Enhancement of Online Education in Engineering College Based on Mobile Wireless Communication Networks and IOT

Abstract

The field of Engineering is that which needs a high level of analytical thinking, intuitive knowledge, and technical know-how. The area of communication engineering deals with different components including, wireless mobile services, radio, broadband, web and satellites. There is a rapid decline in the quality of students produced by engineering faculties as a result of sufficient and quality methods and frameworks of student assessment. The production of high-potential engineers is limited by the utilization of old and traditional education methodology and frameworks. The student presentation estimation system in engineering institution is a motionless manual. Usually, the assessment of student’s performance using the traditional system is limited to the use of students’ performance scores, while failing to evaluate their performance based on activities or practical applications. In addition, such systems do not take cognizance of individual knowledge of students that connects to different activities within the learning environment. Recently, engineering institutions have started paying attention to evaluation solutions that are based on wireless networks and Internet of Things (IoT). Therefore, in this study, an automated system has been proposed for the assessment of engineering students. The proposed system is designed based on IoT and wireless communication networks with the aim of improving the process of virtual education. The data used in this study has been collected through the use of different IoT sensors within the premises of the college, and pre-processed using normalization. After the data was pre-processed, it was stored in cloud. In order to enable the classification of student’s activity, an Adaptive Layered Bayesian Belief Network (AL-BBN) classifier is proposed in this work. The student’s scores have been calculated using fuzzy logic, while Multi-Gradient Boosting Decision Tree (MGBDT) was proposed for decision making. The use of python simulation tool is employed in the implementation of the proposed system, and the evaluation of the performance benchmarks was done as well. Based on the findings of the study, the proposed conceptual model outperformed the existing ones in terms of improving the process of online learning.

Full text

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Enhancement of Online Education in Engineering
College Based on Mobile Wireless Communication
Networks and IOT
https://doi.org/10.3991/ijet.v18i01.35987
Jaafar Q. Kadhim1(*), Ibtisam A. Aljazaery2, Haider TH. Salim ALRikabi3
1Electrical Engineering Department, College of Engineering, ALMustansiriyah University,
Baghdad, Iraq
2Electrical Engineering Department, College of Engineering, University of Babylon, Bbylon, Iraq
3Electrical Engineering Department, College of Engineering, Wasit University, Wasit, Iraq
jaafar80@uomustansiriyah.edu.iq
Abstract—The eld of Engineering is that which needs a high level of analyt-
ical thinking, intuitive knowledge, and technical know-how. The area of commu-
nication engineering deals with different components including, wireless mobile
services, radio, broadband, web and satellites. There is a rapid decline in the
quality of students produced by engineering faculties as a result of sufcient
and quality methods and frameworks of student assessment. The production of
high-potential engineers is limited by the utilization of old and traditional edu-
cation methodology and frameworks. The student presentation estimation sys-
tem in engineering institution is a motionless manual. Usually, the assessment
of student’s performance using the traditional system is limited to the use of
students’ performance scores, while failing to evaluate their performance based
on activities or practical applications. In addition, such systems do not take cog-
nizance of individual knowledge of students that connects to different activities
within the learning environment. Recently, engineering institutions have started
paying attention to evaluation solutions that are based on wireless networks and
Internet of Things (IoT). Therefore, in this study, an automated system has been
proposed for the assessment of engineering students. The proposed system is
designed based on IoT and wireless communication networks with the aim of
improving the process of virtual education. The data used in this study has been
collected through the use of different IoT sensors within the premises of the col-
lege, and pre-processed using normalization. After the data was pre-processed,
it was stored in cloud. In order to enable the classication of student’s activity,
an Adaptive Layered Bayesian Belief Network (AL-BBN) classier is proposed
in this work. The student’s scores have been calculated using fuzzy logic, while
Multi-Gradient Boosting Decision Tree (MGBDT) was proposed for decision
making. The use of python simulation tool is employed in the implementation
of the proposed system, and the evaluation of the performance benchmarks was
done as well. Based on the ndings of the study, the proposed conceptual model
outperformed the existing ones in terms of improving the process of online
learning.
176
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Keywords—Internet of Things (IoT), Online education, Adaptive Layered
Bayesian Belief Network (AL-BBN), fuzzy logic, Multi-Gradient Boosting
Decision Tree (MGBDT)
1 Introduction
One of the key contributors to national development is the educational sector, which
offers a wide range of learning locations and settings. The functionality and productiv-
ity of educational institutions have been signicantly impacted on by the emergence
of technology [1–3]. A key purpose of global computing technologies is to expand the
engagement of students. It also aims at collecting data from a wide range of sources
and incorporating them into different activity solutions, which is vital to the provision
of ratings that are based on the daily activities of students based on an educational
perspective. Regardless of the fact that there are huge technological advancements that
have been made in the area of education, the assessment of students is still carried
out manually. This is prone to human error as key features could be omitted when the
performance of students is computed. The IoT is an internet of networked, distinct
from others items that is gaining traction. It is basically aimed at developing intel-
ligent spaces/environments as well as self-aware objects. The emergence of the IoT
has resulted in the alteration of the global computing [4, 5] asides the numerous areas
that surround different sensors. In more recent times, major new trends are emerging,
particularly, in the area of combining sensors and device systems with technological
systems. This is coupled with the interactions between device-to-device and techno-
logical systems, which helps in solving most problems associated with device and
protocol. It is expected that the synergy between contextual data analytics and digital
applications like machine-to-machine communications can promote the transformation
of different industries. Also, it expected that the advancement of IoT innovation can be
enhanced by the emergence of cloud computing as well as its use in the fog paradigm,
considering the increased utilization of smart products. The interest in this study is
motivated by these developments, stimulating the eagerness to examine extant work,
develop novel models, and unearth novel IoT applications. The advancement in online
education has been supported by the continuous technological advancement in the area
of wireless communication networks, which have attracted the interest of profession-
als and academics, and they’re already being used in nautical applications globally.
Worthy of note is the fact that the current situation has resulted in the forced transition
from face-to-face educational paradigm to online paradigm. Even though this para-
digm is assumed to be simply embraced by learners, a closer examination shows that
this paradigm births a signicant variation. The productivity of learners can be greatly
impacted on by changes made to mode of studying. Given that knowledge is owned by
teachers, they are regarded as key players in the conventional learning system [6, 7].
Recently, there has been rapid advancement in the area of Mobile Wireless Communi-
cation Networks. The efciency of wireless communication has been on the increase,
which in turn allows for the deployment of several phases of cellular phone technology
that is currently used by numerous people [8, 9]. This trend began with 5G network
that was majorly employed in voice conversations, but served as the foundation of all
mobile generations that emerged afterwards. In every phase, novel technologies are
iJET ‒ Vol. 18, No. 01, 2023
177

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
introduced, while new features and functions are supported. The basic overview of
Internet of Things is graphically represented in Figure 1 below.
Fig. 1. General representation of Internet of Things
Investigations on IoT (Internet of Things) technology have focused on determining
if it can be used in improving virtual teaching and learning. In the present study, an
approach that supports decision-making among administrators of educational institu-
tions is proposed. It is expected that with this approach, they will be able to use data
obtained from the IoT to make well-informed decisions in the education sector. For
educational institutions to be able to make decisions based on data, they can make use
of real-time data stream which can be analysed and used to feed their learning analytic
system. More so, the performances of the management of higher institutions are inu-
enced by the ease with which academic platforms can be accessed through the internet.
The key contribution of the proposed approach is that, it demonstrates to educational
institutions that virtual teaching and learning can be supported and improved by using
data obtained through the Internet of Things. The application of IoT in educational
institutions is increasingly becoming popular, with institutions using the internet for
the collection, storage, and transmission of information [10]. The critical role of tech-
nology has been experienced in the education sector, especially in terms of student
connection and education. Virtual education has been signicantly inuenced by the
Internet of Things, which has changed the conventional methods of teaching as well
as the architectural setup of educational institutions. The concept of IoT is regarded in
two-fold in terms of the roles it plays in virtual education, given that it can be used as a
technology for the enhancement of educational infrastructure, and it can also be studied
as a course [11–13]. The revolution of virtual education can be enabled at all levels of
education through the use of IoT technology. This technology offers great benets to
178
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
different stakeholders at every level, including teachers and students. The use of Internet
of Things has been employed in the areas of teaching and research. The incorporation
of the Internet of Things into education allows the easy interaction between people and
things in the academia. Figure 2 is a representation of an IoT enabled teaching model.
Fig. 2. Internet of Things enabled teaching
There is still need for the further improvement of the wireless communications,
given the increasing need for connectivity between devices and the internet of things.
In the nearest future, the paradigms of IoT wireless communications network will be
needing approaches like dynamic spectrum access, spectrum sharing, optimal routing
and extraction of signal intelligence. The recent upsurge in the demand for IoT wireless
communications can be attributed to the unique nature of the Internet of Things wireless
communication networks coupled with the latest ubiquity of machine learning. Given
the high number of Internet of Things’ devices, huge interactions, especially through
wireless communication networks, it becomes important to have a networking archi-
tecture that is characterized by scalability. Particularly, the daily lives of humans are
gradually being pinned around the IoT, giving room for unique access to information.
In addition, the IoT enables the improvement of the virtual learning, enhancing more
accessibility. At the moment, improved results in learning are being recorded due to
the early efforts in IoT-based education. Learning and teaching resources have become
increasingly accessible to people in different parts of the world through wireless or
iJET ‒ Vol. 18, No. 01, 2023
179

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
wired network, thereby increasing the potentials of education for everyone. Through
IoT-based learning, students and teachers in different parts of the world can be able to
obtain local and international information that can improve teaching and learning out-
comes. Virtual education is regarded as a promising alternative for the application of
IoT. Recently, the application of IoT technology has enabled the integration of instruc-
tional materials into the development of repositories that are scalable and rich in media
content. The subject of Internet of Things in education has been extensively studied.
The critical role of IoT in virtual education is illustrated in Figure 3 below.
Fig. 3. IoT in online education
Huge advancements in telecommunications, cloud technology, detectors, nanotech-
nology, and big data will be recorded because of the impact of IoT. Communication
between humans in different locations have been made possible and easy due to the pres-
ence of Internet of Things coupled with current trends in technological advancements.
Also, a great number of intelligent systems have been created with the help of IoT.
Quite a number of areas have been revolutionized because of the application of IoT
in those areas. One of those areas is higher education, in which improved learning,
experimentation, and management is being recorded due to the use of IoT [14, 15].
Thus in this work, a Multi-Gradient Boosting Decision Tree (MGBDT) algorithm
and Adaptive Layered Bayesian Belief Network (AL-BBN) are presented as ideas for
action development for optimal mobile wireless communication networks and IoT.
The remaining parts of the paper are structured as follows: Part II. Review of Related
Works and Problem Statement; (III) Proposed Work; (IV). Performance Analysis;
(V) Conclusion
180
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
2 Related works
In the study carried out in [16], the challenges of educational system as well as the
possible ways of addressing them through the use of IoT technology and were investi-
gated the author examines educational system difculties and how to x them using Net-
work infrastructure and IoT technology. In their work, they designed an algorithm that
enables a modern approach to learning, and named it “IoT-based Centralized Double
Stage Education”. The algorithm allows for contemporary technologies and instructional
strategies to be integrated. More so, the investigation of security challenges was done
considering the physical layer due to the fact that core network safety systems are charac-
terised by complete privacy, minor computer complexity, consumption of resources, and
good adaption to change in channel. [17]. Their investigation focused on resource alloca-
tion, safety of intercept coding, processing of data, multi-node collaboration, alongside
identication and extraction of application layer key. The aim of this investigation is to
nd ways through which the increasing security challenges can be tackled. The authors in
[18, 19] beamed the ashlight on the present contributions of IoT to education, while
highlighting a wide range of obstacles that can hinder or challenge experimental endeav-
ours in the future. This study was a review study that focused on the use of IoT in educa-
tion, vocational learning, clinical advancement, green IoT, and wearable technology. In
[20, 21], the researchers proposed an online education system (OES), which checkmates
abnormal behaviour of users. The system is able to ag consumers with unruly behaviour;
the system exposes the private information of such consumers. This is the strategy used
by the system to achieve system security. The aim of this is to make the user return to
appropriate behaviour. The result of the system test based on reliability and safety param-
eters, the proposed system provides more security than existing ones. The security of the
system enables stem education through the deployment of resource-constrained IoT
devices. It was also reported that only little latency is required for communication and
computation. In addition, efforts were made by [22, 23] to enhance the process of learn-
ing; the researchers integrated Learning management systems with AI “articial intelli-
gence” so that the process of learning can be improved. As part of the new normal, this is
aimed at the creation of a standard educational shift that allows students to learn virtually
and to be able to gain access to virtual assistants that can support their academic endeav-
ours. The present level of research and practice in the area of engineering education was
evaluated in study [24, 25]. Who also investigated the implication of industrial research.
This was done considering the new trending services through wearable technologies,
mobile computing, deep learning, and internet of things. A discussion on the ideas and
history of internet of things was presented in [26, 27] alongside the idea of educational
administration, education, and related issues. The application of such modern technolo-
gies can enable the identication of difculties that exist within the education sector, and
help decision makers in taking the right steps within a smart environment. To this end,
FHM University of Applied Sciences, a well-recognized education in Germany, was
investigated as a case study of an experimental implementation in the area of IoT. Another
educational system was designed by the authors in [28–30], and the system was designed
to imitate the intellectual intelligence of learning things. It is a learning system that is
based on IoT, and designed to complement conventional methods of education alongside
top-notch learning approaches. The use of this system can be employed on a wide range
of applications and devices allowing interaction and opinion-sharing with consumers
iJET ‒ Vol. 18, No. 01, 2023
181

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
through the internet of things. The critical role of internet of things in enhancing the pro-
cess of education, particularly learning was analysed by the authors in [31, 32]. In their
study, they highlighted the application of IoT in different areas of education, including,
distant learning, medicine, science, consumer green education amongst many others. The
emergence of the internet, transformations in terms of human-to-machine, human-to-hu-
man interactions have occurred, and these have been transformed to worldwide commu-
nications network. In [33], the author proposes a strategy for developing a long-term
educational environment that is nancially, socially, and ecologically responsible. In
addition to technology, a better IoT-supported educational environment necessitates
increased collaboration among institutions, staff, and students. The vision of a completely
reformed eld of education, digitally assisted, enriched, and nancially, economically,
and socially economic health is only conceivable with the full commitment of every
stakeholder and respective desire to help and team up. In [34], the use of blockchain tech-
nologies in education was systematically evaluated with the aim of providing in-depth
insight on the critical application and role of blockchain in education. They also focused
on highlighting its application in the future developments of the education sector. Block-
chain technology has huge potentials in the area of education, and as such more efforts
should be geared towards exploring such potentials. These authors, through their research
have set the platform for decision makers and academics to further explore other areas in
which this technology can be applied. The author in [35], proposed the use of a wide
range of sensor devices in an educational system. The proposed system was found to be
efcient in terms of its scalability in addressing the increasing sensor populations. They
described the architecture and implementation of the IoT from a software perspective.
They also provided a description of the proposed system’s features, carried out an analy-
sis of the lessons learned, while highlighting future trends of their work. The authors in
[36] carried out an investigation of the basic principles, features, classications, technol-
ogies, and challenges associated with the internet of things. In their work, the crucial role
played by IoT in the development of a smart educational system was demonstrated. They
also highlighted the contribution of IoT in decision-making by enabling sound judgement
and capacity building which are critical to the daily activities of humans. Also, major
utilities in different industries can be expanded and improved upon through the use of IoT.
By improving those utilities, applications can be developed through a new ecosystem by
means of a world-wide distributed local wireless system of intelligent items. In the work
done by [37], a device referred to as wrist-based wearable for Education 4.0 (tness
tracker) was proposed, and the benets that can be derived from the use of wearable
device were highlighted. The authors also designed a questionnaire to evaluate the expe-
riences of users in terms of their acceptance of modern electronic technology in higher
education. Their experimental results showed the key procedures and sensors for educa-
tion 4.0. They also demonstrated through their results that their proposed tness trackers
designed with a built-in sensor is capable of collecting a huge amount of real-time data
while kids are studying. The researchers in [38] show the importance of the current edu-
cation technology in enabling the productivity of students and teachers. They also demon-
strated that it is time saving for teachers, and requires less efforts. In this study, it was
revealed that the use of Learning Management systems helps students to acquire more
knowledge within a shorter period of time. It was noted in the study that, interaction
between teachers and students, teachers and teachers, and students and students is enabled
through the proposed method. While showing the benets that can be derived by
182
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
integrating an LMS with higher education, the authors also urged other higher institutions
to adopt this technology.
3 Problem statement
There is a wide range of devices that can be used by students to accomplish their
academic goals and tasks, including computers, phones, and tablets. These devices
offer them the benet of participating in classroom activities virtually. In addition, IoT
facilitates interaction and communication between instructors and students. Although
IoT devices may have the simplest applications, such as registering entrance and exit at
a security door, there more complex applications of such devices as they are designed
with more sophisticated components. Additionally, the transmission of critical data to
IoT systems can impact on all other things related to it in a negative way.
4 Proposed methodology
In the current work, a quality IoT strategy has been developed by using an Adap-
tive Layered Bayesian Belief Network (AL-BBN) alongside Multi-Gradient Boosting
Decision Tree (MGBDT) algorithm within the internal environment. The purpose of
this strategy is to increase data that can facilitate online learning. Figure 4 below shows
the functional ow of this study.
Fig. 4. Schematic representation of proposed work
iJET ‒ Vol. 18, No. 01, 2023
183

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
4.1 Data acquisition and synchronization
Data such as students’ geographical location and their daily interaction are collected
through a data acquisition system. The data which is gathered enables the incorporation of
energy-efcient sensors, intelligent systems, as well as other monitoring devices. A per-
sonal sensor network composes of GPS sensors, radio frequency identication (RFID),
and other IoT devices. The purpose of designing this system is to enable the collection of
students’ information, daily engagements of both staff and students, and their locations.
More so, both unstructured and structured data are collected from the personal sensor
network by the gateway. After the data is collected, it is forwarded to a cloud storage
database for further analysis. The features of the dataset are represented in Table 1 below.
Table 1. Personal attributes of student
S.no Features Explanation
1 SID Student identication number
2 Name Student name
3 Age Age of the student
4 Sex Male or Female
5 Address Permanent address of the student
6 Family member name Name of the family member
7 Family member mobile number Family member mobile number
8 Student data Student previous performance information
4.2 Data Pre-processing using normalization
The selection of the target data should be made from the unprocessed collection of
nancial data so that the performance can be boosted. It is important that this data be
prepared to enable its usability. After the target data has been processed, it is analysed
and then the results generated through the use of data mining methods. The purpose of
transforming data is to alter the pattern and types of characteristics. The pre-processing
of data is a step that is crucial to data processing and extraction. There are chances that
data which is falsied will be found among the semi-structured, structured and unstruc-
tured datasets that are unprocessed. Thus, it is necessary for data to be processed so that
it can be void of noises, and can be standardized. The elimination of noisy images from
the dataset requires the use of image retrieval methods. The normalization of the dataset
may be carried out at the stage of pre-processing. The arithmetical representation of
D-count is given be Equation (1) as follows:
DN ][( )/
(1)
Where, b denotes the information’s mean and t represents the standard deviation,
while D is represented as,
D
NN
R
 (2)
184
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Here
N
is the specimen’s mean, and R denotes the standard deviation of the specimen.
Below is the representation of the random specimen:
DN
st
t
 
 
01 (3)
The defects that are depending on t2 are represented by t.
Ensuring that, as seen below, the defects should not depend on one another.
lU
l
lp
n~21

(4)
Here, l represents the random parameter.
Then the movements of the variables are normalised using standard deviation. The
momentary scale deviance is determined using the formula below (5).
NNR
nnr
nnr


(5)
Here, momentary scale is denoted by mms.

nnr
Va (n )NNR^
(6)
N represents random variable, while Va denotes predicted values.

nnr Va nNNR


^^
2 (7)
l
nnr
N
p= (8)
The coefcient of variance is denoted as lp.
Each parameter should be xed at zero so that characteristic scaling can be paused.
This approach is referred to as “unison-based normalizing approach.” After normaliza-
tion, the formula will be as follows:
N
ll
ll
min
ma
xm
in
'
()
()


 (9)
Upon completion of the process of data normalization, the data may be saved and the
dataset’s anomalies and length can be maintained. This stage is aimed at minimizing or
eliminating data delays. Afterwards, the dataset that has been subjected to the process
of normalization can be used as input data in the subsequent stages of the process. The
dataset for students’ virtual education is saved in the cloud, which is referred to as an
Infrastructure as a Service (IaaS) provider. Here, data is gathered from different sources
and can be retrieved at any time. The use of cloud storage repository is employed in
saving the time-stamped data, and this data is later on retrieved for analysis. The clas-
sication of students’ activities is done appropriately based on the different hypotheses
highlighted in the categorization section. In addition, students’ personal information is
iJET ‒ Vol. 18, No. 01, 2023
185

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
saved in the cloud repository, where each student is assigned a unique number through
which they can be identied. The unique number is connected to the daily IoT-based
activities within the institution.
4.3 Students Activity Classication using Adaptive Layered Bayesian Belief
Network (AL-BBN)
In the methodology that is proposed in this study, there are two main categories of
activities including, rare and monotonous activities. The later refers to those activities
that involve the daily monitoring of students’ progress using data from IoT sensors and
hardware devices. The use of activity models can be employed in dening a wide array
of students’ activities. In this work, the correlations between independent variables and
student attrition (which is the dependent variable), are captured and described using
AL-BBN. AL-BBNs are complex mathematical models that show explicitly and natu-
rally show the link prediction structural correlation across different models in an array
of variables and variable groups. The AL-BBN chain rule is an approach that can be
used to conveniently represent complex probability distributions, whereby each ix rep-
resents a variable and Tzix indicates the parents of the same (ix) variable.
Ti
iT
iTz
nx
i
x
n
x
(,
,(
)
11

|)
(10)
Some of the important activities of students that can be captured include participa-
tion of students in different forums and discussions, participation of students in study
cohorts, college involvement in interactions that are key to the theme, and terms of
membership of physical activities. The Bayes rule is the conditioned stimulus, and this
rule involves the computation of the possibility of each provided target number or class
of value. After the computation, the structure possessing the best estimated prediction
is selected for the next stage. Lastly, this replica is aimed at identifying provisional cor-
relations between student attrition predictors. For a variable ix, a suitable representation
of the students is required:
Tz Bi
ix
x
{, }
()

(11)
Due to the fact that exponential growth is exhibited by the amount of conditional
estimations that must be created for each root, it becomes necessary for an intelligent
and professional AL-BBN engineer to commit a good amount of time to one or more
domain experts so as to be able to build a moderate-sized network manually. The exam-
ple below shows that B serves as the base classier in the second fall that has been
recorded. These utilizing techniques how much material is supplied when the category
variable is known.
XiiTii log
Ti i
Ti Ti
Txyxy
xy
xy
ii
xy
();(,) (,)
()()
,x
,

y (12)
186
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
The ordering, which is determined by the relationship amongst each pair of vari-
ables, only includes edges amongst predictor variables. An edge’s weight in a graph is
determined by mutual information which denotes the relationship between two vari-
ables. The following formula denes mutual information between two random vari-
ables ix = Fall student active and iy = Spring student active:
XiiB Ti iBlog
Ti iB
Ti BT i
Tx yxy
xy
xyB
ii
xy
():| (, ,) (, |)
(|)( )
|
,,
xy
BB
 (13)
Where the tree is a function over Tzix is the set of parents for each iy, and B is the class
variable Tzix that has no students.
4.4 Students activity score based on fuzzy logic
There is a relationship between each illustration and a period. The data which pro-
vides details about the activities of students is known as temporal data. Dissimilar
activities-related sensory input is provided in the form of behavior metrics at different
timestamps. Through the process of fuzzication, a collection of terms and fuzzy lan-
guage concepts are created based on the exact set of inputs provided. Subsequently, the
use of membership function is employed in creating a set of fuzzy logic, and followed
by the establishment of the nal inference. Intra-class deviation, Inter-class volatility,
and feature-based time of each component for each sub-band are all fuzzy logic input
elements provided to the student’s activity. The sub-band specic feature subsets are
selected by using fuzzy logic with the most suitable classiers.
eS h
mn
:[,].→0
(14)
The following production rules guide the fuzzy logic:
SIFr yBANDr yBANDr yBTHENclassdiS
ii innnii
:,,,
11 1222 1   ,,
where I denotes the rule index, S represents the number of rules, BKi is a fuzzy term
characterizing the k-th quality in the i-th rule (k = 1, … , m); di is the resultant class,
R = (r1, r2, …, rn) is the binary vector of features, and line r1∧ rk shows if a feature is
present (rk = 1) or absent (rk = 0) in the classier.
There is no exact quantity at the timestamp axis, considering the fact that there
is difference in timestamp according to student. A tensor which is referred to as the
student-activity data tensor (RgPs) has been designed with the aim of achieving this pur-
pose. The mathematical representation of the daily RgPs of a student is given as follows:
RP RRRR
gs m
=[],,,,
123 (15)
iJET ‒ Vol. 18, No. 01, 2023
187

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
In the observation table, the class label is dened {(yp; dp), p = 1, z} as follows:
classdt
tin i


,{}argmax
1

(16)


jp Bi pBin pn Bi
kp
k
k
m
yy
yy
() () ()
()


11 1
 (17)
 
tp iD classt tp iD classt Bi
kp
k
k
m
yS yS y
jj
() ()
()





1 (18)
Where mBik (ypk) denotes the fuzzy term Bik’s membership function value at point ypk.
FR
IFdarg ey R
OTHERWISE
z
p
zpin ip
(, )
,max ;,
,
()











1
1
1
0 (19)
Where e(yp; θ, R) denotes the output of fuzzy logic with fuzzy terms θ parameters
and R at point yp. The key challenge of designing a fuzzy logic is to ascertain the max-
imum of the function in space R and θ = (θ1, θ2, …, θD):
F
Rin
jD
jjj
i
(, )
{,},
,,


Rmax
minmax









 1
01 1

(20)
Where θj
min, θj
max denotes the upper and bottom bounds of each parameter’s fuzzy
logic, respectively. This is an NP-hard problem, and in this study a proposal is made to
resolve the problem by dividing it into two tasks which are student activity and fuzzy
term parameter. Each activity (Zy), where y is the amount of actions from 1 to n, and
the students must complete t. The probability assessment of actions Zy at day f can be
expressed as Uf
y, where
1≤≤ft
is the element of working days in a college term. Using
the formula below, a student’s score for each activity R (Zy) can be calculated:
R
U
t
f
t
y
f
()Zy


1 (21)
Activities that are of great signicance are considered as monotonous activities and
have a Uf
y score that is calculated on a regular basis. While on the other hand, the bal-
ance of the events set is made up of activities that occur occasionally.
The fuzzy logic algorithm is presented in Algorithm 1 below
188
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Algorithm 1: fuzzy logic algorithm
Step 1 Initialization
Initialize (Pop)
Archive.add (Pop)
Set Operators Prob (1.0)
window = Stagnation = 0
Step 2 primary loop
if the stopping requirement is not met,
Step 2.1 Parents’ choice
for x = 1 to |Parents| do
ifRandomDouble (0, 1) ≤ β then
Parents[x] ← TournamentSSD (Archive)
else
Parents[x] ← TournamentSSD (Pop)
end if
end for
Step 2.Reprint
Operator ← Roulette (OpProb)
Of fspring ← Operator (Parents)
Consider your options (Offspring)
UpdateUse = OpUse (Operator)
window++
Step 2.3 Update on the Archive
if ! (Archive.add (Offspring)) then
Stagnation = Update Stagnation ()
end if
Step 2.4 Invoke the Fuzzy Inference System (FIS)
if window == windowSize then
UpdateOpProb(OpUse, Stagnation)
Stagnation = 0 window
end if
Step 2.5 Population Update
NewPop ← Pop.add (Offspring)
fast non dominated sortSSD (NewPop)
P op ← RemoveWorstSolution (NewPop)
end while
Step 3 Output
return Archive
4.5 Decision making layer using Multi-Gradient Boosting Decision Tree
(MGBDT)
The results obtained from the previous classication of decision tree are used in
training each decision tree. The linear nature of the Multi-Gradient Boosting Decision
Tree, makes the parallel training of the decision tree challenging. The second S2 tree
training optimization target is the sum of the rst S1 decision tree’s outcome and the
remaining S-value, and the method’s nal outcomes are the sums of each decision tree’s
outcome. Equation (13), in other words:
213
ˆ
SS S S++
= (22)
iJET ‒ Vol. 18, No. 01, 2023
189

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
There are two loss functions possessed by the MGBDT that are often utilized for
iterative optimization as shown in Equation (13). Alternatively, the effect can be opti-
mized instantly, whereas, the other alternative can be the optimization of the gradi-
ent’s decent signicance. There is a difference between MGBDT and classic boosting.
If MGBDT is sub-optimized, the target is optimal. The booster is a resembling device.
The estimated value of the many samples i as a node average power, which may be
represented as Equation, is the integral gain μ of a node split (14),




ie
y
y
e
1/ (23)
Consequently, the node’s mistake can be written as Equation (15),
Error ()iv
x
2 (24)
In the process of node division, it is compulsory to select the feature which has the
high tear gain for segment, and the tear winning L is determined using the following
formula:
LQQ
x (25)
Based on Equation (17), the difference can be thought of as a less function, or Qx:
Qi i
xn
fe
P
ePnf
 


()
()

22
(26)
Consequently, every splitting node problem will be focused on identifying a vari-
able that is capable of increasing the split gain the most Q and Qx are separated and
expanded as in formula (18):
Lsum Fsum Psum total
fP




22 2
// / (27)
sum2 represents the total of squares of all variations, as stated in Equation (18), where
sum2
f and sum2
p are the total of the squares of all variants in the sub tree, respectively.
Consequently, only L needs improvement. As mentioned earlier, the tree nodes in each
tree node in the MGBDT are not together, rather, they are separated in isolation. Each
trained forest is aimed at summing up the original trees and rate of presentation. The
information entropy can be calculated using the training set. The n class y = 1, 2, … n
is dened by Q, which holds the number of data samples. Qy is the number of data
samples.
Y( ,)
()
,
qq
qw
logw
nyiy
y
n
12 1
 

(28)
190
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
E is the tree’s root, and E contains e values {e1, e2, … … ee} The training set S is
divided into subsets {S1, S2, … … Se}, with Sx denoting a specic subset and ex denoting
the value of e. Syx represents the element of samples in Sx that belong to Qy.
KE
SS S
S
Y(ss
s)
xx nx
xx nx
x
e
() ,,



12
12
1

(29)
Y(ss s) wlog w
xx nx yx yx
y
n
12 2
1

()
(30)
Gain EY(s ss)K(E)
xx nx
() 
12
(31)
The purpose of using MGBDT algorithm in this research is to enable decision-making
on the performance of college students’ performance. Factors such as data extraction,
data treatment, selection of feature, training model, and prediction of unknown data
have been prioritized. The MGBDT algorithm is represented by Algorithm 2.
Algorithm 2: MGBDT algorithm
Input: The training data set GϵSn, size of training set e=|G|, sample data ixϵG, x = 1, 2, …e, number of
regression trees N, the maximum depth of each tree F.
Output: Trained model
QS
Pq
pN
Pz
p
 



.,,,..,12
Initialization: Q = ø, p = 0, p is the current number of regression trees
While p<N: For all ixϵG, calculate the corresponding dx and lx according to



p1 p1
22
p x x x px x x x
d H / j (i ) j j i and l H / j (i );()
−=

=∂ ∂ − − =∂ ∂

Initialize the p th regression tree SPP = ø and the current depth of regression tree f = 0;
While f<F:
Tranverse every leaf node Ny in SPP, nd the best split for each leaf node according to
splitargmin
splitr
D
L
D
L
DD
LL
H
H
S
S
HS
HS
*
()
 

2
22
where
DH
d
x
iN
xyh


,
and
LH
l
x
iN
xyh


,
, and DS, LS are similar.
Split Ny into left child NH
y and right child, NS
y, then add them into SP
P;
Traverse all the leaf nodes of SP
P, calculate the predicted value of Ny;
Add SP
P, into set Q;
Return Q.
5 Performance analysis
The newly proposed IoT and Adaptive Layered Bayesian Belief Network (AL-BBN)
models are functional to Selective Multi-Gradient Boosting Decision Tree (MGBDT)
algorithm applications, according to this section. The performance of the proposed
approaches was analysed using performance parameters like precision, recall, accu-
racy, and score. In analysing the performances of the models, they were compared with
extant approaches like Naïve Bayes, Articial Neural Network, Logistic Regression,
and Decision Tree.
iJET ‒ Vol. 18, No. 01, 2023
191

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Fig. 5a. Performance score computation using proposed methodology
Fig. 5b. Proposed system component based execution time (in seconds) for each day
Fig. 5c. Proposed system stability
Figure 5. (a) The proposed mechanism for calculating performance scores, (b) pro-
posed system component-based execution time (in seconds) for each day, (c) proposed
system stability. Figure 5a Ten students from the same class were graded based on
192
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
their monthly performance over a period of three months. The performance of the rst
month was done using a manual system of grading, while that of the last two months
was done using the approach proposed in this work. The effecting duration of numerous
components required for the computation of the daily scores of students’ performance
is presented in Figure 5b. From Figure 5b, it can be clearly seen that the time required
for the data mining stage is much longer than that of the recognition stage. Increase in
the number of dataset based on the increase in the percentage of students’ results in the
relative shifting of the mean absolute value as shown in Figure 5c.
Fig. 6. Precision comparison
Precision refers to a quantity in decimal numbers that comes with the whole number
and is unrelated to the accuracy. Practically, the concepts of accuracy and precision are
synonymous, and as such, can be easily interchanged. The comparison of the proposed
techniques with extant techniques based on precision is presented in Figure 6.
Fig. 7. Recall comparison
A user holds recall when recalling a visit or repeating a sonnet after reading its title.
Here, a multiple-choice test was used given that is easier than an essay and more pre-
ferred by people. The administered test was based on recall remembrance. The result
iJET ‒ Vol. 18, No. 01, 2023
193

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
of the comparison between the extant approaches and proposed approach based on the
recall parameter is shown in Figure 7:
Fig. 8. Score comparison
Figure 8: Score of comparison between proposed approach and existing approaches.
score
tp
tp fp fn


05.( ) (32)
Fig. 9. Accuracy comparison
Accuracy provides the categorization with the required educational information.
Figure 9: results of the comparison between the proposed approach and extant approach
based on accuracy.
Ac
tp tn
tp tn fp fn


 
()
()
(33)
194
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Fig. 10. Comparison between the predictions of teacher-based and student version
Figure 10 shows the results of the graphical comparison, with the two scenarios over-
lapping in three elements (research opportunity, e-learning, and hyper-connectivity).
The organizations opine that the variables of virtual education IoT ecosystem are sig-
nicantly inuenced by the Internet of Things. Based on the student’s view the most
critical component in virtual learning is self-learning, however, it is not of much rel-
evance in the eyes of the teacher. Also, the inuence of IoT use in virtual education
on the issue of cooperation is another difference between the two perspectives. It is
believed by teachers that the IoT enables effectiveness in terms of teamwork, and coop-
eration, but students do not value the Internet of Things in that regards.
Fig. 11. Impact of the IoT in online education
iJET ‒ Vol. 18, No. 01, 2023
195

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
Figure 11 presents the impact of IoT on virtual education. The ndings revealed that
IoT enables excellent performance in teaching, with high percentage in comparison to
the disagreement and agreement. More so, the ndings show that in terms of improve-
ment in teacher communication, most respondents disagreed that the IoT enables
improved communication. Meanwhile, a high percentage of the respondents agree that
IoT enables teaching activities.
6 Discussion
Here, the usefulness of the approach proposed in this study is estimated in contrast
to the IoT that was previously mentioned for the given data. It was also found that the
method proposed in this study performs as good as that of global standard approaches
like ANN [39], NBC [40], DT [41], and LR [42]. In ANN [39], the selected projection
technique directly impacts on the connection’s performance. The ANN should rst be
converted into numerical characters before it can be used to solve any problem. In the
study of [40], the NBC ‘zero-frequency problem,’ occurs anytime the lowest error is
assigned by the system to the predictor data whose category is not found in the dataset.
Therefore, a mild strategy should be used in solving this problem. In the study of [41],
it was demonstrated that the logistic regression may be signicantly reshaped by a
small piece of data, which can in turn increase insecurity for the system. In comparison
with other approaches, the estimation of a decision tree can be extraordinarily complex
durion. It takes a loger period of time to retrain a decision tree. The authors in [42]
revealed that the key limitation of crucial limitation of logistic regression is the con-
dition of proportionality between the logistic regression variables. Predictor accuracy
(coefcient size) as well as connection direction are also revealed (positive or nega-
tive). However, the aforementioned limitations can be solved through the use of the
proposed technique. In this part, the analyses of the experiments have been presented
for MGBTDT algorithm and AL-BBN. Based on the evaluation, it can be concluded
that the proposed approach demonstrated superior performance in terms of IoT as com-
pared to ANN [22], NBC [40], DT [41], and LR [42].
7 Conclusion
The proposed system demonstrates an experimental conguration concentrating on
the AL-BNN in a IoT virtualized environment. The MGBDT algorithm was presented
to initiate, solve, and test the problem’s intents. Consequently, the results revealed that
improvements were achieved in the IoT method. The extant approaches include Naïve
Bayes Classier, Articial neural network (ANN), Logistic Regression, and Decision
tree (DT). Lastly, the performance parameters of the study are examined in compar-
ison with those of other models with the aim of determining the most effective one.
In addition, the procedures of data migration needed to meet the requirement of the
future generations can be deployed.
196
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
8 References
[1] M. Vaezi, Z. Ding, and H. V. Poor, Multiple Access Techniques for 5G Wireless Networks
and Beyond. Springer, 2019. https://doi.org/10.1007/978-3-319-92090-0
[2] B. Majeed and H. Alrikabi, “Tactical Thinking and its Relationship With Solving
Mathematical Problems Among Mathematics Department Students,” International Journal
of Emerging Technologies in Learning (iJET), vol. 16, no. 9, pp. 247–262, 2021. https://doi.
org/10.3991/ijet.v16i09.22203
[3] D. Turnbull, R. Chugh, and J. Luck, “Transitioning to E-Learning During the COVID-19
Pandemic: How have Higher Education Institutions responded to the challenge?,” Education
and Information Technologies, vol. 26, no. 5, pp. 6401–6419, 2021. https://doi.org/10.1007/
s10639-021-10633-w
[4] W. Ejaz and A. Anpalagan, “Internet of Things for Smart Cities: Overview and
Key Challenges,” Internet of Things for Smart Cities, pp. 1–15, 2019. https://doi.
org/10.1007/978-3-319-95037-2_1
[5] H. T. S. alim and N. A. asim, “Design and Implementation of Smart City Applications Based
on the Internet of Things,” International Journal of Interactive Mobile Technologies (iJIM),
vol. 15, no. 13, pp. 4–15, 2021. https://doi.org/10.3991/ijim.v15i13.22331
[6] W. Villegas-Ch, M. Román-Cañizares, and X. Palacios-Pacheco, “Improvement of an Online
Education Model with the Integration of Machine Learning and Data Analysis in an LMS,”
Applied Sciences, vol. 10, no. 15, p. 5371, 2020. https://doi.org/10.3390/app10155371
[7] L. F. Jawad, B. H. Majeed, and H. T. ALRikabi, “The Impact of Teaching by Using STEM
Approach in the Development of Creative Thinking and Mathematical Achievement Among
the Students of the Fourth Scientic Class,” International Journal of Interactive Mobile
Technologies, vol. 15, no. 13, pp. 172–188, 2021. https://doi.org/10.3991/ijim.v15i13.24185
[8] A. A. Salih, S. Zeebaree, A. S. Abdulraheem, R. R. Zebari, M. Sadeeq, and O. M. Ahmed,
“Evolution of Mobile Wireless Communication to 5G Revolution,” Technology Reports of
Kansai University, vol. 62, no. 5, pp. 2139–2151, 2020.
[9] H. T. Salim, A. H. M. Alaidi, A. S. Abdalrada, and F. T. Abed, “Analysis the Efcient
Energy Prediction for 5G Wireless Communication Technologies,” International Journal
of Emerging Technologies in Learning (iJET), vol. 14, no. 08, pp. 23–37, 2019. https://doi.
org/10.3991/ijet.v14i08.10485
[10] R. Salah Khairy, A. Saleh Hussein, and H. TH. Salim ALRikabi, “The Detection of
Counterfeit Banknotes Using Ensemble Learning Techniques of AdaBoost and Voting,”
International Journal of Intelligent Engineering and Systems, vol. 14, no. 1, pp. 326–339,
2021. https://doi.org/10.22266/ijies2021.0228.31
[11] D. Abdul-Rahman and H. Salim, “Enhancement of Educational Services by Using the
Internet of Things Applications for Talent and Intelligent Schools,” Periodicals of Engi-
neering and Natural Sciences (PEN), vol. 8, no. 4, pp. 2358–2366, 2020.
[12] D. K. Abdul-Rahman Al-Malah, S. Ibrahim Hamed, and H. T. Alrikabi, “The Interactive
Role Using the Mozabook Digital Education Application and its Effect on Enhancing the
Performance of eLearning,” International Journal of Emerging Technologies in Learning
(iJET), vol. 15, no. 20, pp. 21–41, 2020. https://doi.org/10.3991/ijet.v15i20.17101
[13] B. H. Majeed, L. F. Jawad, and H. T. ALRikabi, “Computational Thinking (CT) Among Uni-
versity Students,” International Journal of Interactive Mobile Technologies, vol. 16, no. 10,
2022. https://doi.org/10.3991/ijim.v16i10.30043
[14] M. Al-Emran, S. I. Malik, and M. N. Al-Kabi, “A Survey of Internet of Things (IoT) in Edu-
cation: Opportunities and Challenges,” in Toward Social Internet of Things (SIoT): Enabling
Technologies, Architectures and Applications: Springer, pp. 197–209, 2020. https://doi.
org/10.1007/978-3-030-24513-9_12
iJET ‒ Vol. 18, No. 01, 2023
197

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
[15] G. Pappas, J. Siegel, I. N. Vogiatzakis, and K. Politopoulos, “Gamication and the Internet
of Things in Education,” in Handbook on Intelligent Techniques in the Educational Process:
Springer, pp. 317–339, 2022. https://doi.org/10.1007/978-3-031-04662-9_15
[16] K. Khujamatov, E. Reypnazarov, N. Akhmedov, and D. Khasanov, “IoT Based Centralized
Double Stage Education,” in 2020 International Conference on Information Science and
Communications Technologies (ICISCT), 2020: IEEE, pp. 1–5. https://doi.org/10.1109/
ICISCT50599.2020.9351410
[17] S. Zhang, J. Liu, T. K. Rodrigues, and N. Kato, “Deep Learning Techniques for Advancing
6G Communications in the Physical Layer,” IEEE Wireless Communications, vol. 28, no. 5,
pp. 141–147, 2021. https://doi.org/10.1109/MWC.001.2000516
[18] H. T. H. Haider TH. Salim ALRikabi, “Secure Chaos of 5G Wireless Communication Sys-
tem Based on IOT Applications,” International Journal of Online and Biomedical Engineer-
ing(iJOE), vol. 18, no. 12, pp. 89–102, 2022. https://doi.org/10.3991/ijoe.v18i12.33817
[19] S. F. Shetu, M. M. Rahman, A. Ahmed, M. F. Mahin, M. A. U. Akib, and M. Saifuzzaman,
“Impactful e-learning Framework: A New Hybrid Form of Education,” Current Research in
Behavioral Sciences, vol. 2, p. 100038, 2021. https://doi.org/10.1016/j.crbeha.2021.100038
[20] S. Jegadeesan, M. S. Obaidat, P. Vijayakumar, M. Azees, and M. Karuppiah, “Efcient
Privacy-Preserving Anonymous Authentication Scheme for Human Predictive Online
Education System,” Cluster Computing, pp. 1–15, 2021. https://doi.org/10.1007/
s10586-021-03390-5
[21] M. El-Hajj, A. Fadlallah, M. Chamoun, and A. Serhrouchni, “A Survey of Internet of
Things (IoT) Authentication Schemes,” Sensors, vol. 19, no. 5, p. 1141, 2019. https://doi.
org/10.3390/s19051141
[22] S. Pervez, S. ur Rehman, and G. Alandjani, “Role of Internet of Things (IoT) In Higher
Education,” Proceedings of ADVED, pp. 792–800, 2018.
[23] B. Hasan and L. Fouad, “The Impact of CATs on Mathematical Thinking and Logical Think-
ing Among Fourth-Class Scientic Students,” International Journal of Emerging Technol-
ogies in Learning (iJET), vol. 16, no. 10, pp. 194–211, 2021. https://doi.org/10.3991/ijet.
v16i10.22515
[24] A. Siddhpura, V. Indumathi, and M. Siddhpura, “Current State of Research in Application of
Disruptive Technologies in Engineering Education,” Procedia Computer Science, vol. 172,
pp. 494–501, 2020. https://doi.org/10.1016/j.procs.2020.05.163
[25] D. Al-Malah, H. Alrikabi, and H. A. Mutar, “Cloud Computing and its Impact on Online Edu-
cation,” IOP Conference Series: Materials Science and Engineering, vol. 1094, p. 012024,
2021. https://doi.org/10.1088/1757-899X/1094/1/012024
[26] H. D. Mohammadian, “IoT–A Solution for Educational Management Challenges,” in 2019
IEEE Global Engineering Education Conference (EDUCON), 2019: IEEE, pp. 1400–1406.
https://doi.org/10.1109/EDUCON.2019.8725213
[27] N. A. Jasim and A. Z. Abass, “Smart Learning based on Moodle E-learning Platform and
Development of Digital Skills for University Students,” International Journal of Recent
Contributions from Engineering, Science & IT (iJES), vol. 10, no. 1, 2022. https://doi.
org/10.3991/ijes.v10i01.28995
[28] M. S. Satu, S. Roy, F. Akhter, and M. Whaiduzzaman, “IoLT: An IoT Based Collabora-
tive Blended Learning Platform in Higher Education,” in 2018 International Conference
on Innovation in Engineering and technology (ICIET), 2018: IEEE, pp. 1–6. https://doi.
org/10.1109/CIET.2018.8660931
[29] N. Alseelawi, H. T. Hazim, and H. T. Salim ALRikabi, “A Novel Method of Multimodal
Medical Image Fusion Based on Hybrid Approach of NSCT and DTCWT,” International
Journal of Online & Biomedical Engineering, vol. 18, no. 3, 2022. https://doi.org/10.3991/
ijoe.v18i03.28011
198
http://www.i-jet.org

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
[30] I. A. Aljazaery, J. S. Qateef, A. H. M. Alaidi, and R. a. M. Al_airaji, “Face Patterns Analysis
and Recognition System Based on Quantum Neural Network QNN,” International Jour-
nal of Interactive Mobile Technologies, vol. 16, no. 8, 2022. https://doi.org/10.3991/ijim.
v16i08.30107
[31] D. D. Ramlowat and B. K. Pattanayak, “Exploring the Internet of Things (IoT) in Education:
A Review,” Information systems design and intelligent applications, pp. 245–255, 2019.
https://doi.org/10.1007/978-981-13-3338-5_23
[32] H. T. Salim, and H. Tauma, “Enhanced Data Security of Communication System using
Combined Encryption and Steganography,” International Journal of Interactive Mobile
Technologies, vol. 15, no. 16, pp. 144–157, 2021. https://doi.org/10.3991/ijim.v15i16.24557
[33] M. Maksimović, “IOT Concept Application in Educational Sector using Collaboration,”
Facta Universitatis. Series: Teaching, Learning and Teacher Education, vol. 1, no. 2,
pp. 137–150, 2018. https://doi.org/10.22190/FUTLTE1702137M
[34] S. Baskar, P. M. Shakeel, R. Kumar, M. Burhanuddin, and R. Sampath, “A Dynamic and
Interoperable Communication Framework for Controlling the Operations of Wearable
Sensors in Smart Healthcare Applications,” Computer Communications, vol. 149, pp. 17–26,
2020. https://doi.org/10.1016/j.comcom.2019.10.004
[35] K. Gunasekera, A. N. Borrero, F. Vasuian, and K. P. Bryceson, “Experiences in Building
an IoT Infrastructure for Agriculture Education,” Procedia Computer Science, vol. 135,
pp. 155–162, 2018. https://doi.org/10.1016/j.procs.2018.08.161
[36] M. Abdel-Basset, G. Manogaran, M. Mohamed, and E. Rushdy, “Internet of Things in Smart
Education Environment: Supportive Framework in the Decision-Making Process,” Concur-
rency and Computation: Practice and Experience, vol. 31, no. 10, p. e4515, 2019. https://
doi.org/10.1002/cpe.4515
[37] M. I. Ciolacu, L. Binder, P. Svasta, I. Tache, and D. Stoichescu, “Education 4.0–Jump to
Innovation with IoT in Higher Education,” in 2019 IEEE 25th International Symposium
for Design and Technology in Electronic Packaging (SIITME), 2019: IEEE, pp. 135–141.
https://doi.org/10.1109/SIITME47687.2019.8990825
[38] A. Alaidi, O. Yahya, and H. Alrikabi, “Using Modern Education Technique in Wasit Univer-
sity,” International Journal of Interactive Mobile Technologies, vol. 14, no. 6, pp. 82–94,
2020. https://doi.org/10.3991/ijim.v14i06.11539
[39] M. Pineng, “Using Articial Neural Network for System Education Eye Disease Recogni-
tion Web-Based,” in Journal of Biomimetics, Biomaterials and Biomedical Engineering,
2022, vol. 55: Trans Tech Publ, pp. 262–274. https://doi.org/10.4028/p-7z9xpt
[40] R. Ardianto, T. Rivanie, Y. Alkhali, F. S. Nugraha, and W. Gata, “Sentiment Analysis on
E-Sports for Education Curriculum using Naive Bayes and Support Vector Machine,” Jurnal
Ilmu Komputer dan Informasi, vol. 13, no. 2, pp. 109–122, 2020. https://doi.org/10.21609/
jiki.v13i2.885
[41] A. Hamoud, A. S. Hashim, and W. A. Awadh, “Predicting Student Performance in Higher
Education Institutions using Decision Tree Analysis,” International Journal of Interactive
Multimedia and Articial Intelligence, vol. 5, pp. 26–31, 2018. https://doi.org/10.9781/
ijimai.2018.02.004
[42] H. d. l. Fuente-Mella, B. Umaña-Hermosilla, M. Fonseca-Fuentes, and C. Elórtegui-
Gómez, “Multinomial Logistic Regression to Estimate the Financial Education and Finan-
cial Knowledge of University Students in Chile,” Information, vol. 12, no. 9, p. 379, 2021.
https://doi.org/10.3390/info12090379
iJET ‒ Vol. 18, No. 01, 2023
199

Paper—Enhancement of Online Education in Engineering College Based on Mobile Wireless…
9 Authors
Jaafar Q. Kadhim, Electrical Engineering Department, College of Engineering,
ALMustansiriyah University, Baghdad, Iraq.
Ibtisam A. Aljazaery, Electrical Engineering Department, College of Engineering,
University of Babylon, Bbylon, Iraq.
Haider TH. Salim ALRikabi, Electrical Engineering Department, College of
Engineering, Wasit University, Wasit, Iraq.
Article submitted 2022-09-06. Resubmitted 2022-10-26. Final acceptance 2022-10-27. Final version
published as submitted by the authors.
200
http://www.i-jet.org