Content uploaded by Collins Udanor
Author content
All content in this area was uploaded by Collins Udanor on Jun 30, 2022
Content may be subject to copyright.
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
productivity as the portability of the system will
encourage homestead, urban, and tenant aquaculture.
Despite these potential gains, Africa is yet to reasonably
exploit the potentials of the technology. The success of
aquaponics practice lies mainly in the ability to manage
water quality parameters. Water quality impacts the fish
growth rate, feed consumption, and their general
wellbeing [2]. The following parameters are important in
the health of the fish grown either conventionally or in an
aquaponics system; dissolved oxygen, un-ionized
smelling salts, carbon dioxide, nitrite, nitrate focus, pH,
turbidity, and alkalinity levels. Local conventional fish
farmers experience losses in their fishes or stunted growth
because of their inability to monitor, measure, or control
these parameters in their ponds. In a 1998 survey
conducted in Pennsylvania among 557 fish farmers, it was
discovered that
IO
percent of the problems of the farms
were related to water quality [3]. This led to deaths among
their fishes.
It
was also noted that these farmers never
tested the water quality until a problem has occurred. Most
of the water quality problems in a pond are contributed by
nature and humans' influence.
This paper reports the result of a pilot aspect of a funded
project under the Lacuna Fund for Agricultural Datasets
for AI award, 2020 (https://lacunafund.org/awards/). The
project is aimed at building a remotely monitored and
controlled Internet of Things (IoT) fish pond water quality
management system for the generation oflabelled datasets
from both the conventional ponds and the aquaponics
pond systems. These datasets will enable machine
learning researchers to build models for predicting fish
yield in the aquaponics production system in terms of
weight gain, water quality parameters, and feed
consumption.
Though, the main project is aimed at using seven sensors
(temperature, turbidity, pH, ammonia, nitrate, nitrite, and
dissolved oxygen) for collecting datasets of water quality
parameters in fish ponds, the pilot work demonstrates the
control, big data and business analytics, information
sharing, and collaboration.
In
their work, [7] explored loT, its architecture, and its
relationship with wireless sensor networks (WSN). Also,
they explained different applications of loT including
Smart society (e.g. Smart Home, Smart City, Smart
Traffic, Smart Parking, and Smart waste management).
The Healthcare application of IoT includes health
tracking, Pharmaceutical products, Food sustainability,
and Supply-chains. Finally, they proposed an idea ofusing
IoT in the Indian agriculture domain.
In
[8] the different applications that adopted smart
technologies were covered. Their paper also gives an
overview of the sensors and their standards. Given the
numerous and diverse applications ofloT in everyday life.
Porkodi & Bhuvaneswari [8] broadly covered society,
industries, and the environment. They identified 6 or more
application domains such as smart energy, smart health,
smart buildings, smart transport, smart living, and smart
cities. According to their survey, from the IoT project ran
in 2010, 65 IoT application scenarios were identified and
grouped into 14 domains, which are Transportation, Smart
Home, Smart City, Lifestyle, Retail, Agriculture, Smart
Factory, Supply chain, Emergency, Health care, User
interaction, Culture and Tourism, Environment and
Energy.
Meanwhile, Khan et. al.[5] addressed the existmg
development trends, the generic architecture of loT, its
distinguishing features, and possible future applications.
Their work forecasted the key challenges associated with
the development ofloT. They also identify that the IoT is
getting increasing popularity for academia, the industry as
well as government, and has the potential to bring
significant personal, professional, and economic benefits.
They propose some future applications of IoT such as;
Prediction of natural disasters, Industry applications,
Water Scarcity monitoring, Design of smart homes,
Agriculture application which involves a network of
different sensors which can sense data, perform data
processing and inform the farmer through communication
infrastructure.
It
will also help agronomists to have a
better understanding of the plant growth models and to
have efficient farming practices by knowing land
conditions and climate variability. This will significantly
use of two sensors, namely submersible
sensor and turbidity sensor.
temperature
The remainder of the paper is organized
as follows.
Section 2.0 presents a review of related literature,
followed by, materials and methods in Section 3.0. In
Section 4.0, we present the result of the pilot experiment,
and finally, Section 5.0 is the conclusion and future work.
increase
agricultural
productivity
by
avoiding
inappropriate farming conditions. Other applications are
in intelligent transport system design used to avoid traffic
jams, report traffic incidents, smart beaconing, and
minimizing arrival delay.
Burget and Pachner [9], developed a 'fish farm
automation' that consists of two parts. The first part
monitors the water level, Temperature, PH level, and
Oxygen with SMS notification to the farmer. The second
part is a fish and feed type predictive optimization model
for feeding the fishes and suggesting optimal action or step
to take to give high profit. Unfortunately, the farmer has
to be near the pond to perform the action recommended in
terms of controlling the fish environment. Cahyono, et.
al.[10] automated the circulation of water within the fish
pond by automatically pumping water into the pond using
pH and Water levels as parameters. They reduced the
participation of the farmer but falls short in water
conservation. Nocheski and Naumoski [11] incorporated a
II.
REVIEW OF RELATED LITERATURE
Internet of Things (IoT) brings about some modern
applications in various fields of life. In some cases, it can
be used for environment and climate monitoring, action
and event triggering.
It
could also play a major role in
decision making and by automating our daily tasks, loT
can enormously improve quality of life [4]. "The IoT also
embeds some intelligence in Internet-connected objects to
communicate, exchange information, take decisions,
invoke actions and provide amazing services" [5].
Motion, Position, Environment, Mass measurement, and
Biosensors are some of the IoT sensors identified by [4].
Their work focuses on the smart city, Industrial, and health
care domain. While, [6] identifies three IoT categories for
enterprise applications, these include; monitoring and
2
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
module in their model that sends the status of the fish pond
information to the farm manager to intervene from a
remote area. This system does not incorporate Oxygen,
turbidity, pH control module which is a serious gap that
the proposed system intends to close in addition to
incorporating water conservation which is a major
problem in most parts of Nigeria. Chinni et. al. [12], in
viewed with its meta-data details and may be downloaded
for machine learning analytics to produce a model for
predicting the condition of the fishes, rate of growth, and
yield in terms of weight of the fishes over different time
intervals. This analytic model, which is a Python program
will be able to show various types of visualizations of the
parameters of the water quality, such as temperature, pH
level, turbidity, dissolved oxygen, etc. One other
component of the pond control system is an IP camera that
provides security in real-time on the activities around the
pond.
their
IoT-
based
fish
health
monitoring
system,
implemented water quality factors like pH, water level,
and a buzzer sound to signal the fish farmer who may not
be near the farm to intervene whenever the various water
parameters go out of range. Authors in [13], provided a
heating mechanism when the water temperature is very
low (Coldwater) and a fanning mechanism in case the
temperature goes high. The system also takes into
consideration water colour for regulation. When turbidity
is high, a TDS filter (Total Dissolved solids/substances),
filters the pond's water. This system fails to consider water
colour as it is a factor of turbidity.
B. PHYSICO -CHEMICAL PARAMETERS
The water physio-chemical parameters tested in the pilot
phase are temperature and turbidity.
1)
Temperature:
To ensure optimal productivity in
ponds, the temperature has to be regulated to optimal
levels. The temperature remains a key factor in ponds
as all the biological activities both within the farmed
fish environment and its body systems are
temperature dependent. Temperature greatly affects
water quality as it can influence both the physical and
the chemical properties of water. Temperature
influences the dissolved oxygen levels, pH, density,
ammonia levels, and the rate of photosynthetic
activity of an aquatic environment for a typical fish
pond aqua environment, the higher the temperature
the higher the biological activities of the fish and the
algal productivity of the pond and hence the need to
maintain the temperature at optimal levels for
maximum fish yields. The acceptable temperature for
aquaculture species ranges between 25.5°C - 30.5°C.
Turbidity: Turbidity measures the clarity or
otherwise of a water sample. It is an important water
quality parameter which determines the cloudiness of
the water. The turbidity unit is measured in NTU
"Nephelometric Turbidity Units". The larger the
turbidity is, the cloudy, the sample is. The larger the
turbidity is, the smaller the output voltage will be. The
voltage ranges from O to 4.5 volts. The turbidity
sensor works by using infrared (IR) LED for the light
To the best of our knowledge, there is no indigenous
aquaponics fish pond monitory system that can remotely
monitor and control IoT-enabled fish pond water quality
for the generation of labelled datasets from both the
conventional ponds and the aquaponics
Hence, this research becomes paramount.
pond
systems.
III. MATERIALS AND METHODS
This section describes the entire system, the
Physico-
chemical parameters which are key factors in sustainable
aquaculture production. These parameters include
temperature, pH, dissolved oxygen, ammonia, turbidity,
nitrate, and nitrite among others. The section also
describes the pilot experimentation.
2)
A. POND CONTROLLER SYSTEM DESIGN
The IoT system that controls the pond is made up of an
Arduino Mega 2560 microcontroller interfaced with
various water quality sensors. The block diagram is shown
in fig. 1. The system is made up of a pond controller which
consists of an Arduino Mega 2560 microcontroller
interfaced to several submersible sensors such as, pH
level, temperature, ammonia, dissolved oxygen, nitrate,
and nitrite sensors, as well as a turbidity sensor for
monitoring and controlling the pond water quality. When
the oxygen level is low the microcontroller activates the
aerator pump through a relay automatically, to generate
and recirculate oxygen in the pond ensuring that the water
remains fresh until the water is due for a change. Low
oxygen can happen as a result of high temperature, not
necessarily that the water quality is bad. The turbidity
sensor, on the other hand, signals the farmer through an
SMS alert when the water quality has become bad for a
water change.
Another component of the system is a GSM-edge-cloud
orchestration, which receives real-time data from the pond
controller sensors. The GSM/GPRS module forms an edge
computing gateway through which data is relayed to the
cloud infrastructure. The GSM module sends SMS
messages to the user through the edge gateway, which can
be stored locally iflnternet access is not available. On the
availability of Internet connectivity, the data is uploaded
to a cloud repository. From the cloud, the data can be
source and infrared phototransistor to
much of the amount oflight that is
detect
how
3
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
16x2
LCD
Display
PH
Power Supply
Nitrate
Sensor
Nitrite
Sensor
Arduino
Mega 2560
Microcontroller
Cloud
data
I
repo
Ammonia
Turbidity
Dissolved C02Sensor
Edge
,,
Temperature
"
FIGURE I. Water pond controller
system
Where, the coefficients ofX1, X2, ... , Xn, i.e. B1, B2,..., Bn
are the data values received from the various sensors
represented by X for the training machine learning
models. Y is the weight of the fish which is a dependent
variable and determined by the values of the independent
variables, i.e, sensor inputs. Several supervised learning
algorithms like support vector machine (SVM), Decision
trees, Linear regression, Neural networks, K-nearest
neighbours, etc., may be employed during the training
phase, and confusion matrix or any other metric may be
used to evaluate the best model, based on their accuracy,
among other parameters.
not blocked by the turbid water. Turbidity sensors
measure reflected (IR) light at 90 degrees to the
source. The infrared phototransistor [14] will have a
change in resistance itself and the change of voltage
sensor will be obtained. Turbidity measurement is
important in fish pond as it reveals the amount of
impurities in the water mostly due to unconsumed
feeds and wastes, which can become toxic to the
fishes.
C. DATA STRUCTURE AND FORMAT
Table 2 is the structure ofmy SQLite data table stored
in the cloud from the pond controller. The data can be
stored using XML or JSON format but can be
retrieved as comma-separated values (CSV) or in the
raw format depending on usage.
The sensor data from Table 1 can be used to build a
model using a simple linear model like the linear
regression function shown in (1), for example:
TABLE I
STRUCTURE OF THE SENSOR DATASET
D. IoT SYSTEM DEVELOPMENT
The development of the loT system was done using an
Arduino mega 2560 and ESP32 microcontrollers, in tum.
Both microcontroller units (MCUs) are capable of
independently working with the sensors. However, the
ESP 32, a 32bit MCU is also able to provide wireless
fidelity (Wi-Fi) connectivity to the Internet. Both MCUs
are programmed using the Arduino IDE 1.8.4 and 2.0 Beta
edition, and they both responded well on the IDEs. Both
MCUs support analog and digital inputs. Though, the
Arduino mega has more analog pins than the ESP32. The
ESP 32 is an improved version over the 16-bit ESP 8266.
In addition to other features the ESP32 has support for
Bluetooth version 4.2, 40MHz crystal clock, complies
with Wi-Fi 802.11 b/g/n standards with speeds up to
150Mbps, has 4MB SPI integrated flash memory [15].
SIN
Date/
Temp
Time
PH
Turbidit
y
D02
Ammonia
Nitrate
4
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
E. DESIGNING THE CIRCUIT DIAGRAM
The Pilot Fish Pond Monitoring System was designed
using the following components and Sensors: Arduino
mega 2500, Temperature Sensor, Turbidity Sensor, and
ESP32 Wi-Fi Module.
The power supply feeds the Arduino board with a rectified
voltage of 5v from a PC USB port. Positive terminal of the
supply for each sensor was connected to VCC terminal of
the Arduino board while the negative terminal was
grounded to GND of the Arduino. If the connection for the
supply is done properly the LED in the Arduino board will
start linking.
The Sensors used for the pilot were connected based on
the description below:
FIGURE 3. DFRobot Turbidity Sensor
1. Temperature Sensor:
The
Dallas'
DS18B20
temperature sensor (figure 2) was used. This sensor reads
digital values. DSB18B20 has Unique I-Wire interface
that requires only one port pin for communication.
It
has
reduced component count with Integrated Temperature
sensor and EEPROM.
It
Measures temperatures from -
55°C to+ 125°C (-67°F to +257°F) with a ±0.5°C accuracy
from -10°C to +85°C. The sensor input was connected to
the digital pin 4 of the Arduino
(D,I
3. ESP32 Wi -Fi module: The Wi-Fi has positive,
negative, transmitter and receiver's terminals. The
positive terminal was connected to 3.3v power port of the
Arduino board to pull up the voltage to 5v when both are
to be used together, while the negative was grounded. The
transmitter pin of the Wi-Fi was connected to the receiver
pin of the Arduino while that of the receiver was
connected to the transmitter pin of the Arduino.
F. PROCEDURE
Each sensor was separately connected to the MCU and the
code written in the Arduino IDE was compiled, corrected
and uploaded into the MCU. The output was viewed using
the Arduino IDE's Serial Monitor interface. Each of the
sensor was also calibrated using a calibration code, to
ensure that the instruments work according to standard
specifications.
In the case of the turbidity sensor, a program which
produced the voltage and corresponding sensor values was
written. This is to test and find out if the turbidity voltage
values varied linearly according to standard. The turbidity
sensor was placed in seven (7) different media and we
observed how both the turbidity values and voltages
varied in the different media. The plot is shown in figure
4. The relationship between the turbidity and voltage is
expressed as:
FIGURE 2. Dallas Waterproof DS I 8B20 Temperature Sensor
Voltage
=
sensorvalue
* ( )
2. Turbidity Sensor : The DFRobot analogue turbidity
sensor was used for the experiment (fig. 3). The sensor has
an operating temperature ranging of: 5°C 90 °C, and
storage temperature range: -10°C 90°C. The sensor
connects to the microcontroller through an analogue to
digital converter through this A to D converter.
It
was
fixed in a development board (breadboard) with positive
pin to VCC, negative Pin to the ground and the output pin
connected to analog pin 1 of the Arduino (A,I
1024
Where sensor_value is the reading from the turbidity
sensor as received by the program, 5.0 represents the
maximum voltage supported by the sensor, and 1024 is the
maximum value of turbidity readings. And
4
convert the analog sensor reading (which goes from 0
1023) to a voltage (0 - 5V). The resulting voltage values
are
compared
with
standard
measurements.
The
experiments were performed at room temperature (25°C).
Samples examined include clear water, dark water (zobo
drink),
fish
pond water
(in
use),
fish
pond water
5
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
-
(discarded), mud water (unstirred), mud water (stirred),
and milk. The findings are shown in Table 2 in the results
section. The output is viewed on the Serial monitor at a
baud rate of 9600.
-
In the code turbidity values were graduated in ranges to be
able to classify different turbidity levels in the water. For
instance, turbidity value less than lONTU is classified as
being clear, while values above l 0NTU and less than
50NTU is classified as being cloudy, and values beyond
50NTU is classified as being dirty. These were tested
using clear and clean water, milk, and muddy water,
respectively. Water samples taken from the fish ponds
were also taken and tested, and they were correctly
classified.
-
G. IoT CLOUD MONITORING
The ThingSpeak IoT cloud platform was used to monitor
the loT sensor values in real-time. ThingSpeak offers free
and commercial hosting of loT sensor readings and
visualizations for both private and public users. A channel
was created in ThingSpeak to enable us to create the
storage variables where the sensor values will be stored on
the cloud. To have access to ThingSpeak server, one needs
to generate API keys and channel
ID.
These will be added
to the sketch in the Arduino code. Figure 5 shows a sample
output of both the temperature and turbidity readings.
--
IV RESULTS
The temperature readings were consistent when tested in
different media, such as room, warm water, cold water,
pond water, human body, etc. The plot on the left in figure
4
showed the instant drop in temperature as the sensor was
moved from a warm medium to a colder one. On the other
hand, the turbidity sensor readings shown on the right
hand side of figure
4
remains consistent for a particular
medium at 100NTU.
TABLE3
STANDARD VOLTAGE AND TURBIDITY VALUES (EC, 2020).
-
-
FIGURE 4. ThingSpeak Cloud analysis of the sensors' readings.
Table 2 is the output of equation 2 for different media. The
voltage ranges for the different media are shown in the
table. The purpose of this table is to ensure that the
turbidity sensor is properly calibrated to conform to the
standards given in Table 3.
Figure 5 shows how the voltage varied with turbidity
inversely, which we find consistent with literature like in
•.
The larger the turbidity is, the smaller the output
voltage will be. This shows from both tables 2 and 3 that
the clearer the media, the higher the voltage. According to
[16], "higher concentrations of sediment and turbidity of
the water made the sensor output voltage decrease". The
TABLE2
VOLTAGE VALUES FOR DIFFERENT MEDIA
6
Media
Voltage (V)
Turbidity
(NTU)
-
Clear water
4.1
-
0.5
-
-
Cloudy
-
■
•
MEDIUM
VOLTAGE
Clear water
4.14-4.24V
-
Coloured water(Zobo drink)
3.32- 3.52V
-
Fish pond water (in use)
1.61- 1.74V
-
Fish pond water (discarded)
2.40- 2.74V
-
Mud water (unstirred)
2.87-2.97V
-
Mud water (stirred)
0.09-l.47V
0.00-0.00
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
(6)
Lee, I., & Lee, K., “The Internet of Things (IoT):
Applications, investments, and challenges for enterprises”.
Business Horizons, 58(4), 431-440, 2015.
(7)
Soumyalatha, S. G. H., “Study of IoT: understanding IoT
architecture, applications, issues and challenges”. In 1st
International Conference on Innovations in Computing &
Net-working (ICICN16), CSE, RRCE. International
Journal of Advanced Networking & Applications (No.
478), 2016.
(8) Porkodi, R., & Bhuvaneswari, V., “The internet of things
(I oT) a ppli cati ons and comm unic a tio n en abling
technology standards: An overview”. In 2014 International
conference on intelligent computing applications (pp. 324-
329). IEEE, 2014.
(9) P.
Burget and D. Pachner, “Fish farm automation”.
ELSEVIER IFAC. Pp 137-142, 2005. Available:
https://www.sciencedirect.com [accessed: October 4,
2019]
(10)
D. Cahyono, V. Veronika Nugraheni and S. Lestari,
“Automation of fish pond water circulation by using
A r d u i n o U n o - b a s e d c o n t r o l s y s t e m ” .
Available:https://www.blog.unitomo.ac.ld/veronica/wp-
content/uploads/sites/7/2017/12/automation-of-fish-pond-
water-circulation-by-using-Arduino-uno-based-control-
system.pdf [accessed: November 28, 2019]
(11)
S.Nocheski, and A. Naumoski, “Water monitoring IOT
system for fish farming ponds”. International Science
Journal. Web ISSN 2534-997X, Print ISSN 2534-8582,
2 0 1 8 .
A v a i l a b l e :
https://www.stumejournals.com/journals/i4/2018/2/77.ful
l.pdf[accessed: November 1, 2019]
(12)
P. Chinni Krishna, M. Ventkateswara Rao and V. Ramesh
Reddy, “An IoT based fish Health monitoring system in
aquaculture farming”. International Journal of innovative
Technology and explo ring En ginee ring (IJ ITEE).
ISSN:2275-3075, vol. 8, issue 7, 2019. Available:
h t t p s : / / w w w . i j i t e e . o r g / w p -
content/uploads/papers/v8i7/G0758719.pdf [accessed:
November 4, 2019]
(13)
Hakim, L. W., Hasanah, L., Mulyanti, B., and Aminudin,
A., “Characterization of turbidity water sensor SEN0189
on the changes of total suspended solids in the water”. J.
Phys.: Conf. Ser. 1280 022064, 2019.
(14)
Expressif Systems,
“ESP32 WROOM32
Datasheet”.
REFERENCES
(1) Morrisson, C., Thorbecke, E., Guilmeau, H., & Linskens,
C., “Poverty and malnutrition in sub-Saharan Africa”.
Food Markets and Food Security in West Africa, 8, 2002
(2) H.A. Mohammed and I. Al-Mejibi, “Smart monitoring and
controlling system to enhance fish production with
minimum cost”. Journal of theoretical and applied
information technology. Vol. 98 (10), 2018, ISSN:1992-
8645,
E-ISSN:1817-3195.
pp
2872-2885.
Available:
https://www.jatit.org/volumes/vol96No10/12vol96No10.
pdf [accessed: October 28, 2019]
(3) PenState Extension, “Water Quality Concerns for Ponds”,
A v a i l a b l e
a t :
2015. Available at: https://extension.psu.edu/water-
quality-concerns-for-ponds (Retrieved: 7th March, 2021)
(4)
Rozsa, V., Denisczwicz, M., Dutra, M.L., Ghodous, P., da
Silva, C.F., Moayeri, N., Biennier, F. and Figay, N., “An
Application Domain-Based Taxonomy for IoT Sensors”.
23rd ISPE International Conference on Transdisciplinary
Engineering: Crossing Boundaries, Oct 2016, Curitiba,
Brazil. (pp. 249-258).
(5)
Khan, R., Khan, S. U., Zaheer, R., & Khan, S., “Future
internet: the internet of things architecture, possible
ap plic ati ons and key ch all enge s”. In 2012 10th
international conference on frontiers of information
technology (pp. 257-260). IEEE.
https://www.espressif.com/sites/default/files/documentati
on/esp32-wroom-32_datasheet_en.pdf
(15)
Hasanah, L., Hakim, W. L., Aminudin, A., Sahari, S. K., &
Mulyanti, B., “A design and performance analysis of a
telemetry system for remote monitoring of turbidity of
water during the covid-19 pandemic.”, Indonesian Journal
of Science and Technology, 5(2), 2020.Available at:
https://doi.org/10.17509/ijost.v5i2.24705
(16)
WEDC Mobile Note 50, “Measuring the turbidity of water
supplies”. Available at:
https://wedc-knowledge.lboro.ac.uk/resources/e/mn/050-
Measuring-the-turbidity-of-water-supplies.pdf. (Accessed
30/03/2021)
7
The Journal of Computer Science and It’s Application
Vol. 28, No. 2. December 2021
Dr. Collins Udanor
is a Senior Lecturer in the Depar
tment of Computer Science, University of Nigeria Nsukka. He holds a Ph.D. in Electronic
Engineering. He has advanced training in the Internet of Things (2019, 2020), Data Science
School (2018), a Certificate of Completion in Introduction to Data Science (IBM, 2019).
Dr. Nelson Ossai has a Ph.D. in Fisheries Biology from the Department of Zoology and
Environmental Biology, University of Nigeria Nsukka, where he currently lectures.
Dr Blessing Ogbuokiri is a lecturer at the Department of Computer Science, University of
Nigeria, Nsukka (UNN). He has over fifteen years of work experience in academia, the software,
and IT industries. He has managed teams and made many group decisions.
Nweke Onyinye Edith is a Lecturer with the Department of Computer Science from the
University of Nigeria, Nsukka. She obtained her Bachelor of Engineering (B.Eng.) in Computer
Engineering from Igbinedion University Okada in 2011 and a M.Sc in Computer Science from
the University of Port-Harcourt in 2016.
Paulinus O. Ugwoke obtained M.Sc. (Computer Science) and M.Sc. (Statistics) degrees both
from the University of Lagos, Nigeria; B.Sc. (Combined Hons, Computer Science & Statistics)
from the University of Nigeria, Nsukka, Nigeria. He is a Doctoral Student of the Department of
Computer Science, University of Nigeria, Nsukka, Nigeria. His research interests cut across
Knowledge Discovery in Large Databases, Modelling and Simulation, emerging technology
solutions for Smart sustainable cities such as Internet of Things (IoTs), Big Data, Blockchain
Technologies as well as Artificial Intelligence & Machine Learning algorithms.
Ome Uchenna Kenneth obtained his first degree (B.Eng) in Electrical and Electronics
Engineering Department of Enugu State University of Science and Technology. He also had his
Master's degree (M. Eng. Communication Option) at the sameUniversity. He is presently a Ph.D.
student of Electronics Engineering Department (Communication Option) in Enugu State
University of Science and Technology. He joined the service of the University of Nigeria,
Nsukka in 2008 and is currently a Principal Higher Technical Instructor in the Department of
Computer Science
8
