons.
Beacon station/Accuracy (%)
B1, B 2 B1, B 3 B2, B3
Raw
data 30.423 31.4 0 2 31. 058
Window
si ze (s)
333.453 34.378 36.323
552.698 52.077 54.815
759.577 6 0.119 60.979
963.175 64.828 64.339
11 66.459 67. 513 65.397
13 69.669 69.444 70.476
15 74.0 99 7 3. 814 74.932*

Sensors and Materials, Vol. 32, No. # (2020) 15
Tab le 8
Comparison of accuracy between marked spots and
zoning areas.
Data set/Evaluation, Accuracy (%)
63 Marked Spots 7 Zoning Areas
Raw
data 60.635 83.360
Window
si ze (s)
363.082 86.852
582.037 93.862
786.534 94.634
988.942 95.78 0
11 90.529 96.508
13 93.492 9 7. 090
15 94.866 96.575
Fig. 10. (Color online) Comparison of the i ndoor
positi on i ng a ccu r acy bet wee n ma rke d sp ots (63
marked spots: 1 × 1 m2) and zoning areas (7 zoning
ar eas) .
4.1.2 Indoor positioning visualization
In the proposed system, real-time indoor positioning feedback and easy-to-understand
summary visualization are provided as shown in Figs. 11–13. Historical data of the indoor
positioning is also provided. The system works by counting the amount of time (in minutes) of
each indoor position to monitor the frequencies and positions of the user at home. The system
allows the user to easily manage the zoning areas. For example, the user might want to combine
the marked spots L01–L10 as the living room, L11–L20 as the dining room, and L21–L25 as the
kitchen.
The number of beacons used and their locations can be adjusted, depending on the user’s
needs. The system provides a screen for monitoring the user’s behaviors and times spent in
certain areas with various display options, such as minute, hour, day, week, and month as shown
in Fig. 12.
Tab le 9
Comparison between the proposed system and similar systems presented in the literature.
Ref.
Receiver Transmitter type Detection type
Acc uracy (%)
No. of
Beacons Others Smartwatch Smartphone Others
No. of
marked
spots (Size)
No. of
rooms
Zoning
area
(25) 30 — — x — 24
(2 × 2 m2)— — 76.96
(30) 5 — — x — — 5 — 91.32
(38) 4 — — x — — — 3 89.71
(39) 19 3
Wi-Fi — x — — 19 —95
(less than 2.6 m.)
Proposed
method 3 — x — — 63
(1 × 1 m2)— 7
94.87
(with marked spots)
96.58
(with zoning areas)

16 Sensors and Materials, Vol. 32, No. # (2020)
Fig. 11. (Color online) Visualization of real-time indoor positioning monitoring shown by frequency.
Fig. 12. (Color online) Visualization of indoor positioning monitoring shown by time interval in real time.
Fig. 13. (Color online) Summary of the indoor positioning monitoring.
Furthermore, the system provides a screen for the user to manage the number of beacons and
group the locations into zoning areas to reduce cost and improve personalization. For example,
the user might want to use two beacons, e.g., B1 and B2, B1 and B3, or B2 and B3. The system
maps the classifier model with the user’s requirements for classification in real-time use.
5. Conclusion and Future Work
In this paper, a practical and affordable indoor positioning system is proposed by combining
beacons and a smartwatch, which provides a convenient and unobtrusive service for users.
Data mining techniques were applied to build the model and examine the indoor positioning
of the smartwatch’s wearer. Different numbers of beacons and window sizes of the data were
compared in terms of accuracy to reduce the number of beacons required and thus reduce the
cost of the system. The system was evaluated for an entire home, the first f loor only, and the

Sensors and Materials, Vol. 32, No. # (2020) 17
second floor only with the same number and positions of beacons. Moreover, the system was
developed with real-time visualizations to track indoor positions, monitor subject behaviors, and
issue a summary report. Finally, several visualizations were introduced showing an informative
timeline of the user’s locations and behaviors at home. The achieved accuracy rate of the indoor
positioning was 94.87% and the recall and precision were 0.95.
We plan to use this monitoring system for elderly people or others who may live alone to
monitor their behaviors and movement areas while at home so that we can learn more about
them. Furthermore, the system could be extended for use in hospitals, nursing homes, and
healthcare centers. The obtained information is useful for caregivers such as family members,
healthcare professionals, and doctors, especially in an aging society.
Acknowledgments
This work was supported by a Petchra Pra Jom Klao research scholarship from King
Mongkut’s University of Technology Thonburi (KMUTT). The authors would like to thank all
the members of the Data Science and Engineering Laboratory (D-Lab) of School of Information
Technology at KMUTT for their support. We also wish to thank Mr. Anthony French for
English proofreading and all the volunteers involved in our data collection.
References
1 R. Stepler: Smaller Share of Women Ages 65 and Older Are Living Alone: More Are Living with Spouse or
Children (Pew Research Center, Washington, D.C., 2016).
2 J. Vespa, J. M. Lewis, and R. M. Kreider: Curr. Popul. Rep. 20 (2013) 570.
3 Y. Fukukawa: J. Am. Geriatr. Soc. 59 (2 011) 174. h t t p s:/ /d oi.o r g /10.1111/ j.1532 -5 415. 2 010.03216 . x
4 N. Noury, A. Fleury, P. Rumeau, A. Bourke, G. Laighin, V. Rialle, and J. Lundy: 29th Annual Int. Conf.
IEEE Engineering in Medicine and Biology Society (IEEE, 2007) 1663. https://doi.org/10.1109/IEMBS.
2007.4352627
5 Z. Yang, Z. Zhou, and Y. Liu: ACM Comput. Surv. 46 (2013) 25. ht t p s://doi.or g /10.1145/2543581.2543592
6 K. S. Bok, Y. H. Park, J. I. Pee, and J. S. Yoo: Int. Conf. Multimedia, Computer Graphics, and Broadcasting
(Springer, 2011) 307.
7 B. S.I.G: Bluetooth Specification: w ww.bluetooth.com/what-is-bluetooth-technology/bluetooth (accessed
September 2018).
8 M. D. Rodriguez, J. Favela, E. A. Martínez, and M. A. Muñoz: IEEE Trans. Inf. Technol. Biomed. 8 (2004)
448. https://doi.org/10.1109/TITB.2004.837887
9 P. Thornycroft: White Paper, Aruba Networks 71 (200 9).
10 P. Martin, B.-J. Ho, N. Grupen, S. Muñoz, and M. Srivastava: Proc. 1st ACM Conf. Embedded Systems for
Energy-Ecient Buildings (ACM, 2014) 190. https://doi.org/10.1145/2674061.2675028
11 Y. Geng, J. Chen, R. Fu, G. Bao, and K. Pahlavan: IEEE Trans. Mob. Comput. 15 (2015) 656. https://doi.
org/10.1109/ T MC .2015. 2416186
12 K. Maneerat and K. Kaemarungsi: Mobil. Info. Syst. 2018 (2018). https://doi.org/10.1155/2018/4198504
13 Q. Li, W. Li, W. Sun, J. Li, and Z. Liu: IEEE Access 4 (2016) 2993. h t t ps://doi .o rg/10.1109/ACCE SS.
2016.2579879
14 P. Jiang, Y. Zhang, W. Fu, H. Liu, and X. Su: Int. J. Distrib. Sens. Netw. 11 (2015) 429104. https://doi.
org/10.1155/ 2015/429104
15 M. Ji, J. Kim, J. Jeon, and Y. Cho: 17th Int. Conf. Advanced Communication Technology (IEEE, 2015) 92.
ht tps://d oi .o rg /10.1109/ICACT.2015.7224764
16 Z. Gu, Z. Chen, Y. Zhang, Y. Zhu, M. Lu, and A. Chen: Comput. Commun. 83 (2016) 56. https://doi.
org/10.1016/j.co mc om.2015.09.02 2

18 Sensors and Materials, Vol. 32, No. # (2020)
17 A. Razavi, M. Valkama, and E.-S. Lohan: IEEE Globe. Worksh. 2015 (2015) 1. https://doi.org/ 10.1109/
GLOCOMW.2015.7414026
18 J. Seitz, T. Vaupel, S. Meyer, J. G. Boronat, and J. Thielecke: 7th Workshop on Positioning, Navigation and
Commu nicat io n ( I EE E, 2010) 120. htt p s://doi.or g/10.1109/ WPNC.2010.5650501
19 H. Liu, H. Darabi, P. Banerjee, and J. Liu: IEEE Trans. Syst. Man Cybern. Par t C Appl. Rev. 37 (2007) 1067.
20 C.-H. Huang, L.-H. Lee, C. C. Ho, L.-L. Wu, and Z.-H. Lai: IEEE Trans. Instrum. Meas. 64 (2014) 728. htt ps://
doi.o rg/10.1109/ T IM.2014.23476 91
21 H. Y. Kung, S. Chaisit, and N. T. M. Phuong: Int. J. Commun. Syst. 28 (2015) 625. https://doi.org/10.1002/
dac.2692
22 H. Zou, H. Wang, L. Xie, and Q.-S. Jia: 1st Int. Conf. Cyber-Physical Systems, Networks, and Applications (IEEE,
2013) 66. https: //doi.org /10.1109/CPSNA. 2013.661424 8
23 Z. Xiong, Z. Song, A. Scalera, E. Ferrera, F. Sottile, P. Brizzi, R. Tomasi, and M. A. Spirito: J. Embed. Syst.
2013 (2013) 6.
24 A. R. J. Ruiz, F. S. Granja, J. C. P. Honorato, and J. I. G. Rosas: IEEE Trans. Instrum. Meas. 61 (2011) 178.
ht tps://d oi .o rg /10.1109/ TIM.2011.2159317
25 Q. Wang, Y. Feng, X. Zhang, Y. Sun, and X. Lu: Mobil. Info. Syst. 2016 (2016). https://doi.org/10.1155/2016/
8765874
26 H.-H. Liu and C. Liu: Sensors 18 (2018) 3. https: //doi.org /10.3390/s18010 003
27 S. Alletto, R. Cucchiara, G. Del Fiore, L. Mainetti, V. Mighali, L. Patrono, and G. Serra: IEEE IoT J. 3 (2015)
24 4. ht t ps://doi.o rg/10.1109/J IO T.2015.25062 58
28 L. Mainetti, V. Mighali, and L. Patrono: IEEE Int. Conf. Communications (IEEE, 2015) 704. https://doi.
org/10.1109/ICC.2015.72484 04
29 J. Budina, O. Klapka, T. Kozel, and M. Zmítko: International and Interdisciplinary Conference on Modeling
and Using Context (Springer, Larnaca, 2015) p. 105.
30 M. S. A. Thakkar, M. S. Patel, and M. B. Kamani: Int. J. Adv. Res. Comput. Commun. Eng. 5 (2016 ) 161.
https://doi.org/10.17148/IJARCCE.2016.5341
31 Y. Yang, Z. Li, and K. Pahlavan: Int. Multi-Disciplinary Conf. Cognitive Methods in Situation Awareness and
Decision Suppor t (IEEE, 2016) 187. https://doi.org/10.1109/COGSIMA.2016.7497808
32 J. Yang, Z. Wang, and X. Zhang: Int. J. Smart Home 9 (2015) 161. https://doi.org/10.14257/ijsh.2015.9.7.16
33 H. K. Fard, Y. Chen, and K. K. Son: 28th Canadian Conference on Electrical and Computer Engineering (IEEE,
2015) 275. https: //doi.org /10.1109/CCEC E.2015.7129199
34 X.-Y. Lin, T.-W. Ho, C.-C. Fang, Z.-S. Yen, B.-J. Yang, and F. Lai: 37th Annual Int. Conf. of the IEEE
Engineering in Medicine and Biology Society (IEEE, 2015) 4970. https://doi.org/10.1109/ EMBC.2015.7319507
35 Z. Li, Y. Yang, and K. Pahlavan: 10th Int. Symp. Medical Information and Communication Technology (IEEE,
2016) 1. ht t ps://d oi .o rg /10.1109/I SM IC T.2 016.74989 06
36 J.-H. Lee, J. Uk-Jin, and Y.-S. Hong: 8th Int. Conf. Ubiquitous and Future Networks (IEEE, 2016) 424. https://
doi.o rg/10.1109/I CUF N.2016.7537063
37 E. Frontoni, A. Mancini, R. Pierdicca, M. Sturari, and P. Zingaretti: 24th Mediterranean Conf. Control and
Automation (IEEE, 2016) 605. https://doi.org/10.1109/MED.2016.7536047
38 W. Posdorfer and W. Maalej: Procedia Comput. Sci. 83 (2016) 42. ht t ps://doi .o rg /10.1016/j.proc s. 2016.0 4. 09 7
39 R. Faragher and R. Harle: IEEE J. Sel. Areas Commun. 33 (2015) 2418. https://doi.org/10.1109/JSAC.2015.
24302 81
40 M. E. Rida, F. Liu, Y. Jadi, A. A. A. Algawhari, and A. Askourih: 2nd Int. Conf. Information Science and
Control Engineering (IEEE, 2015) 769. https://doi.org/10.1109/ICISCE.2015.177
41 P. C. Liang and P. Krause: IEEE J. Biomed. Health. Inf. 20 (2015 ) 756. ht t ps://doi.o rg/10.1109/J BH I.2015.
2500439
42 Z. Chen, Q. Zhu, H. Jiang, and Y. C. Soh: 10th Conf. Industrial Electronics and Applications (IEEE, 2015)
1723. ht t ps://doi.org/10.1109/ICIE A.2015.733 4389
43 M. M. Company: Moto 360 Gen 1 Specications: http://www.motorola.com/we/products/moto-360-gen-1
(accessed September 2018).
44 E. Frank, M. Hall, and L. Trigg: The University of Waikato (2000).
45 J. Han, J. Pei, and M. Kamber: Data Mining: Concepts and Techniques (Elsevier, 2011).

Sensors and Materials, Vol. 32, No. # (2020) 19
About the Authors
Sittichai Sukreep received his B.S. in computer science from Mahasarakham
University, Thailand, in 2005 and his M.S. in software engineering from
School of Information Technology (SIT), King Mongkut’s University of
Technology Thonburi, Thailand, in 2013. He is currently a Ph.D. candidate in
Computer Science at SIT. His research interests include data mining, machine
learning, Internet of Things (IoT), and image processing.
Chakarida Nukoolkit received her Ph.D. degree in computer science from
the University of Alabama, USA, in 2001. She is an assistant professor
with the School of Information Technology, King Mongkut’s University of
Technology Thonburi, Thailand. She was the Head of Data and Knowledge
Engineering Lab (D-Lab) during 2012–2015. Her current research interests
include wellness and health monitoring systems, data mining, visualization,
and artificial intelligence.
Pornchai Mongkolnam received his Ph.D. degree in computer science from
Arizona State University, USA, in 2003 and currently works at School of
Information Technology (SIT) at King Mongkut’s University of Technology
Thonburi, Thailand. He is the Head of Data Science and Engineering
Laboratory (D-Lab) at SIT. His research interests include use-inspired
information technologies and applications, machine learning, and artificial
intelligence.