IAES International Journal of Artificial Intelligence (IJ-AI)

Vol. 11, No. 3, September 2022, pp. 977~985

ISSN: 2252-8938, DOI: 10.11591/ijai.v11.i3.pp977-985  977

Pipe leakage detection system with artificial neural network

Muhammad Iqmmal Rezzwan Radzman1, Abd Kadir Mahamad1, Siti Zarina Mohd Muji1, Sharifah
Saon1, Mohd Anuaruddin Ahmadon2, Shingo Yamaguchi2, Muhammad Ikhsan Setiawan3
1
Faculty of Electrical and Electronic Engineering, University of Tun Hussein Onn Malaysia, Johor, Malaysia
2
Graduate School of Sciences and Technology for Innovation, Yamaguchi University, Ube, Japan
3
Faculty of Civil Engineering, Narotama University, Surabaya, Indonesia

Article Info ABSTRACT

Article history: This project aims to develop a system that can monitor to detect leaks in
water distribution networks. It has been projected that leakage from
Received Jul 21, 2021 pipelines may lead to significant economic losses and environmental
Revised Apr 8, 2022 damage. The loss of water from leaks in pipeline systems accounts for a
Accepted May 7, 2022 large portion of the water supply. Pipelines are maintained throughout their
lives span; however, it is difficult to avoid a leak occurring at some point. A
tremendous amount of water could be saved globally if automated leakage
Keywords: detection systems were introduced. An embedded system that monitors
water leaks can efficiently aid in water conservation. This project focuses on
Artificial neural networks developing a real-time water leakage detection system using a few types of
Cloud database sensors: water flow rate sensor, vibration sensor, and water pressure sensor.
Google sheets The data from the sensors is uploaded and stored by the microcontroller
Real-time water leakages (NodeMCU V3) to the database cloud (Google Sheets). The data that is
stored in the database is analyzed by artificial neural network (ANN) by
using Matlab software. An application is developed based on results from
ANN training to detect the leakage event. Implementing the proposed
system can increase operations efficiency, reduce delay times, and reduce
maintenance costs after leaks are detected.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Abd Kadir Mahamad
Department of Electrical and Electronic Engineering, Faculty of Electrical and Electronic Engineering,
University Tun Hussein Onn Malaysia
86400 Parit Raja, Johor, Malaysia
Email: [email protected]

1. INTRODUCTION
Pipelines are becoming a more popular method for transporting bulk water in many nations since it
is a safe and cost-effective alternative. Each year, a large number of new pipelines are arranged and built-in
public and worldwide. Pipeline leaks can potentially cause a wide range of natural disasters and financial
problems [1]–[6]. The outflow of treated water from this country is higher than 4,27 billion liters due to
ageing pipelines. A leading expert warns that unless reactionary measures are taken, more will be wasted.
The consequences of this problem may also harm society [7]–[11].
For example, a water treatment plant pipeline leak at Sungai Selangor caused a water cut in October
2020. In a statement, Air Selangor reported that more than 686 areas in Petaling Jaya, Gombak, Klang, Shah
Alam, Kuala Lumpur, and Hulu Selangor districts were affected. Societies and economies are negatively
impacted by this situation [12]. A pipeline can leak for various reasons, such as incorrect installation,
the movement of soil around the pipeline, the depth of placement of the pipeline, and the material of
the pipeline itself. In order to minimize damage, leak detection that is accurate and enables a quick response
is imperative [13].

Journal homepage: http://ijai.iaescore.com

978  ISSN: 2252-8938

As per the specification report by Ranhill SAJ 2018, clean water shall be used for pipe leak testing,
and air trapped inside the system shall be exhausted via a vent. A pressure test conducted at the end of 24
hours, and the rate of loss has been calculated by dividing it by time [14]. A long time is required for this
method to yield a result, and it is less accurate.
This project proposes using a piezoelectric sensor, flowrate sensor, and pressure sensor attached to a
steel pipe to detect pipeline leaks. Any leakage detected will be sensed by the sensor, and data automatically
been sent to the cloud (Google Sheets). Then, artificial neural networks (ANNs) has been used to analyze the
data to determine the degree of leakage in the pipe.
A pipe leak occurs when liquids and gases escape from the pipeline through a leak or crack. A
relationship between leak outflows and flow conditions of water distribution systems must be defined to
understand pipe leakage conditions. The relationship between these two variables is crucial in water
distribution systems. The leak outflow, 𝑄𝐿 , depends mainly on the effective leak area 𝐶𝐿 𝐴𝐿 - defined as the
product of the discharge coefficient 𝐶𝐿 and of the leak area 𝐴𝐿 - and on the total head inside the pipe, H, or on
the piezometric head, h. Other quantities can also be considered, as pipe thickness, discharge conditions
(in air/submerged), ratio 𝑄𝐿 /𝑄𝑢 (with 𝑄𝑢 being the discharge upstream the leak), and, for large leaks, leak
shape [15], [16]. In steady-state conditions, the general equation

𝑄𝐿 = 𝑎𝐻𝑏 (1)

is often used [17], that includes the Torricelli’s equation

𝑄𝐿 = 𝐶𝐿 𝐴𝐿 √2𝑔𝐻 (2)

when a= 𝐶𝐿 𝐴𝐿 (2𝑔)1/2 and b=1/2. The (1) is used both at a global/district area scale, with H being a “mean
pressure” over the district and 𝑄𝐿 is the flow entering the district and at a local scale, considering a single
leak. In both cases, on a local as well as on a global scale, the variation of 𝐶𝐿 𝐴𝐿 with H can be used to explain
the increase of the b exponent with respect to Torricelli’s formula [18].
An artificial neural network (ANN) is a simulation model that simulates the way of the human brain
analyses, and processes information. With ANN, problems that are impossible or difficult to solve by human
or statistical standards are resolved. As a result of self-learning capabilities, this computing system is able to
produce better data analysis. ANNs consist of hundreds or thousands of artificial neurons, called processing
units, interconnected by nodes. A processing unit consists of an input unit and an output unit. Input units
receive information in a variety of forms and structures based on internal weightings, and neural networks are
learning about information to produce an output.
ANNs with feed-forward connections have connections between processing units that do not form a
cycle. The input layer, hidden layer, and the output layer of this ANN are all made up of layers. It is the first
and most straightforward type of ANN and be implemented in this proposed system.

2. RESEARCH METHOD
This project aims to develop a pipeline leak detection system that operates in real-time, using the
ANN [19]–[23] and internet of things (IoT) [24]–[26]. Wireless communication is possible with this system.
A cloud server hosts the outputs data of the system, which is analyzed by ANN. As a result of the cost and
instrumentation limitations, vibration sensors module (SW 420), flowrate sensors (YF-201), and water
pressure sensors (SKU SEN0257) have been used to sense vibration, flowrate, and pressure from the
pipeline.

2.1. Methods
In this project, the vibration sensor, flow rate sensor, and pressure sensor has been used to detect
water leaks. As a result, the sensor does not obstruct water flow but simply senses the vibration, flowrate, and
pressure and collects the data. Microcontrollers are used in this project to read data from multiple sensors and
monitor pressure, vibration, and flowrate. Data has been collected and uploaded to the cloud by the system. A
neural network from MATLAB software has been used to analyze the stored data. Then, a minimalist
application is developed based on ANN analysis results to detect leaks. The flowchart in Figure 1 provides an
overview of the overall process.

Int J Artif Intell, Vol. 11, No. 3, September 2022: 977-985

Int J Artif Intell ISSN: 2252-8938  979

Figure 1. The flowchart for overall process flow

3. RESULTS AND DISCUSSION

3.1. Flowrate
According to Figure 2, two types of water flowrate data were taken. There were the flowrate data for
the pipeline system with no leakage and with a leakage event. The unit of measurement for the above data
distribution is liters per minute (L/min). The flowrate data for a pipeline system with no leakage event is
higher than the flowrate data for a pipeline system with a leakage event. Due to no leaks in the pipeline,
water flows in one way without being disturbed by changes in flow velocity (V). The water would flow
outside the pipe if the leak occurred in the pipeline. This may affect the flow velocity of water when such an
event occurs. When a leak has occurred, the flow of water becomes slower. Based on Figure 3, flowrate (Q)
is defined to be the volume (v) of fluid passing by some location through an area during a period of time (t).
Based on (3), the flowrate value (Q) decreased if the velocity of water decreases.
𝑣
𝑄= (3)
𝑡

3.2. Vibration
Figure 4 gives a comparison of vibrations based on two different data samples. Vibration data from
pipeline systems that had a leakage and those without a leakage show significant differences. Vibration data
for leakage events is very high compared to vibration data without leakage events. The pipe produced a force
Pipe leakage detection system with artificial neural network (Muhammad Iqmmal Rezzwan Radzman)
980  ISSN: 2252-8938

that resulted in an unstable flow of water outside the pipe that caused this situation to occur. Despite the
absence of leakage on this pipeline system, vibrations do occur. However, they are deficient in comparison
with the vibration reading on the pipeline system with an event.

Figure 2. Flowrate result comparison

Figure 3. Flow rate and its relation to velocity

Figure 4. Vibration result comparison

This project finds vibration to be a particularly sensitive parameter because of many external
disturbances that can prevent the data from being read properly from the vibration sensor, for example, the
vibration from the water pump, or the presence of unwanted movement close to the pipeline system. Figure 5
shows the precautions taken while working on this project to obtain accurate data and reduce an external
disturbance.

Int J Artif Intell, Vol. 11, No. 3, September 2022: 977-985

Int J Artif Intell ISSN: 2252-8938  981

Figure 5. The frame that supports the pipeline system

3.3. Pressure
Figure 6 shows the different results of pressure reading data for pipeline systems with leakage and
no leakage. Based on the results, the pressure data reading from the pipeline system shown in Figure 5, with a
leakage event is lower than pressure data for pipeline systems with no leakage event. It is because the
pressure in the pipeline system is decreased due to the existence of the leakage.

Figure 6. Pressure result comparison

3.4. Liquid output

Figure 7 shows the results of the liquid output of the pipeline system for leakage event and no
leakage event. From the results of both of the liquid output, the result is increased directly proportional over
time. But there is a noticeable difference in term of the gradient of the results. The gradient liquid output
results for no leakage event in the pipeline system is steeper than results for leakage event in the pipeline
system. This is because of the difference in the volume of water flow through the pipeline. When the leakage
has occurred, water flows outside the pipe and caused the loss of volume of water in the pipeline.

3.5. Result of artificial neural network (ANN)

In order to develop this ANN, it needs many data to develop a more stable and accurate ANN. In
this project, the amount of data used to develop ANN is more than 3000 data for both types of data leakage
and no leakage event. This ANN consists of a single layer and 10 nodes. Figure 8 to 11 show the result of
ANN training, validation, testing and correlation coefficient R2 for this project respectively.

Pipe leakage detection system with artificial neural network (Muhammad Iqmmal Rezzwan Radzman)
982  ISSN: 2252-8938

Figure 7. Liquid output result comparison

Figure 8. Results of ANN training Figure 9. Results of ANN validation

Figure 10. Results of ANN testing Figure 11. Results for output vs target

3.6. Result of application development

An application is developed to the interface for the user to key in the sensor reading. This
application has been determined the existence of leakage events based on the data given by the user. This

Int J Artif Intell, Vol. 11, No. 3, September 2022: 977-985

Int J Artif Intell ISSN: 2252-8938  983

application interface is developed by using application designer on MATLAB Software, and the functionality
of the application is determined based on ANN training results. The application is extracted from the
MATLAB software and is a standalone application in extension format (exe). Figures 12 and 13, show the
result “NO LEAKAGE” and “LEAKAGE ALERT!!!” when the random untrained data for no leakage event
and leakage event on the pipeline system is key in by the user to the application.

Figure 12. Application result for no leakage event Figure 13. Application result for leakage event data
data

4. CONCLUSION
In conclusion, this project is developed successfully. With an algorithmically programmed
approach, it can determine leakage on pipelines based on real-time data. Additionally, the data was uploaded
to the cloud database, which can be used as a reference or record in the future. In addition, the pipe leakage
detection system based on ANN application has been successfully developed and can detect the leakage
event with real-time data from the sensor. This project also includes an application representing the interface
of the system. As well as being effective, easy to use, and compatible with a wide range of devices, this
application also works properly.

ACKNOWLEDGEMENTS
Communication of the research is made possible through monetary assistance by Universiti Tun
Hussein Onn Malaysia, and this paper was partially supported by Faculty of Engineering, Yamaguchi
University, Japan.

REFERENCES
[1] X.-J. Wang, M. F. Lambert, A. R. Simpson, and J. P. Vítkovský, “Leak detection in pipeline systems and networks: A Review,” in
Conference on Hydraulics in Civil Engineering, 2001, pp. 1–10.
[2] I. A. Tijani, S. Abdelmageed, A. Fares, K. H. Fan, Z. Y. Hu, and T. Zayed, “Improving the leak detection efficiency in water
distribution networks using noise loggers,” Sci. Total Environ., vol. 821, p. 153530, May 2022, doi: 10.1016/j.scitotenv.2022.153530.
[3] B. M. S. Arifin, Z. Li, S. L. Shah, G. A. Meyer, and A. Colin, “A novel data-driven leak detection and localization algorithm using the
Kantorovich distance,” Comput. Chem. Eng., vol. 108, pp. 300–313, Jan. 2018, doi: 10.1016/j.compchemeng.2017.09.022.
[4] M. Liu, J. Yang, S. Li, Z. Zhou, E. Fan, and W. Zheng, “Robust GMM least square twin K-class support vector machine for urban
water pipe leak recognition,” Expert Syst. Appl., vol. 195, p. 116525, Jun. 2022, doi: 10.1016/j.eswa.2022.116525.
[5] M. J. Brennan, Y. Gao, P. C. Ayala, F. C. L. Almeida, P. F. Joseph, and A. T. Paschoalini, “Amplitude distortion of measured leak
noise signals caused by instrumentation: Effects on leak detection in water pipes using the cross-correlation method,” J. Sound Vib.,
vol. 461, p. 114905, Nov. 2019, doi: 10.1016/j.jsv.2019.114905.
[6] F. Piltan and J.-M. Kim, “Leak detection and localization for pipelines using multivariable fuzzy learning backstepping,” J. Intell.
Fuzzy Syst., vol. 42, no. 1, pp. 377–388, Dec. 2021, doi: 10.3233/JIFS-219197.
[7] S. S. Sufian, N. S. Romali, R. A. Rahman, and M. A. Seman, “Current practice in rehabilitating old pipes for water distribution
network in Malaysia,” IOP Conf. Ser. Earth Environ. Sci., vol. 641, no. 1, p. 12011, Feb. 2021, doi: 10.1088/1755-
1315/641/1/012011.

Pipe leakage detection system with artificial neural network (Muhammad Iqmmal Rezzwan Radzman)
984  ISSN: 2252-8938

[8] Y. Gao, Y. Liu, Y. Ma, X. Cheng, and J. Yang, “Application of the differentiation process into the correlation-based leak detection in
urban pipeline networks,” Mech. Syst. Signal Process., vol. 112, pp. 251–264, Nov. 2018, doi: 10.1016/j.ymssp.2018.04.036.
[9] X. Hu, Y. Han, B. Yu, Z. Geng, and J. Fan, “Novel leakage detection and water loss management of urban water supply network
using multiscale neural networks,” J. Clean. Prod., vol. 278, p. 123611, Jan. 2021, doi: 10.1016/j.jclepro.2020.123611.
[10] B. C. Yalçın, C. Demir, M. Gökçe, and A. Koyun, “Water leakage detection for complex pipe systems using hybrid learning
algorithm based on ANFIS method,” J. Comput. Inf. Sci. Eng., vol. 18, no. 4, Dec. 2018, doi: 10.1115/1.4040130.
[11] S. K. Vandrangi, T. A. Lemma, S. M. Mujtaba, and O. T. N., “Developments of leak detection, diagnostics, and prediction algorithms
in multiphase flows,” Chem. Eng. Sci., vol. 248, p. 117205, Feb. 2022, doi: 10.1016/j.ces.2021.117205.
[12] T. Kawata, Y. Nakano, T. Matsumoto, A. Mito, F. Pittard, and H. Noda, “Challenge in high-speed TBM excavation of long-distance
water transfer tunnel, Pahang-Selangor raw water transfer tunnel, Malaysia,” 2014.
[13] A. A. Lyapin and Y. Y. Shatilov, “Vibration-based damage detection of steel pipeline systems,” in Non-destructive Testing and
Repair of Pipelines, 2018, pp. 63–72.
[14] R. Beieler and A. Roshak, “Useful tips and tools for design of ductile iron and PVC pipelines,” in Pipelines 2014, Jul. 2014,
pp. 594–604, doi: 10.1061/9780784413692.055.
[15] A. Keramat, B. Karney, M. S. Ghidaoui, and X. Wang, “Transient-based leak detection in the frequency domain considering fluid-
structure interaction and viscoelasticity,” Mech. Syst. Signal Process., vol. 153, p. 107500, May 2021,
doi: 10.1016/j.ymssp.2020.107500.
[16] A. M. Cassa, J. E. van Zyl, and R. F. Laubscher, “A numerical investigation into the effect of pressure on holes and cracks in water
supply pipes,” Urban Water J., vol. 7, no. 2, pp. 109–120, Apr. 2010, doi: 10.1080/15730620903447613.
[17] M. Ferrante, B. Brunone, and S. Meniconi, “Wavelets for the analysis of transient pressure signals for leak detection,” J. Hydraul.
Eng., vol. 133, no. 11, pp. 1274–1282, Nov. 2007, doi: 10.1061/(ASCE)0733-9429(2007)133:11(1274).
[18] J. E. van Zyl and C. R. I. Clayton, “The effect of pressure on leakage in water distribution systems,” Proc. Inst. Civ. Eng. Manag.,
vol. 160, no. 2, pp. 109–114, Jun. 2007, doi: 10.1680/wama.2007.160.2.109.
[19] C. Ai, B. Wang, and H. Zhao, “Detection and fault diagnosis for acoustic vibration of pipes buried in soil,” in 2006 6th World
Congress on Intelligent Control and Automation, 2006, pp. 5756–5759, doi: 10.1109/WCICA.2006.1714178.
[20] Q. Xu and W. Kong, “Research on forecast model based on BP neural network algorithm,” J. Phys. Conf. Ser., vol. 1982, no. 1,
p. 12065, Jul. 2021, doi: 10.1088/1742-6596/1982/1/012065.
[21] R. B. Santos, M. Rupp, S. J. Bonzi, and A. M. F. Filetia, “Comparison between multilayer feedforward neural networks and a radial
basis function network to detect and locate leaks in pipelines transporting gas,” Chem. Eng. Trans., vol. 32, pp. 1375–1380, 2013.
[22] E. J. Pérez-Pérez, F. R. López-Estrada, G. Valencia-Palomo, L. Torres, V. Puig, and J. D. Mina-Antonio, “Leak diagnosis in pipelines
using a combined artificial neural network approach,” Control Eng. Pract., vol. 107, p. 104677, Feb. 2021,
doi: 10.1016/j.conengprac.2020.104677.
[23] T. Dawood, E. Elwakil, H. M. Novoa, and J. F. Gárate Delgado, “Toward urban sustainability and clean potable water: Prediction of
water quality via artificial neural networks,” J. Clean. Prod., vol. 291, p. 125266, Apr. 2021, doi: 10.1016/j.jclepro.2020.125266.
[24] B. Zhou, V. Lau, and X. Wang, “Machine-learning-based leakage-event identification for smart water supply systems,” IEEE Internet
Things J., vol. 7, no. 3, pp. 2277–2292, Mar. 2020, doi: 10.1109/JIOT.2019.2958920.
[25] Y. Kim, S. J. Lee, T. Park, G. Lee, J. C. Suh, and J. M. Lee, “Robust leak detection and its localization using interval estimation for
water distribution network,” Comput. Chem. Eng., vol. 92, pp. 1–17, Sep. 2016, doi: 10.1016/j.compchemeng.2016.04.027.
[26] S. T. N. Nguyen, J. Gong, M. F. Lambert, A. C. Zecchin, and A. R. Simpson, “Least squares deconvolution for leak detection with a
pseudo random binary sequence excitation,” Mech. Syst. Signal Process., vol. 99, pp. 846–858, Jan. 2018,
doi: 10.1016/j.ymssp.2017.07.003.

BIOGRAPHIES OF AUTHORS

Muhammad Iqmmal Rezzwan Radzman graduate from Johor Matriculation

College for pre-University Tertiary Education (2017), and Bachelor of Electronic Engineering at
University Tun Hussein Onn Malaysia in 2021. Currently he is an engineer and independent
reseacher. His research interests include automation, electronic, SMT, and embedded system. He
can be contacted at email: [email protected].

Abd Kadir Mahamad received his Bachelor of Science in Electrical Engineering

(2002) and Master of Electrical Engineering (2005) from University Tun Hussein Onn Malaysia
before pursuing Doctor of Philosophy (Computer Science and Electrical Engineering) at
Kumamoto University, Japan (2010). He currently an Associate Professor at Faculty of Electrical
and Electronic Engineering UTHM and registered as Professional Engineer. During the period of
May 2015 through May 2016, he was doing industrial attachment at Melaka ICT Holdings Sdn
Bhd, as Executive Assistant Manager. He was involved in the Smart City project in Melaka. He
currently leads a research team in Video Analytic and internet of things (IoT). His research
interests include Deep Learning, Smart City, Intelligent System applications and embedded
system. He can be contacted at email: [email protected].

Int J Artif Intell, Vol. 11, No. 3, September 2022: 977-985

Int J Artif Intell ISSN: 2252-8938  985

Siti Zarina Mohd Muji is Associate Professor at Department of Electronic

Engineering in Computer field at Faculty of Electronic and Electrical Engineering, Universiti
Tun Hussein Onn Malaysia (UTHM). Her research interest is in Embedded System and
Application, Tomography, and Sensor and Application. She currently being a head of several
grants includes Fundamental Research Grant Scheme (FRGS), Multidisciplinary Research
(MDR) and MTUN Commercialization (Internal Grant). For FRGS grant, this is a collaboration
with oil and gas industry that related to pipe corrosion. For MDR, this research focus on
detection of pipe leakage at UTHM and for MTUN Commercialization is a grant to
commercialize Jaundice Meter which is a device to detect the jaundice among babies. She also
involves in publishing articles in journal (50), book chapter (10), technical papers in conferences
(>30) and peer reviewed journal (>20) (IEEE sensor, Sensor and Actuator B Chemical and many
more). She also won several medals in research and innovation showcases where a Jaundice
Meter project won a gold medal in Pecipta 2017. She can be contacted at email:
[email protected].

Sharifah Saon is currently a senior lecturer in the Faculty of Electrical and

Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Malaysia, and registered
Professional Technologists. She received the Bachelor of Science in Electrical Engineering and
Master of Electrical Engineering from Universiti Teknologi Malaysia, and Kolej Universiti Tun
Hussein Onn Malaysia, Malaysia, in 2001, and 2004, respectively. Her research interest is in the
area of theoretical digital signal processing, visible light communication, and digital and data
communication, including the application to the internet of things (IoT) and big data analysis.
She is a member of IEEE, Institute of Engineering Malaysia (IEM), Board of Engineering
Malaysia (BEM), and Professional Technologist of Malaysia Board of Technologists (MBOT).
She can be contacted at email: [email protected].

Mohd Anuaruddin B. Ahmadon graduated from Kumamoto National College of

Technology, Japan, in 2012. He received his B. Eng. (2014), M. Eng. (2015) and Dr. Eng. (2017)
from Yamaguchi University, Japan. He is currently an Assistant Professor at Graduate School of
Sciences and Technology for Innovation, Yamaguchi University, Japan. He was awarded IEEE
Consumer Electronics Society East-Japan Young Scientist Paper Award in 2016. His research
interests include formal methodology in software and service engineering and its application to
cyber-security and Internet of Things. He is a member of IEEE and Consumer Technology
Society. He can be contacted at email: [email protected].

Shingo Yamaguchi is currently a (full) professor in the Graduate School of

Sciences and Technology for Innovation, Yamaguchi University, Japan. He received the B.E.,
M.E. and D.E. degrees from Yamaguchi University, Japan, in 1992, 1994 and 2002, respectively.
He was an Assistant Professor in the Faculty of Engineering, Yamaguchi University, from 1997
to 2007. He was also a Visiting Scholar in the Department of Computer Science at University of
Illinois at Chicago, United States, in 2007. He was an Associate Professor in the Graduate
School of Sciences and Technology for Innovation, Yamaguchi University, from 2007 to 2017.
His research interest is in the area of theoretical computer science and software engineering,
including their application to business process management, IoT, bigdata analysis, AI, and cyber
security. He is also a Senior Member of IEEE, Board of Governors of IEEE Consumer
Electronics Society, Young Professionals Chair of IEEE Consumer Electronics Society, and a
member of International Coordination Committee of ITC-CSCC. In academic societies other
than IEEE and IEICE, he plays many important roles, which is an Editorial Board Member of
International Journal of Internet of Things and Cyber-Assurance. He can be contacted at email:
[email protected].

Muhammad Ikhsan Setiawan received his Bachelor of Civil Engineering (2002)

from Universitas Merdeka, Malang, Indonesia, and Master of Civil Engineering (2005) from
Universitas Indonesia before pursuing Doctor of Philosophy (Civil Engineering) at Universitas
Tarumanagara, Indonesia (2010). He currently an Assistant Professor at Faculty of Civil
Engineering, Narotama University, Indonesia and registered as Engineer Expert Certified. He
currently leads a research team in Sustainable and Digital in Transportation, Tourism and
Regional Economic, grant from Ministry of Education, Indonesia. His research interests include
Smart City and Sustainability. He is also a Chairman of WORLDCONFERENCE.ID, IPEST
commerce, SONGSONG ridt, member of IEEE, editors, and reviewers some Journal indexed in
SCOPUS, DOAJ, CROSSREF and GOOGLE, also until now as Vice Rector of Narotama
University, Indonesia. He can be contacted at email: [email protected].

Pipe leakage detection system with artificial neural network (Muhammad Iqmmal Rezzwan Radzman)