Most traditional e-learning systems fail to provide the
intelligence to guide a learner according to their learning style. However,
intelligent agents can be created to perform the role of guide to a student
depending on a predetermined learning style. In view of this, the study
discusses how to design, develop and implement intelligent agents for
supporting personalized e-learning based on a predetermined learning style. The
main objective of this study was to design and implement an intelligent
e-learning system based on intelligent agents for supporting personalized
e-learning. The system, which is based on intelligent agents, provides some
intelligence and supports dynamic learning. Each learner has different levels
of achievement depending on their learning styles and gets personalized feedback/recommendations.
Three intelligent agents were developed; a learner agent, a tutor agent, and an
information agent. The learner agent, which has an AI engine, uses deep neural
networks to provide a recommendation to the learners based on their learning
styles. The tutor agent accesses what the learner has accessed and passes this
information to the learner agent which then recommends the appropriate
materials. The information agent presents the recommendations/feedback of the
learners through the Moodle user interface. The learning styles of the students
are determined by filling out a Visual, Aural, Read/Write, and Kinesthetic
(VARK) questionnaire. The three agents were developed using the Prometheus
methodology. They were also tested and integrated into Moodle Learning
Management System (LMS). This integration allows learners who are using LMS
such as Moodle to learn based on their learning style. The results indicate
that it is possible to train a learner agent using deep neural networks and
provide personalized learning to the learner based on the learning style.
Future studies need to focus on using data collected in a learning management
system to identify learner styles instead of using the VARK questionnaire.
Additionally, it is necessary to use other learning styles models, such as the
Filder-Silverman model, and the Kolb learning style model among others, to
identify learning styles and conduct an experimental study to determine their
effectiveness in personalized learning with intelligent agents.
Declarations............................................................................................... i
Dedication................................................................................................. ii
Acknowledgment.................................................................................... iii
Abstract.................................................................................................... iv
Table of Contents...................................................................................... v
List of Figures.......................................................................................... xi
List of Abbreviations.............................................................................. xii
CHAPTER ONE....................................................................................... 1
1.0 Introduction........................................................................................ 1
1.1 Background
Information..................................................................... 1
1.1.1 Components and
Architecture of the E-Learning System............ 2
1.1.2
Personalized Learning Strategies................................................. 3
1.2 Problem
Statement.............................................................................. 5
1.3 Objectives of
the study....................................................................... 6
1.3.1 Main
objective.............................................................................. 6
1.3.2 Specific
objectives........................................................................ 6
1.4 Justification......................................................................................... 6
1.5 Significance
of the study.................................................................... 6
1.6 Scope of the
study............................................................................... 7
CHAPTER TWO...................................................................................... 8
LITERATURE REVIEW......................................................................... 8
2.0 Introduction......................................................................................... 8
2.1 Intelligent
Agents.............................................................................. 10
2.2 Intelligent
Agents Architectures....................................................... 11
2.2.1 Logic-Based
architecture............................................................ 12
2.2.2 Reactive
Architecture................................................................. 12
2.2.3 Belief-Desire-Intention
(BDI) Architecture............................... 13
2.2.4 Layered
(Hybrid) Architecture................................................... 14
2.2.5 Cognitive
Architecture............................................................... 16
2.3 Methodologies
for Developing Intelligent Agents........................... 17
2.3.1 The
Prometheus Methodology................................................... 17
2.3.1.1 System
Specification Phase................................................. 17
2.3.1.2
Architectural Design Phase................................................. 18
2.3.1.3 Detailed
Design Phase......................................................... 19
2.3.2 MaSE Methodology.................................................................... 20
2.3.2.1 The
Analysis Phase.............................................................. 21
2.3.2.2 The
Design Phase................................................................ 21
2.3.3 Tropos
Methodology.................................................................. 21
2.3.3.1 Early
Requirements Phase................................................... 22
2.3.3.2 Late
Requirements Phase..................................................... 22
2.3.3.3
Architectural Design phase.................................................. 22
2.3.3.4 The
Detailed Design phase.................................................. 23
2.3.3.5 The
Implementation phase................................................... 23
2.4 AI Techniques
Applied in Intelligent Agent Systems...................... 23
2.5 Personalized
e-Learning................................................................... 25
2.5.1 Prior
Studies on Personalized e-Learning.................................. 26
2.5.2
Personalized e-Learning and Content......................................... 29
2.6 Overview of
e-Learning Systems Based on Intelligent Agents........ 31
2.6.1 Intelligent
Tutoring System........................................................ 31
2.6.2 An
Agent-Based Intelligent Tutoring System............................ 32
2.6.3
Personalized Intelligent Multi-Agent Learning System............. 34
2.7 Overview of
the Different Learning Style models........................... 34
2.8 Personalized
E-Learning and Intelligent Agents.............................. 38
2.9 Overview of
Moodle Learning Management System....................... 39
2.10 Theoretical
framework.................................................................... 42
CHAPTER THREE................................................................................ 45
RESEARCH
METHODOLOGY........................................................... 45
3.0 Introduction....................................................................................... 45
3.1 Research
Methodology..................................................................... 45
3.2 System
specification/Problem definition.......................................... 46
3.3 Architectural Design........................................................................ 46
3.4 Detailed
Design................................................................................. 47
3.5 Implementation................................................................................. 48
3.6 Testing.............................................................................................. 49
CHAPTER FOUR................................................................................... 50
RESEARCH FINDINGS
AND DISCUSSIONS................................... 50
4.0 Introduction....................................................................................... 50
4.1 Determining
the Learning Style of the Learner................................ 50
4.2 Design and
Development of the Intelligent Agents.......................... 52
4.2.1 The Learner
Agent...................................................................... 53
4.2.2 Tutor Agent................................................................................ 64
4.2.3 Information
Agent...................................................................... 65
4.3 System
Architecture.......................................................................... 66
4.4 System
Integration............................................................................ 68
4.5 Results from
the Learning management system............................... 69
4.6 Discussion of
Research Findings...................................................... 73
CHAPTER FIVE.................................................................................... 75
CONCLUSION AND
RECOMMENDATIONS................................... 75
5.0 Introduction....................................................................................... 75
5.1 Summary of
Research Findings........................................................ 75
5.2 Conclusion........................................................................................ 75
5.3
Recommendation of the study.......................................................... 76
5.4 Limitation of
the Study..................................................................... 76
5.5 Further
Research............................................................................... 77
REFERENCES....................................................................................... 78
APPENDICES........................................................................................ 85
APPENDIX I: The
VARK Questionnaire.............................................. 85
APPENDIX II:
Source Codes................................................................. 90
Table 2.1: Comparison of e-learning models
................................................................................
27
Table 2. 2: Summary of most adopted learning styles
.................................................................. 35
Table 2. 3: VARK model categories /dimensions with various
teaching strategies ..................... 37
Table 4. 1: Summary of the various intelligent agents
................................................................. 53 List
of Figures
Figure 2.1: Reactive Architecture
.................................................................................................
13
Figure 2.2: Horizontal Layer Architecture
....................................................................................
15
Figure 2.3: Vertical Layer Architecture
........................................................................................
16
Figure 2.4: The phases of the Prometheus Methodology
............................................................. 20
Figure 2.5: An example of a deep neural network consisting
of interconnected neurons ............ 24
Figure 2.6: Personalized e-learning block
....................................................................................
29
Figure 2.7: Online personalization Block
.....................................................................................
30
Figure 2.8: Offline
Personalization Block
...................................................................................
30
Figure 2.9: Main Components of Intelligent Learning System
.................................................... 33
Figure 2.10: Learning Management System Moodle
................................................................... 40
Figure 2.11: Learning Management System
.................................................................................
41
Figure 2.12: Theoretical Framework Model
.................................................................................
43
Figure 2.13:Conceptual Framework Model for the intelligent
agent-based system ..................... 44
Figure 3.1: Prometheus Methodology Phases
...............................................................................
46
Figure 3.2:Interaction diagram showing the behavior of the
system ............................................ 47
Figure 3.3: The three agents and how they interact with one
another .......................................... 48
Figure 4. 1: Machine learning process used to create the
learner agent ....................................... 54
Figure 4.2: Sample data from the JSON file
.................................................................................
55
Figure 4.3: A simple
tokenization
................................................................................................
56
Figure 4.4: A neural network consisting of 8 fully
connected neurons and two hidden layers .... 61
Figure 4.5: Results of the neural network metrics used
................................................................ 62
Figure 4.6: System
architecture
...................................................................................................
68
Figure 4.7: Notification of the learning style
................................................................................
71
Figure 4.8: Sample of the feedback/recommendation
.................................................................. 72
AI Artificial
Intelligence
|
AUML
|
|
Agent Unified Modelling
Language
|
|
|
BDI
|
|
Belief Desire-Intentions
|
|
|
HTML
|
|
Hyper Text Mark-up Language
|
|
|
ITS
|
|
Intelligent Tutoring System
|
|
|
LCMS
|
|
Learning Content Management
System
|
|
|
LMS
|
|
Learning Management System
|
|
|
MaSE
|
|
Multi-agent Software
Engineering
|
|
|
Moodle
|
|
Modular Object-Oriented Dynamic Learning
Environment
|
|
|
PDT
|
|
Prometheus Design Tool
|
|
|
PVLE
|
|
Personalized Virtual
Learning Environment
|
|
|
RMI
|
|
Remote Method Invocation
|
|
|
UML
|
|
Unified Modelling Language
|
|
|
VLE
|
|
Virtual
Learning
|
Environment
|
INTRODUCTION
1.0 Introduction
This chapter covers the following
subsections: background information of the study, statement of the problem,
objectives of the study, research questions, and scope of the study.
1.1 Background Information
Teachers and students are
increasingly turning to e-learning systems and applications as a result of
technological improvements (El Fazazi et al., 2021). Despite the fact that each
student has a unique learning style, taste, and area of interest, the
traditional learning model often offers a wealth of educational materials to
all learners (Hosni et al., 2020). There are many different ways for students
to acquire information and knowledge (Balasubramanian & Margret Anouncia,
2018). While some learners prefer theories and mathematical models to grasp,
others focus on data and algorithms, while others do better with verbal form
and spoken explanations, and others do better with drawings, diagrams, and all
other visual forms. Additionally, some students prefer to actively learn in
groups, while others prefer to learn alone (Lakkah et al., 2017). Consequently,
the outcomes of students' learning are significantly impacted by their
characteristics. According to numerous studies, giving all students the same
learning materials and teaching methods without taking into account their
varied backgrounds, past knowledge, and learning objectives results in lower
performance (Wu et al., 2018).
The teachers in a physical classroom
should be aware of the preferences and learning preferences of the students
they are teaching. They may find it very challenging to comprehend the various
students' learning styles. This is now achievable in virtual classrooms with
adaptive e-learning systems thanks to technological advancements. For instance,
employing technology for agents appears to be the primary strategy for
resolving this issue. The employment of intelligent agents enables the
development of a robust system that accommodates the demands and the learners'
interests, giving the e-learning system adaptability and intelligence (Nadrljanski
et al., 2018).
E-learning agents keep an eye on the
online learning environment and enhance collaboration, which depends on the
prior knowledge, social achievements, and learning preferences of the students.
The e-learning agents also permit the study of new learning materials, allowing
students to change the exhibited content to improve learning and teamwork
outcomes in an elearning environment (Fasihfar & Rokhsati, 2017). Personal
learning, cooperative learning, and virtual learning are the three main
e-learning methods. For personal
learning, a major interest is chosen by the individual and looked at and
evaluated through the internet and the individual asks the expert instructions
some questions of their own indirectly. Concerning cooperative learning, an
online discussion is crucial.
A learning management system (LMS)
and a learning content management system (LCMS) make up an e-learning system.
An association's learning board is taken under the direction of the learning
management system. The system serves as a turning point for many learning
resources, and this tool programs the LMS and adds new capabilities available.
Its attributes and qualities include individual guidance throughout the entire
course, including the online classes, registration management, and data
storage, concurrent management of numerous learning components, learning
resource management and their presentations, access level management, and
safety problems, saving progress, and performance management of students'
interaction and learning model systems. The LCMS is an information executives‘
framework that gives the chance to gather data in different structures and
arrangements. The system assumes control over the administration of learning
things accessible in learning storage facilities (Fasihfar & Rokhsati,
2017.)
Compared to traditional learning
environments, many e-learning platforms fall short of providing excellent
support. By enabling these settings to adapt based on the demands of the users,
smart environments can assist in finding a solution. With the use of
intelligent software agent technology, this is made possible since intelligent
software agents can decide on their own without user input (Fasihfar &
Rokhsati, 2017).
According to Dou and Ying (2012),
the absence of customized studying is one of the shortcomings of traditional
learning. E-learning has changed the
conversational imparting method for tutoring that focuses on the instructors
and puts more effort into learners‘ active learning in this way an individual
gives more consideration to it. However, numerous instigations show that
numerous e-learning systems need insight, which cannot give students direction
in their studying as per their very own skills and conditions, and thus these
systems cannot give the students personalized knowledge service. Additionally,
these traditional systems have a few issues such as little interaction, unequal
distribution of tutoring materials, and a lack of unique kinds of networks and
study groups, which causes e-learning to appear untrustworthy to students (Duo
& Ying, 2012). Along these lines, the utilization of related advances to
take care of the current issues in e-learning turns out to be progressively pressing.
Interaction and personalization are
key characteristics of e-learning systems. The personalization feature
contributes to the improvement of interactions in an e-learning system.
Personalizing an e-learning system aims at achieving customized learning
through interaction with the learners. Some of the personalization techniques
in the learning process include (Duo & Ying, 2012):
i) customizing the user interface according to
the different users such as tutors and learners ii) Customizing the study materials, for example,
mixed media courseware, homework, and other individual data that are separated
to students dependent on specific qualities of the channel rules. Tutors are
able to recommend different learning materials to various learners according to
their situations. The content of each learner is different from the other which
fully incorporates personalized learning materials.
iii) individualized learning exercises that are
diverse intelligent and customized iv) Offering personalized guidelines whereby
the system keeps the learning log of the learner which can then be analyzed to
give individualized guidelines and recommendations to the learners
v) customizing
communication that involves the use of a group collaborative learning as a mode
of learning and communication whereby close learners may choose to exchange
information
Learners who apply Information and
Communication Technology in their studying appreciate the open environment
since they are in charge of their learning and are able to make choices of
their own in the courses and the modules (Pour et al., 2017). Online educational tools have the content and
also are able to interact with the learner depending on their approaches and
level of understanding. This is possible through the use of intelligent agents.
Intelligent agents participate in a crucial role in personalizing the
e-learning environments. The agents offer the behavior of the intelligent
system and also cooperate to achieve the personalization of the e-learning
environment.
Traditional e-learning systems lack
intelligence which fails to give learners instructions in their learning
according to their learning styles(El Fazazi et al., 2021), preferences, and
interests (Hosni et al., 2020). Students have numerous approaches to learning
and acquiring knowledge thus they cannot provide learners with personalized
knowledge services (Balasubramanian & Margret Anouncia, 2018). In addition,
they don‘t provide features to support a personalized learning approach and all
students have access to the same activities and resources (Cakula & Sedleniece, 2013). While some learners do better with verbal forms and spoken
explanations, others do better with drawings, diagrams, and all other visual
forms. Additionally, some learners prefer to actively learn in groups, while
others prefer to learn alone (Lakkah et al., 2017). The instructors in the
physical classroom need to be aware of the preferences and learning preferences
of the students they are teaching. They may find it very challenging to
comprehend the various students' learning styles. This is now achievable in
virtual classrooms because of the development of intelligent e-learning
systems. For example, employing agent technology appears to be the primary
strategy for resolving this issue. The employment of intelligent agents enables
the development of a robust system that accommodates the demands and
preferences of learners. Agents give the e-learning system adaptability and
intelligence (Nadrljanski et al., 2018). In view of this, the study has
utilized intelligent agents to accomplish personalized learning by identifying
the learning style of the students using the VARK Learning style model. The agents were developed using the
Prometheus methodology whereby these agents provide the learners with
instructional resources that match their learning style.
1.3 Objectives of the study
1.3.1 Main objective
This study aims to design and
implement an intelligent system for supporting personalized elearning.
1.3.2 Specific objectives
This study also aims to achieve the following
objectives:
i) To review the literature on how
intelligent agents can support and improve
personalized e-learning ii) To design a learner agent, tutor agent,
and information agent that will assist in a personalized e-learning process
based on a given learning style iii) To develop and implement a learner
agent, tutor agent, and information agent that will assist in a personalized
e-learning process based on a given learning style iv) To integrate the
intelligent agents with an existing learning management system such as Moodle
The study was important since was
expected to offer a solution to college students with different backgrounds and
learning styles through the development of an agent-based system. The
intelligent agents will assist the students in their learning process which
aims at improving the student's performance and also support the
student-centric approach to learning.
1.5 Significance of the
study
This study was expected to be used by college
students with the aim of supporting a studentcentric learning approach as
opposed to the tutor–centric approach as well as improving their performance. The intelligent system can be used by
learners in higher learning institutions to study as per their preferred method
of learning. Through learning management
systems like Moodle, the integration enables students to learn according to their
preferred learning style. The study will also benefit the lecturers in that
they won‘t have too much involved in the monitoring of student performance
since the intelligent agents can monitor the student learning process and
recommend the student the appropriate content based on the learning styles.
Through learning management systems like Moodle, the integration enables
students to learn according to their preferred learning style.
1.6 Scope of the study
This study is meant to be used for
higher learning institutions in Kenya to support dynamic learning
(student-centric) and improve the student's performance. For demonstration
purposes, one course (C programming course) was created in Moodle learning
management system with four topics: arrays, datatypes, functions, and control
structures
Buyers has the right to create
dispute within seven (7) days of purchase for 100% refund request when
you experience issue with the file received.
Dispute can only be created when
you receive a corrupt file, a wrong file or irregularities in the table of
contents and content of the file you received.
ProjectShelve.com shall either
provide the appropriate file within 48hrs or
send refund excluding your bank transaction charges. Term and
Conditions are applied.
Buyers are expected to confirm
that the material you are paying for is available on our website
ProjectShelve.com and you have selected the right material, you have also gone
through the preliminary pages and it interests you before payment. DO NOT MAKE
BANK PAYMENT IF YOUR TOPIC IS NOT ON THE WEBSITE.
In case of payment for a
material not available on ProjectShelve.com, the management of
ProjectShelve.com has the right to keep your money until you send a topic that
is available on our website within 48 hours.
You cannot change topic after
receiving material of the topic you ordered and paid for.
Login To Comment