Research Paper

Journal of Engineering and Technological Sciences

Machine Learning-based Indoor Positioning Systems Using Multi-

Channel Information

Shu-Hung Lee 1, Chia-Hsin Cheng 2, Tzu-Huan Huang 2 & Yung-Fa Huang3

\\\\\\\\
1
School of Intelligent Manufacturing and Automotive Engineering, Guangdong Business and Technology
University, Qixingyan Scenic Area, Zhaoqing, Guangdong, 526020 China
2
Department of Electrical Engineering, National Formosa University, Wenhua Rd, Huwei, Yunlin, 632301 Taiwan
3
Department of Information and Communication Engineering, Chaoyang University of Technology, Jifeng E. Rd.,
Wufeng District, Taichung, 413310 Taiwan

Corresponding author: yfahuang@cyut.edu.tw

Abstract
The received signal strength indicator (RSSI) is a metric of the power measured by a sensor in a receiver. Many indoor
positioning technologies use RSSI to locate objects in indoor environments. Their positioning accuracy is significantly affected
by reflection and absorption from walls, and by non-stationary objects such as doors and people. Therefore, it is necessary
to increase transceivers in the environment to reduce positioning errors. This paper proposes an indoor positioning
technology that uses the machine learning algorithm of channel state information (CSI) combined with fingerprinting. The
experimental results showed that the proposed method outperformed traditional RSSI-based localization systems in terms
of average positioning accuracy up to 6.13% and 54.79% for random forest (RF) and back propagation neural networks
(BPNN), respectively.

Keywords: channel state information; indoor positioning; machine learning; RSSI; random forest; times.

Introduction
Nowadays, when people try to find an address, get lost, or are unsure of their current location, most of them
will use the positioning service provided by the Google Maps App to locate and track the target points. The
earliest positioning service technology can be traced back to the global positioning system (GPS) developed in
the nineteenth century. The target in this technology uses received satellite signals to perform positioning
algorithms to obtain 3D position information [1-4]. The positioning error decreases with an increase in the
number of satellites that signals can be received. This method can accurately locate and track outdoor places
but in complex environments, such as indoor places and deep mountain environments, the target cannot
maintain the line of sight (LOS) with satellites, which makes the positioning accuracy not good enough [5-7].
In recent years, 5G mmWave technology has also been in use for localization in addition to GPS. Reference [8]
proposed low-complexity channel estimation approaches in mmWave multiple-input single-output systems for
accurate indoor positioning. Reference [9] provides a brief overview of the use of massive MIMO arrays for
indoor localization in 5G, while a novel method for single-snapshot localization and mapping of the radio
environment using a single-antenna receiver in 5G mmWave systems was proposed in Reference [10].
Indoor positioning topology is carried out according to a positioning algorithm, and the metrics measured
between the transmitting and receiving devices are taken as an index of positioning judgment. The metrics
include time of arrival (TOA), time difference of arrival (TDOA), angle of arrival (AOA), received signal strength
indicator (RSSI), etc. TOA and TDOA require a high synchronization property for hardware devices [11-14], AOA
requires a directional antenna [15-18], RSSI judges the signal strength between transceivers and the distance is
measured by the logarithmic path loss method. Among them, the RSSI calculation is the most convenient. It does
not require additional hardware equipment for measurement, so that related studies have been developed
successively, such as enhancing the reliability of environmental changes to reduce data collection [19-22], data
filtering [23-26], and the comparison of indoor positioning with different communication technologies [27-30].

Copyright ©2023 Published by IRCS - ITB J. Eng. Technol. Sci. Vol. 55, No. 3, 2023, 373-383
ISSN: 2337-5779 DOI: 10.5614/j.eng.technol.sci.2023.55.4.2
Yung-Fa Huang et al. 374

However, the accuracy of positioning using RSSI is susceptible to reflection and absorption from walls and non-
stationary objects such as doors and people. Thus, it is necessary to increase transceivers in the environment to
reduce positioning errors.
To reduce positioning errors, it is necessary to increase the number of transceivers in the environment. However,
some research has proposed advanced methods for direct position estimation in dynamic multipath
environments that do not require an extensive deployment of transceivers. For example, [31] presents an
algorithm that estimates positions of multi-antenna receivers in dynamic multipath environments using
narrowband broadcast radio signals. Reference [32] proposes exploiting sparse spatiotemporal features of the
received waveforms to achieve localization in multipath environments using a tensor-based algorithmic
framework. Moreover, a novel approach that combines angle and velocity information for direct position
estimation in multipath environments where standard AOA-based techniques fail is presented in [33].
In addition, there are many types of machine learning (ML) algorithms and models that can be used for different
purposes, for instance, neural networks (NN) [34,35] and deep learning [36]. This paper proposes an indoor
positioning technology that adopts the machine learning (ML) algorithms of random forest (RF) and back
propagation neural networks (BPNN) using channel state information (CSI) combined with finger-printing to
improve the problem that the accuracy of RSSI positioning is easily affected by various indoor environmental
factors.
The rest of this paper is organized as follows. Related technologies are reviewed in Section 2. The experimental
environments and research methods are described in Section 3. The experimental results are discussed in
Section 4, and brief conclusions are given in Section 5.

Background

Channel State Information

CSI refers to known channel properties of a communication link. This information describes how a signal
propagates from the transmitter to the receiver and represents the combined effect of, for example, scattering,
fading, and power decay with distance. The CSI makes it possible to adapt transmissions to current channel
conditions, which is crucial for achieving reliable communication with high data rates in multi-antenna systems.
Therefore, multi-input multi-output-orthogonal frequency division multiplexing (MIMO-OFDM) precoding is
used to reduce environmental noise interference and receive multi-channel data [30].
When an OFDM system uses a channel frequency response (CFR) of statistical CSI to perform CSI data operations,
the frequency responses of different frequencies in a frequency band are slightly different due to frequency
selective fading in the frequency domain. Assume that its CFR is as shown in Eq. (1) in the case of infinite
bandwidth.
𝐻𝑘 = |𝐻(𝑘)|𝑒 ∠𝐻(𝑘) (1)

where H (k ) is the k-th subcarrier amplitude, and H (k ) is the phase of the k-th subcarrier. The CSI data
collected each time will be assembled into a set of matrices, as shown in Eq. (2).
𝐻 = [𝐻1 , 𝐻2 , 𝐻3 , . . . , 𝐻𝑖 ] (2)
where Hi is the i-th data of the receiving antenna. The CSI data, a complex number, can be expressed by
𝐻𝑖 = 𝐼𝑖 + 𝑗𝑄𝑖 (3)
where I i and Qi are the real part and imaginary part of the i-th CSI data respectively.

Fingerprinting
Fingerprinting uses two phases to predict the location of the target, namely the offline phase and the online
phase. In the offline phase, the environment is divided into several areas and randomly arranges reference
points (RP) in these areas, and multiple transmitters are set up in the environment. Then environment
exploration is conducted to collect the data of metrics of the detected radio signals from the transmitters at
375 Machine Learning-based Indoor Positioning Systems
DOI: 10.5614/j.eng.technol.sci.2023.55.4.2

many RPs of known locations to build an offline fingerprint database. Hence, each RP can be identified by its
fingerprint. In the online phase, the target measures metrics of the detected radio signals from the transmitters
at its position and uses the machine learning algorithm to predict the target’s position in the environment. The
machine learning model is trained by the fingerprint database built in offline mode.

Random Forest
Random Forest (RF) uses bagging to generate multiple sample sets and then generates multiple decision trees
(DT) through node segmentation and aggregates them into a forest, and finally makes predictions [37-39].
Bagging is an ensemble learning method. It uses bootstrapping to randomly extract a fixed number of sample
sets from the original database. After that the analyzed sample set data is put back into the original database. It
is then repeatedly extracted and recursed to form a variety of different sample sets.
For classification problems, the majority voting method is used to determine the output result. If it is a regression
problem, the output is the average prediction of the individual trees. The node segmentation of DT first uses
Classification and Regression Tree (CART) for node classification, and then performs node segmentation through
the Gini algorithm. The formula can be expressed as follows:
𝐼𝐻 = − ∑𝑐𝑗=1 𝑝𝑗 𝑙𝑜𝑔2 ( 𝑝𝑗 ) (4)
where c is the number of child nodes after the parent node is divided, and pj is the probability of this child node
in the class. Information gain (IG) is used to measure the quality of node classification, taking node A as an
example, as shown in Eq. (5):
𝑁𝑗
𝐼𝐺(𝐷𝑝 , 𝐴) = 𝐼𝐻 (𝐷𝑝 ) − ∑𝑚 𝐼 (𝐷 ) (5)
𝑗=1 𝑁 𝐻 𝑗

where IH(Dp) is the entropy of the parent node, IH(Dj) is the entropy of each split child node, N is the sample
number of parent node, and Nj is the sample number of each child node.
In the procedure of RF algorithm, first, the original database uses the bagging method to randomly select data
features and generate an input sample set. Secondly, it uses the Gini algorithm to split the nodes to form multiple
sets of DTs. Then it determines whether the number of sample sets needs to be increased. If the specified
number of samples is not reached, the input sample set will be returned to the original database recursively
until the set number of samples is reached. Finally, the majority voting method is used for the classification
problem. The average method is used to judge the results of the regression problem.

Back Propagation Neural Network

Figure 1 The procedure of the BPNN algorithm.

Yung-Fa Huang et al. 376

The BPNN architecture is mainly divided into an input layer, a hidden layer and an output layer, and the predicted
value of the output is calculated through forward propagation, after which the weights are updated by back
propagation. In this way, the model converges through repeated operations [40,41]. Figure 1 shows the
procedure of the BPNN algorithm. First, each input data is calculated linearly with the weight and is then
summed up at the next neuron. Finally, the activation function converts the linear equation into a nonlinear
equation to output the predicted value. Then it is checked whether the pre-set number of iterations is reached.
If not, then the weight of each neuron is updated through backpropagation. Otherwise, the predicted result will
be the output.

Experimental Environment and Research Methods

The experimental environment along with the hardware equipment used in this paper will be described in this
section. Moreover, the detailed research methods contain RF and BPNN combined with fingerprinting, which is
also depicted here.

Experimental Environment
The specifications of the experimental equipment used in this study are described as follows. The transmitting
device was an AP with two antennas, using a laptop as the receiving device. An IWL5300 network card with three
receiving antennas was installed in the laptop, which received the CSI data through three antennas. We used
Linux 802.11n CSI Tool’s commands to collect the CSI data and adjust the hardware parameters.
The experimental environment was located behind the communication classroom on the fifth floor of the
Department of Electrical Engineering, National Formosa University. The total area behind the communication
classroom was 9.9 meters by 5 meters, and the transmitter AP was placed in the classroom behind the middle
aisle. A schematic diagram is shown in Figure 2.

Test environment

Figure 2 Schematic diagram of the experimental environment.

The receiver could receive data from up to three antennas due to the effect of MIMO-OFDM. Each antenna
collected 30 sub-carriers. Thus, the three antennas could receive a total of 90 sub-carriers. The antennas were
arranged in descending order according to the received signal strength and were named antenna A, Antenna B,
and Antenna C. The strength curve of the three antenna shows in Figure 3.
377 Machine Learning-based Indoor Positioning Systems
DOI: 10.5614/j.eng.technol.sci.2023.55.4.2

Figure 3 The strength curves of the three antennas.

Research Methods
Figure 4 shows the target positioning procedure of the RF algorithm combined with the fingerprinting method.
First, the RP’s topology was performed in the testing environment, the AP transmission rate was changed, and
then the fingerprinting method was used to collect the data from each RP to build a database. We selected
Antenna A of the strongest signal for amplitude filtering and then judged the area positioning through the RF
algorithm. The filtered offline database was randomly selected by bagging to generate a sample set, and the DT
was generated by the Gini algorithm. Then it was checked if the number of sample sets had to be increased
according to the number of decision trees, n. Assuming that the maximum number of decision trees n was 2,000,
if n did not reach 2,000, the data was put back into the offline database to generate multiple sets of DT results.
Conversely, if n had reached 2,000, multiple sets of DT results were predicted. We used these for the
classification task in which the output result was judged by the majority voting method. Finally, the fingerprint
model of Antenna A was applied to Antenna B and Antenna C to compare the positioning accuracy of each
received antenna.
The procedure of the target localization of the BPNN algorithm combined with the fingerprinting method is
shown in Figure 5. First, the RP topology was performed in the environment to be tested, the AP transmission
rate was adjusted and then the fingerprint method was used to detect the data from each RP and a database
was built. The three antennas could receive 90 sub-carriers. We selected Antenna A with a strong signal for
amplitude filtering and then judge the target positioning through the BPNN algorithm.
The input layer is the number of received sub-carriers and performs linear operation with the weight, which is
added up at the next neuron, and finally the linear equation is converted into a nonlinear equation through the
activation function ReLU and the predicted value is output. Then judge whether the set number of iterations ep
is reached. Assuming that the maximum number of iterations ep is 1,000, if ep has not reached 1,000, the error
is calculated with multi-classification loss function CE through backpropagation, and the weights between the
neurons are updated through optimization function SGD. In contrast, when ep reaches 1,000, the output of the
positioning accuracy of Antenna A is performed, and finally, the neural network model is applied to Antenna B
and Antenna C to compare the positioning accuracy of each receiving antenna.
Yung-Fa Huang et al. 378

Figure 4 The procedure of RF combined with the fingerprinting method.

Experimental Results and Discussion

Zone I was located in the middle aisle in the environment where the signal was transmitted under the LOS
situation, so the signal could not easily be disturbed in the area. Another zone was located in the left area and
the right area, where the signal could easily be disturbed because the transmission path suffered from
interference by obstacles, for example, tables, chairs, and screens. Zone II in the environment was divided into
two levels of interference. The areas of different interference levels in the experimental environment are shown
in Figure 6.

Figure 5 The procedure of BPNN combined with the fingerprinting method.

379 Machine Learning-based Indoor Positioning Systems
DOI: 10.5614/j.eng.technol.sci.2023.55.4.2

Figure 6 The areas of different interference levels in the experimental environment.

The amplitude response for the different subcarriers on antenna A was measured first to check the possible
relationship between the positioning accuracy and the number of subcarriers. Figure 7(a) and (b) show the
amplitude response for 5 and 30 subcarriers on Antenna A, respectively. From Figure 7, it is clear that the more
subcarriers there are, the more CSI information there is.

Figure 7 Schematic diagram of the experimental environment.

To investigate the performance of the proposed ML-based positioning method combined with fingerprinting
using CSI information compared to RSSI information, three different experimental environments (A, B, and C)
were set up to ensure the reliability of the experimental results. In Environment A, the AP transmission rate was
60 Mbps, and the experimental environment was divided into 12 areas. Each area was further separated into 4
RPs, so Environment A had 48 RPs in total. Every RP could receive 90 subcarrier signals. The layout plan of
Environment A is shown in Figure 8.
Yung-Fa Huang et al. 380

AP sends CSI data with a AP sends CSI data with a

transmission rate of 60Mbps transmission rate of 60Mbps

Reference point (90 subcarriers Reference point (90 subcarriers

received each time) received each time)
(a) (b)
Figure 8 The layout plan of environment A: (a) training environment, (b) testing environment.

Environment B was an area (Zone II) where the signal was not easily interfered. The difference with Environment
A is that only the middle aisle was used for target positioning. The AP transmission rate was 60 Mbps. The
experimental environment to be tested was divided into six areas and separated each area into 4 RPs. There
were 24 RPs in total in Environment B. Each RP could receive 90 subcarrier signals. The layout plan of
Environment B is shown in Figure 9(a). Environment C was similar to Environment A. The only different
parameter was the number of subcarriers used for transmission. The number of subcarriers was 15 for
Environment C and 90 for Environment A. Environment C was used to investigate the impact of the difference
in the number of input subcarriers. The layout plan of Environment C is shown in Figure 9(b).

AP sends CSI data with a AP sends CSI data with a

transmission rate of 60Mbps transmission rate of 60Mbps

Reference point (90 subcarriers Reference point (15 subcarriers

received each time) received each time)
(a) (b)
Figure 9 Schematic diagram for training and testing with (a) Environment B, (b) Environment C.

In this study, two machine learning models, RF and BPNN, were tested in three environments using the metrics
of RSSI and CSI respectively to analyze and compare the accuracy of positioning and the impact factors. For the
RSSI case, the experimental results are listed in Table 1. The positioning accuracies of RF in Environments A, B,
and C were 85.22%, 94.72%, and 82.22% respectively, and the average value was 87.39%. Similarly, BPNN scored
20.41%, 43.88%, and 20.41% respectively, and the average was 28.23%.
381 Machine Learning-based Indoor Positioning Systems
DOI: 10.5614/j.eng.technol.sci.2023.55.4.2

The experimental results for the CSI case are shown in Table 2. The positioning accuracies for RF in Environments
A, B, and C were 99.3%, 100%, and 81.25% respectively, and the average was 93.52%. Similarly, BPNN scored
100%, 100%, and 49.16% respectively, and the average was 28.23%.
Table 1 Experimental results of RSSI positioning accuracy in different environments.
Environment
M L Method Average
A B C
RF (%) 85.22 94.72 82.22 87.39
BPNN (%) 20.41 43.88 20.41 28.23
Table 2 Experimental results of CSI positioning accuracy in different environments.
Environment
M L Method Average
A B C
RF (%) 99.3 100 81.25 93.52
BPNN (%) 100 100 49.16 83.05
From Table 1, it can be seen that the positioning accuracy for RF in Environments A, B, and C was 64.81%, 50.84%,
and 61.81% higher than that of BPNN respectively in the RSSI case. Thus, the RF model is more suitable for using
RSSI as input data than BPNN.
From Table 2, for the CSI case, the positioning accuracy of BPNN was better than RF in Environment A by 0.7%.
Both BPNN and RF were 100% correct in Environment B, but BPNN was 32.09% lower than RF. Environment B
was insusceptible to interference, so the positioning accuracy was higher than for the other environments.
Environment C used 15 subcarriers for transmission, 83.3% less than A, which used 90 subcarriers. This means
that the number of input data for the BPNN model in Environment C was smaller than in A, which is why the
positioning accuracy of BPNN in Environment C was so much worse than in A.
The summary of the experimental results is as follows:
1. Regardless of RF or BPNN, positioning accuracy is affected by environmental noise.
2. For the RF model, either using the measured values of RSSI or those of CSI, the positioning accuracy had at
least a good performance, i.e., at least 81.28%.
3. The positioning accuracy of the BPNN model is greatly affected by the number of subcarriers.
4. When using CSI as the input data for predicting the target position, the average positioning accuracy of RF or
BPNN was better than that of using RSSI, which was increased by 6.13% and 54.79% respectively.

Conclusion
This paper proposed an ML model combined with fingerprinting for indoor localization using CSI information.
Experiments were conducted on the positioning accuracy performance of RF and BPNN machine learning models
using RSSI and CSI information, respectively, in three different environments. The experimental results showed
that when RF and BPNN were used to determine the target position, the average positioning accuracy of using
CSI information was increased by 6.13% and 54.79%, respectively, compared with RSSI information. Therefore,
for the RF and BPNN machine learning algorithms, the use of CSI can effectively improve the positioning accuracy
of the target. However, it was found from the experimental results that the number of subcarriers impacts the
performance of the BPNN model. The relationship between the number of subcarriers and the positioning
accuracy of BPNN is worthy of further research in the future. Whether the CSI information input can improve
other ML models for indoor positioning is also worth considering.
The main objective of this paper was to show the effect and practical advantages of the proposed indoor
positioning technology, which leverages channel state information (CSI) with a combination of fingerprinting
and a machine learning algorithm. Even though this approach demands more computational resources
compared to conventional techniques like RSS/TOA/AOA, the increased computational cost of the combined
fingerprinting and machine learning algorithm of the CSI approach is justified by the superior accuracy it provides
in indoor positioning when compared to traditional methods such as RSS/TOA/AOA.
Yung-Fa Huang et al. 382

Acknowledgements
This research was funded by National Science and Technology Council (NSTC), R.O.C. grant number NSTC 112-
2221-E-324-010.

References
[1] Mulla, A., Baviskar, J., Baviskar, A. & Bhovad, A., GPS Assisted Standard Positioning Service for Navigation
and Tracking: Review & Implementation, Proc. International Conference on Pervasive Computing (ICPC),
January 2015. doi: 10.1109/PERVASIVE.2015.7087165.
[2] Chunhakam, P., Pummarin, P., Jeen-im, P., Wardkien, P., Wisartpong, P. & Lertteerada, K., GPS Positon
Predicting System by Kalman Filter with Velocity from OBD and Direction from Magnetometer, Proc. 9th
International Electrical Engineering Congress (IEECON), pp. 444-447, 2021.
[3] Kaewket, P. & Sukvichai, K., Investigate GPS Signal Loss Handling Strategies for a Low Cost Multi-GPS
system based Kalman Filter, Proc. 19th International Conference on Electrical Engineering/Electronics,
Computer, Telecommunications and Information Technology (ECTI-CON), pp. 1-4, 2022.
[4] Abidin, H.Z., Andreas, H., Gamal, M., Surono & Hendrasto, M., Studying Landslide Displacements in
Megamendung (Indonesia) Using GPS Survey Method, Journal of Engineering and Technological Sciences,
36(2), pp.109-123, 2004.
[5] Vo, Q. D. & De, P., A Survey of Fingerprint-Based Outdoor Localization, IEEE Comm. Surveys & Tutorials,
18(1), pp. 491–506, 2015.
[6] Garvanov, I. & Garvanova, M., Improving GPS Positioning of Vehicles in Urban Environment, Proc. 21st
International Symposium on Electrical Apparatus & Technologies (SIELA), pp. 1-5, 2020.
[7] Shi, Z., Deng, Z., Zheng, W. & Li, N., Campus Indoor and Outdoor Positioning System based on GPS and
Wi-Fi, Proc. 9th International Conference on Dependable Systems and Their Applications (DSA), pp. 903-
908, 2022.
[8] Fascista, A., De Monte, A., Coluccia, A., Wymeersch, H. & Seco-Granados, G., Low-Complexity Downlink
Channel Estimation in mmWave Multiple-Input Single-Output Systems, IEEE Wireless Communications
Letters, 11(3), pp. 518-522, 2022.
[9] Wen, F., Wymeersch, H., Peng, B., Tay, W.P., So, H.C. & Yang, D., A Survey on 5G Massive MIMO
Localization, Digital Signal Processing, 94, pp. 21-28, 2019.
[10] Fascista, A., Coluccia, A., Wymeersch, H. & Seco-Granados, G., Downlink Single-Snapshot Localization and
Mapping with a Single-Antenna Receiver, IEEE Transactions on Wireless Communications, 20(7), pp.
4672-4684, 2021.
[11] Maqsood, B. & Naqvi, I.H., Sub-Nyquist Rate UWB Indoor Positioning Using Power Delay Profile and Time
of Arrival Estimates, Proc. IEEE 86th Vehicular Technology Conference (VTC-Fall), pp. 1-5, 2017.
[12] Makki, A., Siddig, A., Saad, M., Cavallaro, J.R. & Bleakley, C.J., Indoor Localization Using 802.11 Time
Differences of Arrival, IEEE Trans. Instrumentation and Measurement, 65(3), pp. 614-623, 2016.
[13] Chugunov, A., Petukhov, N. & Kulikov, R., ToA Positioning Algorithm for TDoA System Architecture, Proc.
International Russian Automation Conference (RusAutoCon), pp. 871-876, 2020.
[14] Ahmed, S., Abbasi, A. & Liu, H., A Novel Hybrid AoA and TDoA Solution for Transmitter Positioning, Proc.
International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1-7, 2021.
[15] Bnilam, N., Ergeerts, G., Subotic, D., Steckel, J. & Weyn, M., Adaptive Probabilistic Model Using Angle of
Arrival Estimation for IOT Indoor Localization, Proc. International Conference on Indoor Positioning and
Indoor Navigation (IPIN), pp. 1-7, 2017.
[16] Bnilam, N., Tanghe, E., Steckel, J., Joseph, W. & Weyn, M., ANGLE: ANGular Location Estimation
Algorithms, IEEE Access, 8, pp. 14620-14629, 2020.
[17] Alteneiji, A., Ahmad, U., Poon, K., Ali, N. & Almoosa, N., Indoor Localization in Multi-Path Environment
based on AoA with Particle Filter, Proc. 3rd International Conference on Signal Processing and Information
Security (ICSPIS), pp. 1-4, 2020.
[18] Zhao, X. & Yang, Y., An AOA Indoor Positioning System Based on Bluetooth 5.1, Proc. 11th International
Conference of Information and Communication Technology (ICTech), pp. 511-515, 2022.
[19] Zhu, J.Y., Zheng, A.X., Xu, J. & Li, V.O., Spatio-Temporal (S-T) Similarity Model for Constructing WIFI-Based
RSSI Fingerprinting Map for Indoor Localization, Proc. International Conference on Indoor Positioning and
Indoor Navigation (IPIN), pp. 678-684, 2014.
383 Machine Learning-based Indoor Positioning Systems
DOI: 10.5614/j.eng.technol.sci.2023.55.4.2

[20] Ezpeleta, S., Claver, J., Perez-Solano, J. & Marti-Aviles, J., RF-Based Location Using Interpolation Functions
to Reduce Fingerprint Mapping, Sensors, 15(10), pp. 27322-27340, 2015.
[21] Ketabalian, H., Biguesh, M., & Sheikhi, A., A Closed-Form Solution for Localization Based on RSS, IEEE
Transactions on Aerospace and Electronic Systems, 56(2), pp. 912-923, 2020.
[22] Yinjing, G., Xianqi, S., Lei, Y. & Wenhong, L., A Coal Mine Underground Localization Algorithm Based on
the Feature Vector, Journal of Engineering and Technological Sciences, 51(2), pp. 184-197, 2019.
[23] Xue, W., A New Weighted Algorithm Based on the Uneven Spatial Resolution of RSSI for Indoor
Localization, IEEE Access, 6, pp. 26588-26595, 2018.
[24] Zafari, F., Papapanagiotou, I. & Hacker, T.J., A Novel Bayesian Filtering Based Algorithm for RSSI-Based
Indoor Localization, Proc. IEEE International Conference Communications (ICC), pp. 1-7, 2018.
[25] Tian, X., Wei, G., & Wang, J., Target Location Method Based on Compressed Sensing in Hidden Semi
Markov Model, Electronics, 11(11), pp. 1715, 2022.
[26] Avendaño-Lopez, C.M., Castro-Sanchez, R., Almanza-Ojeda, D.L., Avina-Cervantes, J.G., Gomez-Martinez,
M.A .& Ibarra-Manzano, M.A., Scalable Visible Light Indoor Positioning System Using RSS, Mathematics,
10(10), 1738, 2022.
[27] Sadowski, S. & Spachos, P., RSSI-Based Indoor Localization with the Internet of Things, IEEE Access, 6, pp.
30149-30161, 2018.
[28] Xue, W. Qiu, W., Hua, X. & Yu, K., Improved Wi-Fi RSSI Measurement for Indoor Localization, IEEE Sensors
Journal, 17(7), pp. 2224-2230, 2017.
[29] Mahmud, M.I., Abdelgawad, A., Yanambaka, V.P. & Yelamarthi, K., Packet Drop and RSSI Evaluation for
LoRa: An Indoor Application Perspective, Proc. IEEE 7th World Forum on Internet of Things (WF-IoT), pp.
913-914, 2021.
[30] Yao, L., Peng, X., Shi, D. & Liu, B., Design of Indoor Positioning System Based on RSSI Algorithm, Proc.
International Conference on Management Science and Software Engineering (ICMSSE), pp. 145-148,
2021.
[31] Fascista, A., Coluccia, A. & Ricci, G., A Pseudo Maximum Likelihood Approach to Position Estimation in
Dynamic Multipath Environments, Signal Processing, 181, 107907, 2021.
[32] Zhao, H., Huang, M. & Shen, Y., High-Accuracy Localization in Multipath Environments via Spatio-
Temporal Feature Tensorization, IEEE Transactions on Wireless Communications, 21(12), pp. 10576-
10591, 2022
[33] Fascista, A., Coluccia, A. & Ricci, G., Direct Position Estimation of a Mobile Receiver in Multipath
Environments via Adaptive Beamforming, 28th European Signal Processing Conference (EUSIPCO),
Amsterdam, Netherlands, pp. 1782-1786, 2021.
[34] Tripura, J., Roy, P. & Barbhuiya, A.K., Application of RBFNNs Incorporating MIMO Processes for
Simultaneous River Flow Forecasting, Journal of Engineering and Technological Sciences, 50(3), pp.434-
449, 2018.
[35] Ushada, M., Wijayanto, T., Trapsilawati, F. & Okayama, T., Modeling SMEs’ Trust in the Implementation
of Industry 4.0 using Kansei Engineering and Artificial Neural Network: Food and Beverage SMEs Context,
Journal of Engineering and Technological Sciences, 53(2), 210203, 2021.
[36] Nguyen, H., Phan, T., Dao, T., Phuc, P., Nguyen, C., Pham, N. & Huynh, H., Gene Family Abundance
Visualization based on Feature Selection Combined Deep Learning to Improve Disease Diagnosis, Journal
of Engineering and Technological Sciences. 53(1), pp. 99-115, 2021.
[37] Sanam, T.F. & Godrich, H., An Improved CSI Based Device Free Indoor Localization Using Machine Learning
Based Classification Approach, Proc. 26th European Signal Processing Conference (EUSIPCO), pp. 2390-
2394, 2018.
[38] Wang, Y., Xia, S., Tang, Q., Wu, J. & Zhu, X., A Novel Consistent Random Forest Framework: Bernoulli
Random Forests, IEEE Trans. Neural Networks and Learning Systems, 29(8), pp. 3510-3523, 2018.
[39] Bicego, M. & Escolano, F., On learning Random Forests for Random Forest-clustering. Proc. 25th
International Conference on Pattern Recognition (ICPR), pp. 3451-3458, 2021.
[40] Cheng, C.H., Huang, Y.H. & Chen, H.C., Enhanced Channel Estimation in OFDM Systems with Neural
Network Technologies, Soft Computing, 23, pp. 5185-5197, 2019.
[41] Dong, Z., Wu, C., Fu, X. & Wang, F., Research and Application of Back Propagation Neural Network-Based
Linear Constrained Optimization Method, IEEE Access, 9, pp. 126579-126594, 2021.

Manuscript Received: 19 November 2022

1st Revised Manuscript Received: 5 April 2023
2nd Revised Manuscript Received: 12 May 2023
Accepted Manuscript: 22 May 2023