Académique Documents
Professionnel Documents
Culture Documents
PROJECT REPORT
MASTER OF TECHNOLOGY
IN
COMPUTER SCIENCE & ENGINEERING
By
MINU. M. DAS
JUNE 2010
CERTIFICATE
This is to certify that this project work entitled “Context Aware E-Learning System
with Dynamically Composable Learning Objects” is a bona fide record of work
done by Ms. Minu. M. Das, Reg. No. 1082308, in partial fulfillment of the
requirements for the Degree of Master of Technology in Computer Science and
Engineering in the Department of Computer Science, School of Engineering and
Technology of Pondicherry University.
This work has not been submitted elsewhere for the award of any other degree to the
best of our knowledge.
i
ACKNOWLEDGEMENT
I like to express my profound gratitude to all faculties and non- teaching staff of
Department of Computer Sciences, Pondicherry University for supporting me in
fulfilling the projected targets.
Last but not the least I acknowledge the blessings of my parents, which had constantly
supported me in many ways throughout development of this project. I am grateful for
the providence of the grace provided by the LORD ALMIGHTY.
- Minu. M. Das
ii
ABSTRACT
In this work, a standardization of context model for context aware E-learning has
been proposed. The design of the standardized context model requires that a learning
object should not have a static monolithic structure but be flexible enough to be
dynamically composed based on a learner‟s context. Hence, a flexible learning object
model and its representation are defined in this paper. A content management system
which stores these flexible learning object constituents and assembles them
dynamically based on a learner‟s context is also described.
iii
LIST OF FIGURES
Figures Page
No
Figure 2.1 Learnativity Content Models 21
Figure 2.2 SCORM Content Aggregation Model 22
Figure 2.3 CISCO RLO/RIO Model 23
Figure 2.4 NETg Learning Object Model 24
Figure 2.5 Hierarchical Structure of various Learning Object Content 25
Models
Figure 2.6 Learning Content Management System Components 28
Figure 4.1 Formalized way of representing standardized context model 33
Figure 4.2 Different levels of abstraction 35
Figure 4.3 Three dimensional representation of learning object chunks 37
Figure 4.4 Hierarchical representation of learning objects 37
Figure 4.5 Architecture of proposed context aware E-Learning system. 39
Figure 5.1 User interface of proposed system 41
Figure 5.2 Learner‟s context for generating learning content 41
dynamically
Figure 5.3 Dynamically composed adaptive learning object 42
Figure 5.4 Graphical representation of evaluation of existing E- 44
Learning systems against proposed E-Learning system
iv
LIST OF TABLES
Tables Page
No.
Table 2.1 List of context parameters 13
Table 4.1 Structured set of contexts 31
Table 4.2 Learning object structure based on the learner‟s preferences and 36
intentions
Table 5.1 Fulfillment of context aware requirements by the proposed system 42
v
LIST OF ABBREVIATIONS
vi
TABLE OF CONTENTS
CERTIFICATE i
ACKNOWLEDGEMENT ii
ABSTRACT iii
LIST OF FIGURES iv
LIST OF TABLES v
LIST OF ABBREVIATIONS vi
1. INTRODUCTION 1-3
1.1 E-Learning
1.2 Personalized E-Learning
1.3 Context Aware E-Learning
1.4 Problems in existing Context Aware E-Learning
1.5 Proposed System
1.6 Organization of the report
2. LITERATURE SURVEY 4- 28
4.1 Introduction
4.2 Architecture of the Proposed System
4.3 Summary
vii
5. CASE STUDY AND ANALYSIS 40- 45
5.1 Introduction
5.2 Case Study- GURUDEV
5.3 Analysis
5.4 Summary
BIBLIOGRAPHY 47- 53
PUBLICATIONS 54-55
viii
CHAPTER I
INTRODUCTION
1.1 E-LEARNING
E-Learning uses network technology to design, deliver, select, administer and extend
learning. Using the network, students can learn the contents anytime and any where.
E-Learning can be self- paced, instructor led or self study with an expert. E-Learning
is the process of delivering formal and informal learning and training activities and
events through the use of all electronic media such as Internet, intranet, extranet, CD-
ROM, video tape, TV, Cell phones, personal organizers, computer technology, etc. M
1
1.3 CONTEXT AWARE E-LEARNING
A context aware E-Learning system considers many parameters that contribute for a
learner‟s contexts. By using these context parameters, the system will give
customized information to the user. The definition of context given by ubiquitous
computing community as “Context is any information that can be used to
characterize the situation of an entity. An entity is a person, place, or object that is
considered relevant to the interaction between a user and an application, including the
user and applications themselves.”
Context aware E-Learning systems select or filter the learning resources in order to
make the E-Learning content more relevant and suitable for the learner in his/her
situation. The selection or filtering of the e-learning resources is done by considering
the learner‟s personal information, learning style preferred by him, learner‟s
situation, etc. These parameters constitute for the learner‟s context.
Existing context aware E-Learning system uses only some of the context parameters
or sub context parameter values. These systems do not capture the learner‟s context
fully since it uses only some of the context parameters. There is no standardized
context model for capturing the learner‟s context fully.
The learning objects structures in the existing context aware E-Learning systems are
monolithic and do not support to provide learning content based on the complete
context of the learner.
From the study of the existing works in context aware E-Learning, it is obvious that
different subsets of the context parameters are considered for capturing the learner‟s
context. Each of them helps to capture certain aspects of the learner‟s context. But
they are incomplete in certain aspects. Hence, there is a need to define a standardized
context model which can completely capture the learner‟s context. Also, to provide
the learning content based on a learner‟s context, a learning object have to be
available at different levels of abstraction and media types which is termed as learning
2
chunks. These learning chunks have to be composed dynamically and constitute for a
learning object to be delivered to the learner.
At present, the structure of learning objects are monolithic and do not support to
provide learning content based on the complete context of the learner. Hence, there is
a need to define the modular structure of a learning object that helps to realize a
learning object based on complete learner‟s context. Since a new learning object
structure is defined, a suitable representation for the same also has to be proposed. In
addition, a content management system for storing the learning chunks and
dynamically composing them to form a learning object based on a leaner‟s context has
to be defined.
In this project, the following have been carried out to develop a context aware E-
Learning system
3
CHAPTER 2
LITERATURE SURVEY
Context is a set of constraints that can influence the behavior of a system in a given
task (Schmidt, 2007). The most generally accepted definition in the community of
ubiquitous computing as given by (Dey, 2001) is “Context is any information that can
be used to characterize the situation of an entity. An entity is a person, place, or object
that is considered relevant to the interaction between a user and an application,
including the user and application themselves.” In (Schmidt, 2006) the situation of a
user is defined as a relevant subset of the state of the world at a given point in time
including the respective knowledge of history and expectations for the future at that
point in time. According to (Schmidt, 2005) there are two aspects of context
awareness. They are
Context-aware computing refers to a general class of mobile systems that can sense
their physical environment, i.e., their context of use, and adapt their behavior
accordingly. Three important aspects of context are:
4
The term „context-aware' can be described as a model of computing in which users
interact with many different mobile and stationary computers and classify a context-
aware systems as one that can adapt according to its location of use, the collection of
nearby people and objects, as well as the changes to those objects over time over the
course of the day.
Location
Identity
Activity
Time
In computer science it refers to the idea that computers can both sense, and react
based on their environment. Devices may have information about the circumstances
under which they are able to operate and based on rules, or an intelligent stimulus,
react accordingly. The term context-awareness in ubiquitous computing was
introduced by (Schilit, 1994). Context aware devices may also try to make
assumptions about the user's current situation. (Dey, 2001) define context as "any
information that can be used to characterize the situation of an entity."
According to (Cristiana et. al., 2007) context are used in context-aware applications to
Adapt interfaces
Discover services
5
A context adaptive system typically enables the user to maintain a certain application
(in different forms) while roaming between different wireless access technologies,
locations, devices and even simultaneously executing everyday tasks like meetings,
driving a car etc.
Interactivity: Learners can interact with experts, teachers, or peers in the form
of synchronies or asynchronous communication. Hence, the experts are more
reachable and the knowledge becomes more available.
Adaptability: Learners can get the right information at the right place with the
right way.
6
2.1.3 Context parameters in existing context aware E-Learning systems
This section gives an overview of the context parameters used in the various context-
aware E-Learning systems. The following are the various context parameters
considered.
This is described in (Carla et al., 2008; Enrico et al., 2004; Srimathi & Srivatsa; IMS,
2003; Jeongwoo et al., 2006; Jovanovic et al., 2007; Kawanish et al.,
2006;Thyagharajan & Nayak, 2007; Maria, 2009; Mingfei et al., 2007; Peng et al.,
2007; Stefan et al., 2007; Sun Microsystems , 2003; Tzone et al., 2008; Xinyou et al.,
2008; Yang , 2006a; Yevgen et al., 2009). Learner‟s personal profile contains
learner‟s personal details such as name, ID, Date of Birth, Knowledge of the learner
etc. The knowledge of the person is the prior knowledge and that is described in
(Adriana & Francisco; IMS, 2003; Jeongwoo et al., 2006; Thyagharajan & Nayak,
2007).
This is described in (Andreas & Claudia, 2004; Srimathi & Srivatsa; IMS, 2003;
Jeongwoo et al., 2006; Koun & Hsin, 2008; Mingfei et al., 2007). Level of expertise
7
is used to indicate whether the person is a beginner or that learner has some pre-
knowledge about a topic or the learner is an expert in that topic.
Learning Style
Learning Style (ADLI, 2003;Adriana & Francisco; Andreas & Claudia, 2004; Darrel,
2009; Enrico et al., 2004; Srimathi & Srivatsa; IMS, 2003; Jeongwoo et al., 2006;
Jose et al., 2008; Thyagharajan & Nayak, 2007; Peng et al., 2007; Sun Microsystems,
2003; Yuan et al., 2007)corresponds to video, audio, textual, animation media used
by the learner for learning his lessons.
Learner’s Preferences
Most of the existing systems are focusing on Learner‟s preferences (Adriana &
Francisco; Carla et al., 2008; IMS, 2003; Jeongwoo et al., 2006; Jovanovic et al.,
2007; Kawanishi et al., 2006; Thyagharajan & Nayak, 2007; Koun & Hsin, 2008;
Maria, 2009; Mianxiong et al., 2007; Mingfei et al., 2007; Stefan et al., 2007; Sun
Microsystems, 2003; Tzone et al., 2008; Xinyou et al., 2008; Yang, 2006a; Yevgen et
al., 2009). Learner‟s preferences described in these papers correspond to the
conceptual, example-oriented, case study or problem-oriented, demonstration,
simulation approaches preferred by the learner for learning the e-content.
Learner’s Intention
Learner‟s intention (Enrico et al., 2004; IMS, 2003; Thyagharajan & Nyak, 2007;
Yang, 2006a; Yang, 2006b) means in what intention the learner is coming for E-
Learning site. The learner can come for research purpose or survey purpose or
interview purpose or just to learn the concept etc.
Learner’s Situation
Learner‟s situation (Bill et al., 1994; Carla et al., 2008; Jovanovic et al., 2007;
Kawanishi et al., 2006; Koun & Hsin, 2008; Maria, 2009; Mingfei et al., 2007)
defines the situation of the learner. The learner might be driving some vehicle or
he/she might be in private place or in public place etc. The learner‟s location details
are also included in learner‟s situation.
8
Quality of Learning Service (QoLS)
QoLS (Bill et al., 1994; Carla et al., 2008) contains functional and non functional
quality requirements. The functional requirements are network bandwidth and
response time. Non- functional requirements are reliability, availability and cost.
Network
Network (Bill et al., 1994; Carla et al., 2008; Howe, 2006; Jovanovic et al., 2007;
Kawanishi et al., 2006; Mianxiong et al., 2007; Mingfei et al., 2007; Yevgen et al.,
2009; Yuan et al., 2007; Zhu, 2009) can be wired network or wireless network.
Device
The device (Bill et al., 1994; Carla et al., 2008; Howe, 2006; Jovanovic et al., 2007;
Kawanishi et al., 2006; Koun & Hsin, 2008; Maria, 2009; Mianxiong et al., 2007;
Mingfei et al., 2007; Yuan , 2007; Zhu, 2009) used by learner can be mobile, PC,
Laptop, PDA etc.
Learning Pace
Learning pace (IMS, 2003; Jovanovic et al., 2007) means the speed of learning the
subject. This is determined by conducting some test for the learner. The learner can
be a fast learner, medium learner or slow learner.
Learning State
Learning state (Bill et al., 1994; Darrel, 2009; Srimathi & Srivatsa; Jose et al., 2008;
Jovanovic et al., 2007; Thyagharajan & Nayak, 2007; Xinyou et al., 2008; Yuan et
al., 2007; Zhu, 2009) can take the following values.
„Studied‟ – if the learner has gone through each and every lesson and in test he/she
has not performed well then this value is considered.
„To Be Studied‟ – if the learner skipped some lesson then this value is considered.
„To Be Revised‟ – if the learner has not performed well in test, then this value is
considered.
9
Comprehension Level
Comprehension level (Jose et al., 2008; Thyagharajan & Nayak, 2007; Tzone et al.,
2008) means whether the person understood the e-content well, or understood
completely or understood a little, or not understood. Table 1 gives a list of context
parameters.
Personality Type
The learners are of different personality type. Some of the personality types include
the following.
Extrovert
Introvert
Sensate
Intuitive
Feeler
Thinker
Judger
Perceiver
Extrovert
60% of the populations are in extrovert personality type category. The following are
the characteristics of extrovert personalities.
Introvert
40% of the populations are in introvert personality type category. Some of the
characteristics of introvert personalities are given below.
10
Likes to watch before doing.
Prefers working alone or with one other.
Sets own standards when possible.
Likes quiet space to work.
Seems deep and hard to understand.
Idea starts from inside out.
Sensate
Intuitive
35% of the populations are from this personality type category. Intuitive people
characteristics are given below.
Feeler
From the entire population 65% of females and 45% of males are from feeler
personality category. Characteristics of these personality types are given below.
11
Focuses more on personal relationships.
Is tuned into others feelings.
Is warm and arouses enthusiasm.
Makes decisions based on his/ her heart.
Thinker
55% of males and 35% of females from the population are in this personality type
category. The characteristics of thinker personality types are given below.
Judger
45% of populations are from this category. Characteristics of judger personality type
category are given below.
Perceiver
12
Likes to keep opinions open.
Seeks more to understand than manage things.
May have trouble making up his/ her mind.
Table 2.1 gives the list of context parameters which are used by the existing systems.
13
Jeongwoo et al., 2006;
Koun & Hsin, 2008;
Mingfei et al.
14
Stefan et al., 2007;
Sun Microsystems, 2003;
Tzone et al., 2008;
Assignment
Seminar
Requirement
15
Howe, 2006;
Jovanovic et al., 2007;
Kawanishi et al., 2006;
Maria, 2009;
Mianxiong et al., 2007;
Mingfei et al., 2007;
Yuan et al., 2007
Zhu, 2009
Fast
16
Thyagharajan, 2007;
Xinyou et al., 2008;
Yuan et al., 2007
Zhu, 2009
Understood Completely
Learning Objects (LO) are modular building block of E-Learning content. Learning
objects can be defined as individual elements of learning or basic unit of training.
Each learning object is designed to teach or test a series of specific objectives. Each
learning object is a standalone entity. It does not rely on other learning object to
function and does not specifically refer to other learning objects. A learning object is
a resource, usually digital and web-based, that can be used and re-used to support
learning. Learning objects offer a new conceptualization of the learning process:
rather than the traditional several hour chunks, they provide smaller, self-contained,
re-usable units of learning. They will typically have a number of different components
that range from descriptive data to information about rights and educational level. At
their core, however, will be instructional content, practice, and assessment. A key
issue is the use of metadata. Learning object design raises issues of portability, and of
the object's relation to a broader learning management system. Learning objects
contents can be audio, video, text, animation etc. these learning objects can be a short
video or complete lesson. Learning objects can be used for the following.
17
Pose problems for students to solve
“Any entity, digital or non-digital, which can be used, re-used or referenced during
technology supported learning.” – Learning Object Metadata Working Group of the
IEEE Learning Technology Standards Committee (LTSC)
“The main idea of „learning objects‟ is to break educational content down into small
chunks that can be reused in various learning environments, in the spirit of object
oriented programming.” – David Wiley
“Learning Objects are small or large resources that can be used to provide a learning
experience. These assets can be lessons, video clips, images, or even people. The
Learning Objects can represent tiny „chunks‟ of knowledge, or they can be the whole
courses.” – Claude Ostyn, Click2Learn
The following are some of the characteristics of the learning objects and their
description.
18
Reusable – A single learning object may be used in multiple contexts for
multiple purposes.
Accessible - It refers to the capability to have been found and became
available to learners and developers anywhere.
Durable - It is not necessary to change the learning objects in the case of new
version of software.
Self Contained - Each learning objects can be taken independently.
Can be aggregated - Learning objects can be grouped to form larger
collections of contents for example different learning objects are integrated to
form the course structure.
Static Learning Objects (Carlo, 2007) are helpful in instructional settings with simple
and / or very straight forward requirements, generally similar to those in which
educators need to have full control of learning method and process. These static
learning objects are used by previous E-Learning systems. Nowadays the E-Learning
systems are using only dynamic learning objects. SLOs are self paced learning
objects. These learning objects are organized in a pre-determined order. The delivery
19
or invocation of objects is determined by time or sequence. The delivery of these
Static Learning Objects is defined by an instructional designer or teacher.
Dynamic Learning Objects (DLO) is un-paced learning objects. These objects are not
ordered, that means each learning objects are independent of the other learning
objects. The delivery or invocations of objects are triggered by events. The delivery
of learning objects is based on learner choices.
Dynamic learning objects are used when educators need to adapt to the ever changing
way of knowledge acquisition of students. Dynamic Learning Objects (Carlo, 2007)
are conceived and designed to be used within learning environments where an
educator encounters variable level of skill, experience, retention and reasoning
amongst a group of learners. Dynamic Learning Objects represents a great challenge
when adapting educational software to the true nature of human‟s learning methods.
Content models identify different kind of learning objects and their components.
Content Models provide a more precise definition of what learning objects are and
also it helps to identify learning object components and repurpose them. This content
model contains a collection of learning object. These learning object content models
groups the learning objects to form a complete course structure. Different types of
content models are described below.
20
Learnativity Content Model
The Learnativity content model (Wagner 2002) identifies the following taxonomy:
Raw Media Elements are the smallest level in this model: these elements
reside at a pure data level. Examples include a single sentence or paragraph,
illustration, animation, etc.
Information Objects are sets of raw media elements. Such objects could be
based on the information block model.
Aggregate Assemblies that deal with larger (terminal) objectives. This level
corresponds with more conventional lessons or chapters.
21
SCORM Content Aggregation Model
Assets
Content Aggregations.
Assets: Assets are an electronic representation of media, text, images, audio, web
pages or other data that can be presented in a web client. Figure 7 shows the SCORM
Content Aggregation Model.
22
CISCO RLO/RIO Model
Reusable Information Objects (RIOs) are pieces of information that are built around a
single learning objective. Each RIO is composed of three components: content items,
practice items and assessment items. A practice item is an activity that gives the
learner the ability to apply its knowledge and skills, like a case study or a practice test.
An assessment item is a question or measurable activity used to determine if the
learner has mastered the learning objective for a given RIO. The following figure
Figure 2.3 shows CISCO RLO/RIO Model.
NETg was one of the first to use the LO concept for its IT courses. It has a hierarchy
of 4 levels – course, unit, lesson and topic. A course contains independent units. A
unit contains independent lessons and a lesson contains independent topics. A topic
represents an independent learning object that contains a single learning objective and
has a corresponding activity and assessment. The following figure Figure 2.4 shows
NETg Learning Object Model.
23
Figure 2.4: NETg Learning Object Model
Figure 2.5 gives the hierarchical Structure of various Learning Object Content Model
Structure.
24
Learning Object Content Models
Raw Media
Elements
Homogeneity of the different learning object content models can be found out easily.
It is obvious that a learning object of a model can be used in another model if the
learning object is in a subset of both models. For example, a learnativity learning
object can be used in CISCO if it contains 7 ± 2 information objects, an overview,
25
summary and assessment. If the learning object contains only 4 RIOs, it is not in a
subset of both profiles and cannot be used within a CISCO context. A learning object
of CISCO fits within the NETg model if the RLO contains a single learning objective
and has a corresponding activity and assessment.
The LCMS is a complex piece of software that labels learning objects then organizes
and delivers them in infinite combinations. The core components of a LCMS are
26
are presented to learners through the interface which tracks users, provides links to
information, and handles assessment and feedback. The administrative application
manages learner information, launches courses from a catalogue, and tracks and
reports on learner progress. The authoring application provides templates that
automate storyboarding. Using these templates authors may develop an entire course
by using existing learning objects in the repository, creating new learning objects, or
using a combination of old and new objects (Brennan, et al., 2001). So an LCMS can
support the creation and management of Reusable Learning Object (RLO).
The following Figure: 2.6 depict the elements that comprise a typical LCMS. The
content is created and stored in a repository that is accessed by the learning
management system and distributed to the users (i.e., learners). The individual learner
data is also managed by the system and is accessible to the individual user. So one
begins to comprehend the integration of content, managing the content for
distribution, and managing learner data.
LCMS are based on a reusable learning object model allowing content to be reused
within or across courses or programs (Hall, 2003). To accomplish this, LCMS
manage content separately from the media in which the content will be delivered.
RLO are assembled into learning chunks or accessed as individual pieces of
information or instruction and delivered to the learner. The successful and efficient
deployment of an LCMS relies largely on effective development and use of learning
objects, which are reusable, media-independent chunks of information organized by a
metadata classification system (Ellis, 2001). LCMS were not created with the
intention of replacing LMS. LCMS and LMS can be complementary and each solves
a uniquely different challenge. LCMS are particularly suited to handling large
amounts of content for E-Learning efforts. An effective LCMS will enable an
organization to organize courseware without programming expertise.
27
Figure 2.6: Learning Content Management System Components
2.5 SUMMARY
This chapter describes various context parameters that are used in existing systems to
acquire context awareness in E-Learning and also about the learning objects, learning
content management systems that are described in the existing works.
28
CHAPTER 3
From the study of the existing works in context aware E-Learning, it is obvious that
different subsets of the context parameters are considered for capturing the learner‟s
context. Each of them helps to capture certain aspects of the learner‟s context. But
they are incomplete in certain aspects. Hence, there is a need to define a standardized
context model which can completely capture the learner‟s context. Also, to provide
the learning content based on a learner‟s context, a learning object have to be
available at different levels of abstraction and media types which is termed as learning
chunks. These learning chunks have to be composed dynamically to constitute for a
learning object to be delivered to the learner based on his current learning context.
At present, the structure of learning objects are monolithic and do not support to
provide learning content based on the complete context of the learner. Hence, there is
a need to define a modular structure of a learning object that helps to realize a learning
object based on complete learner‟s context. Since a new learning object structure is
defined, a suitable representation for the same also has to be proposed. In addition, a
content management system for storing the learning chunks and dynamically
composing them based on a leaner‟s context has to be defined.
Thus the proposed system needs the following to dynamically compose and provide
the learning object according to the learner‟s context.
29
CHAPTER 4
PROPOSED SYSTEM
4.1 INTRODUCTION
In the existing E-Learning systems, different subsets of context parameters have been
used for capturing a learner‟s context. Since the subset is not complete, it cannot help
to accommodate all the details of a user‟s context completely. Hence, it is necessary
to derive a standardized context model that helps to establish a learner‟s context
comprehensively.
The standardized context model consists of mainly four sub context parameters
which consolidates the existing systems parameters. They are the following.
Profile Context
Preference Context
Infrastructure Context
Learning Context
Profile Context
30
Preference Context
Infrastructure Context
It describes the information about learner‟s situation, network and device used by the
learner.
Learning Context
This describes the information about the learning pace, learning state and the
comprehension level of the learner.
DOB
Gender
Address
Email-id
Phone Number
Technologies Known
Knowledge Level
OS Experience
Internet Usage
Sensory
Thinkers
Judgers
31
Beginner
Level of Expertise Practitioner
Expert
Conceptual
Example-Oriented
Learner Preference Case Study
Simulation
Preference Context Static Demonstration
Research
Learner Intention Survey or Overview
Quick Reference
Basic Introduction
Project
Assignment
Seminar
Audio
Text
Animation
Slides
Public
Infrastructure Static Driving
Context Network Wired
Wireless
Device Mobile
32
PDA
Laptop
PC
Slow
Learning Pace Medium
Fast
Studied
Learning State To Be Studied
Learning Context Dynamic To Be Revised
Not Understood
Comprehension Understood a little
Level Understood Well
Understood Completely
These sub-contexts are either Static type or Dynamic type. Static contexts are
constant; it will not change in the entire E-Learning session. In the above sub-
contexts, the profile context, preference context and infrastructure contexts are static
because it will remain the same for the entire course session. Learning context is
dynamic context because it changes according to the learner‟s pace, learner‟s state
and comprehension level. Formalized way of representing the standardized context
model is given in Fig.4.1.
33
Personality Type {Extrovert, Sensory, Thinkers, Judges,}
34
Learner’s State {Studied, To Be Studied, To Be Revised}
The design of the standardized context model requires a flexible learning object
model. That is, the learning object structure should not be static. The structure of the
learning object will change according the learner‟s preferences and intentions.
This requires that the learning object is structured in terms of different levels of
abstractions as given below in Fig 4.2. That is, the same learning object is available
in the form of a concept, detailed concept, example, case study, simulation and
demonstration. Each of these corresponds to the various abstraction of the same
learning object. Every abstraction would be available in different media types. These
learning object abstractions in the various media types are called as learning object
chunks.
Concept
Detailed Concept
Example
Case Study
Simulation
Demonstration
Figure 4.2: Different levels of abstraction
When a learner whose learning preference is learning by „case study‟ approaches the
E-Learning system with the intention of preparing for interview, the different
learning object abstraction chunks chosen to constitute the learning object structure
35
and the sequencing order of these abstractions while presenting to the learner is as
shown below
Thus, for the above mentioned scenario, the learning object is structured with three
abstractions – simple concept, case study and example. This structure is dynamically
determined based on the learning preference and intention of the learner.
Formalized way of representing the learning object model for different intentions of a
learner is given in Table 4.2. This shows the different learner‟s intention and the
corresponding sequencing of the learning object abstractions for each of these
intentions.
Table 4.2: Learning object structure based on the learner’s preferences and
intentions.
36
4.1.3 Definition of Learning Object-Chunk Representation
For representing the standard context model and structured learning object model a
suitable representation technique has to be identified. Every learning chunk
corresponds to a particular domain. It is available in a particular level of abstraction
in a particular media. Thus, learning objects chunks are represented in a three-
dimensional way. X-axis represents the domain ontology to which the learning object
chunk belongs. Y-axis represents the level of abstraction of the learning object chunk
viz. concept, detailed concept, example etc. and the Z-axis represents the media in
which a learning object chunk abstraction is existing. Fig. 4.3 shows the 3
dimensional representation of learning object chunks.
Level of
Abstraction
Media
Domain Ontology
The following Fig. 4.4 shows hierarchical representation of learning object. That is, a
learning object x, is available in abstractions y1..yn and every abstraction is available
in z1.. zn media types.
z1
y1
zn
x
x
yn
37
4.1.4. Content Management Systems for Context Aware E-Learning Systems
In order to accommodate the newly designed standardized context model and learning
object content model, a content management system which can store the learning
object chunks and dynamically compose a learning object according to the current
context of the learner is required.
The content management system has to store and retrieve the learning object chunks.
During content generation, the learning object delivery module makes use of the
learning object model which is dynamically generated for the learner‟s context and
composes a learning object in terms of many zs which correspond to the various ys
that have been chosen to constitute for the structure of the learning object in a domain
x.
The advantages of the proposed system are that it generates content based on a
standardized set of context parameters. Also, since the learning object structure is
dynamically composed it can cater to learner‟s preference an intentions so that the
learner will get highly customized learning content.
Architecture of the proposed context aware e-learning system includes the following
modules.
Fig 4.5 shows the architecture of the proposed Context Aware E-Learning system.
The learner will give input through the user interface module. Through this user
interface module the learner‟s context is built. A suitable learning object model which
best suits the current context is generated dynamically. The learning object model is
38
the input to content management system which fills the structure with the required
learning object chunks and delivers it to the learner through the learning object
delivery module.
Standardized Learning
Context Object
Model Model
User
Interface Learning
Module Object
Delivery
Module
Content
Management
System
4.3 SUMMARY
This chapter describes the proposed systems and the architecture of the proposed
context aware E-Learning system.
39
CHAPTER 5
5.1 INTRODUCTION
This chapter describes about proposed context aware E-Learning system and screen
shots of proposed context aware E-Learning system. This chapter also explains the
two analyses carried out among proposed context aware E-Learning system and
existing context aware E-Learning system.
GURUDEV defines everything that is described above. Fig. 5.1 shows the user
interface of the GURUDEV. Fig.5.2 gives the learner context for generating the
appropriate learning content dynamically. In Fig. 5.2 the learner comes with an
intention of „seminar‟. The learner provides „detailed concept‟ as his learning
preference. The learner is assumed to be in „private‟ place, the media preferred by the
learner is „text‟ and the learner is using „laptop‟ and network used is wired and the
learner want to study about network topology. Then, the sequencing of abstraction of
learning object chunk will be in the following form
Finally the system dynamically composes learning objects according to the learner‟s
context and is given to the learner. That is shown in Fig. 5.3.
40
Figure 5.1: User Interface of proposed system
41
Figure 5.3: Dynamically composed adaptive learning object
5.3 ANALYSIS
Two types of analyses are carried out among proposed and existing context aware E-
Learning systems. First analysis verifies whether implemented context aware E-
Learning system, GURUDEV fulfills the requirements of the context aware E-
Learning system. Each of the stipulated parameters are fulfilled by GURUDEV and
explained in Table 5.1.
42
Background Knowledge Context
Learner‟s Interest Fulfilled Described in the Profile
Context
Learner‟s Skills Fulfilled Described in the Profile
Context
Learner‟s Requirements Fulfilled Described in Profile as
well as Infrastructure
Context
Table 5.2: Comparison of proposed system with existing context aware E-Learning
systems
43
Koun & Hsin, 2008 3
Lanzilotti et al., 2006 3
Maria, 2009 2
Mianxiong et al., 2007 2
Mingfei et al.,2007 1
Peng et al., 2007 2
Stefan et al., 2007 1
Sun Microsystems, 3
2003
Tzone et al., 2008 1
Xinyou et al., 2008 3
Yang, 2006 3
Yang et al., 2006 3
Yevgen et al., 2009 2
Yuan et al., 2007 3
Zhu, 2009 3
Proposed System 4
The following Fig. 5.4 shows the graphical representation of the evaluation. The X
coordinate represents the E-Learning systems and Y coordinates represents the Total
Value of that each system obtained. Most of these existing systems are satisfying only
3 context parameters described in the proposed context model but the proposed E-
Learning system satisfies all the 4 context parameters and is shaded in Fig. 5.4.
4.5
3.5
3
Total Score
2.5
1.5
0.5
0
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31
e-learning Systems
44
5.4 SUMMARY
This chapter gives the two types of analysis carried out among the existing and
proposed context aware E-Learning systems and also the screen shots of the proposed
context aware E-Learning system GURUDEV.
45
CHAPTER 6
A context aware E-Learning system considers many parameters that contribute for a
learner‟s learning context. By using these context parameters, an E-Learning system
will give customized information to the user. Context aware E-Learning systems
select or filter the learning resources in order to make the E-Learning content more
relevant and suitable for the learner in his/her situation. But most of the existing
context aware E-Learning systems uses only some of the context parameters namely
learner‟s preferences, learning styles, learner‟s intentions etc.
In this work a context aware E-Learning system is proposed to be developed. For this,
a standardized context model and learning object model are devised. A new content
management system (CMS) which can store the structured learning objects and
deliver highly customized content to the learner by dynamically composing the
learning objects is also developed.
In future psychological aspects and user‟s cognitive level details can be included in
the context model.
46
BIBLIOGRAPHY
Andreas S., Claudia W. (2004). User Context Aware Delivery of E-Learning Material:
Approach and Architecture. Journal of Universal Computer Science, 10(1), pp.
38-46.
Becking, D., Betermieux, S., Bomsdorf, B., Feldmann, B., Heuel, E., Langer, P.,
Schlageter, G. (2004) Didactic Profiling: Supporting the Mobile Learner.
Proceedings E-Learn 2004.
47
Carla Limongelli, Filippo Sciarrone, Marco Temperini, Giulia Vaste. (2008).
Adaptive Learning with the LS-Plan System: a Field Evaluation, IEEE
Transaction on Learning Technologies.
Chen Y.S., Kao T.C., Sheu J.P., Chiang C.Y. (2002). A Mobile Scaffolding-Aid-
Based Bird -Watching Learning System. IEEE International Workshop on
Wireless and Mobile Technologies in Education (WMTE'02), pp.15-22.
Cui, Y.; Bull, S. (2005). Context and Learner Modelling for the Mobile Foreign
Language Learner, International Journal of Educational Technology and Applied
Linguistics, 33(2), pp. 353-367.
Curtis M., Luchini K., Bobrowsky W., Quintana C., Soloway E. (2002). Handheld
Use in K-12: A Descriptive Account, IEEE International Workshop on Wireless
and Mobile Technologies in Education (WMTE'02), pp.23-30.
Cristiana B., Carlo A., Elisa Q., Fabio A., Letizia T. (2007). A data-oriented survey of
context models, ACM SIGMOD Record. 36(4), pp 19-26.
48
Enrico Rukzio, George N. Prezerakos, Giovanni Cortese, Eleftherios Koutsoloukas,
Sofia Kapellaki. (2004). Context for Simplicity: A Basis for Context-aware
Systems Based on the 3GPP Generic User Profile. International Journal of
Computational Intelligence, 1(1), pp. 1-12.
IMS Global Learning Consortium. (2003). IMS Abstract Framework: White paper.
Jeongwoo Ko, Fumihiko Murase, Teruko Mitamura, Eric Nyberg, Masahiko Tateishi,
Ichiro Akahori. (2006). Context-Aware Dialog Strategies for Multimodal Mobile
Dialog Systems, Journal on AAAI.
Jose Manuel Marquez, Juan Antonio Ortega, Luis Gonzalez-Abril, Francisco Velasco.
(2008). Creating adaptive learning paths using Ant Colony Optimization and
Bayesian Networks. IEEE International Joint Conference on Neural Networks
(IJCNN 2008), pp. 3834-3839.
Jovanovic, J., Gasevic, D., Knight, C., Richards, G. (2007). Ontologies for Effective
Use of Context in e-Learning Settings. Educational Technology & Society, 10(3),
pp. 47-59.
49
K.K. Thyagharajan, Ratnamanjari Nayak. (2007). Adaptive Content Creation for
Personalized e-Learning Using Web Services. Journal of Applied Sciences
Research, 3(9), pp. 828-836.
Koun-Tem Sun, Hsin-Te Chan. (2008). The Study of Using Sure Stream to Construct
Ubiquitous Learning Environment, 2008 IEEE International Conference on
Sensor Networks, Ubiquitous, and Trustworthy Computing, pp. 534-548.
Lanzilotti, R., Ardito, C., & Costabile, M. F., De Angeli, A. (2006). eLSE
Methodology: a Systematic Approach to the eLearning Systems Evaluation.
Educational Technology & Society. 9(4), pp. 42-53.
Maria Zajac, (2009). Using Learning Styles to Personalize Online Learning, Journal
on Campus- Wide Information System. 26(3), pp.256-265.
Mianxiong Dong, Kaoru Ota, Zixue Cheng, Guojun Wang. (2007). A Support Method
for Improving Learner‟s Learning Habit Using Behavior Analysis in a Ubiquitous
Environment, IEEE 2007 International Conference on Parallel Processing
Workshops (ICPPW 2007), pp. 67-72.
Mike A., Rupert C., Steve H., Joe N., Pete S., Andy W., Andy H. (2000).
Implementing a Sentient Computing System, Philosophical Transactions, Royal
Society London. 358, pp. 2349-2358.
Mingfei Wang, Linlin Ci, Ping Zhan, Yongjun Xu. (2007). Applying Wireless Sensor
Networks to Context-Awareness in Ubiquitous Learning, IEEE Third
International Conference on Natural Computation (ICNC 2007), 5, pp. 791-795.
Peng Chen, Anbo Meng, Chunhua Zhao. (2007). Constructing Adaptive Individual
Learning Environment Based on Multi- Agent System. IEEE International
Conference on Computational Intelligence and Security Workshop (CISW 2007),
pp. 374-377.
50
Ogata H., Yano Y. (2004). Context-Aware Support for Computer Supported
Ubiquitous Learning. IEEE International Workshop on Wireless and Mobile
Technologies in Education (IEEE WMTE2004), pp.27-34.
51
Thyagharajan K.K, Ratnamanjari N. (2007). Adaptive Content Creation for
Personalized e-Learning Using Web Services. Journal of Applied Sciences
Research, 3(9), pp. 828-836.
Tzone-I. Wang, Kun-Te Wang, Yueh-Min Huang. (2008). Using a style-based ant
colony system for adaptive learning. Elsevier Journal on Expert System with
Application, 34(4), pp. 244-246.
Yang S. J. H, Irene Y.L. Chen. (2006). Providing Context Aware Learning Services to
Learners with Portable Devices. In proceedings of 2006 IEEE International
Conference on Advanced Learning Technologies (ICALT ‘06), pp. 840-842.
Yang, S. J. H., Chen, I., & Shao, N. (2004). Ontological Enabled Annotations and
Knowledge Management for Collaborative Learning in Virtual Learning
Community. Educational Technology and Society, 7 (4), pp. 70-81.
Yang, S. J. H., Lan, B. C. W., Wu, B. J. D., & Chang, A. C. N. (2005). Context
Aware Service Oriented Architecture for Web Based Learning. International
Journal of Advance learning Technology, 2(4).
Yang. S. J. H. (2006). Context Aware Ubiquitous Learning Environment for Peer- to-
Peer Collaborative Learning. Educational Technology and Society, 9(1), pp. 188-
201.
52
Yevgen B., Hamidreza Baghi, Igor Keleberda, Michael Fleming. (2009). An
adjustable personalization of search and delivery of learning objects to learners,
Elsevier Journal on Expert System with Application, 36(5), pp. 9113-9120.
Yuan Fan Zhan, Laurence Capus, Nicole Tourigny. (2007). A Learner Model for
Learning- by- Example Context. Eighth ACIS International Conference on
Software Engineering, Artificial Intelligence, Networking, and
Parallel/Distributed Computing, pp. 778-785.
53
PUBLICATIONS
JOURNALS
2. Minu. M. Das, Dr. T. Chithralekha, Dr. S. Siva Sathya. “Static Context Model
for Context Aware E-Learning”. International Journal of Engineering Science
and Technology (IJEST), 2010, Vol. 2, No. 6, pp. 2337-2346.
3. Manju Bhaskar, Minu. M. Das, Dr. T. Chithralekha, Dr. S. Siva Sathya. “Genetic
Algorithm Based Adaptive Learning Scheme Generation For Context Aware
E- Learning”. International Journal on Computer Science and Engineering
(IJCSE), Vol. 2, No. 4, 2010.
CONFERENCES
54
2. Minu.M.Das, Dr. T. Chithralekha, Dr. S. Siva Sathya, “Learning Objects in E-
Learning”. Proceedings of the National Conference on Emerging Trends in
Computing (NCETIC), March 24-26, Government Engineering College, Thrissur,
Kerala, India.
55
56