Conference PaperPDF Available

Automated Adaptive Mobile Learning System using the Semantic Web

Abstract and Figures

ELearning (Electronic Learning) and m-learning (Mobile Learning) systems are online learning platforms. In our research we are modeling them as a weighted directed graph where each node represents a course unit. A directed graph represents an accurate picture of course descriptions for online courses through the computer-based implementation of various educational systems. The Learning Path Graph (LPG) represents and describes the structure of domain knowledge, including the learning goals, and all other available learning paths. In this paper, we propose an adaptive m-learning system architecture and a conceptual framework that uses the Semantic Web to obtain the students' data from other educational institutions. This process will enable the educational institutions to communicate and exchange students' data, and then use this information to adjust the students' profiles and modify their learning paths. The Semantic Web will create a more personalized dynamic course for individual students according to their ability, educational level, and experience.
Content may be subject to copyright.
1
Automated Adaptive Mobile Learning System
using the Semantic WEB
Samir Hamada
Department of Computer
Science and Engineering
University of Bridgeport
Bridgeport- CT, USA
shamada@my.bridgeport.edu
Ibrahim Alkore Alshalabi
Department of Computer
Science and Engineering
University of Bridgeport
Bridgeport- CT, USA
ialkorea@my.bridgeport.edu
Khaled Elleithy
Department of Computer
Science and Engineering
University of Bridgeport
Bridgeport- CT, USA
elleithy@bridgeport.edu
Ioana A. Badara
School of Education University
of Bridgeport
Bridgeport- CT, USA
ibadara@bridgeport.edu
Abstract— ELearning (Electronic Learning) and m-
learning (Mobile Learning) systems are online
learning platforms. In our research we are modeling
them as a weighted directed graph where each node
represents a course unit. A directed graph represents
an accurate picture of course descriptions for online
courses through the computer-based implementation
of various educational systems. The Learning Path
Graph (LPG) represents and describes the structure
of domain knowledge, including the learning goals,
and all other available learning paths. In this paper,
we propose an adaptive m-learning system
architecture and a conceptual framework that uses the
Semantic Web to obtain the students’ data from other
educational institutions. This process will enable the
educational institutions to communicate and
exchange students’ data, and then use this
information to adjust the students’ profiles and
modify their learning paths. The Semantic Web will
create a more personalized dynamic course for
individual students according to their ability,
educational level, and experience.
Keywords: Adaptive Learning; dotNetRDF; Graph;
M-learning; Ontology; RDF; Semantic Web; Shortest
Path; Turtle; User Profile.
I. I
NTRODUCTION
Adaptive eLearning researchers explore and develop
adaptive techniques that provide a better educational
experience for students. Researchers offer accurate and
personalized content to students in an effective way [1]
that may allow for adjustments in course content based on
the student’s most recent performance. This technique
allows the student to skip unnecessary and/or redundant
learning activities by providing automated and
personalized support for the student [2]. Students with
different educational backgrounds and with different
learning styles are the main challenge for the eLearning
and m-learning systems. These systems provide
personalized course units to meet the educational needs
of different students.
Throughout the most recent decades, various research
has examined the possibilities of changing the
educational instruction model from the customary one-
size-fits-all instructing model to a more adaptive and
customized learning instruction model.
Most of the techniques calculate the optimal learning
path depending on the characteristics in the student’s
profile to make the course more personalized. However,
we have not seen any technique updating the profiles
dynamically using the Semantic Web to exchange the
information between educational institutions.
The student profile contains information about the
student such as first name, last name, address, course
units that have been completed, and grades of those
course units.
This model can be applied for mobile leaning and
eLearning in community colleges as well as in a typical
graduate or under graduate course. Students can benefit
from and personalize their college experience and
completing their requirements. However this model does
not apply to K-12 students as they are outside the scope
of our research.
Adaptive Learning is an educational method that aids
students in the learning process according to their needs.
In addition, Adaptive Learning assists instructors in
conveying course content to their students in a
personalized manner based on the students’ ability and
background. Furthermore, from the developers view
point Adaptive Learning is a technique using computers
and other resources to assist in producing a better learning
experience.
One of the most challenging tasks for Adaptive
Mobile Learning is to create an Adaptive Course. Several
researchers have used different techniques in order to
make the course adaptive in terms of the course content
and units. To the best of our knowledge, we have not seen
any research that attempts to make the course adaptive in
terms of previously completed materials by the students
at another educational institution by using the Semantic
Web to communicate directly with various educational
institutions’ systems to acquire the students’ profiles.
According to our proposed system, at the time of
course registration, the students complete their profile
information. If there is a claim that the student has
successfully completed a course unit at another
educational institution, our system will run a query
against the Semantic Web files which will be performed
by using The SPARQL (SPARQL Protocol and RDF
Query Language) [3], where (RDF) is the Resource
Description which “is a general-purpose language for
representing information in the Web” [4]. During our
research, we ran the query against TURTLE files (“Terse
2
RDF Triple Language, a concrete syntax for RDF” [5]) in
another website to simulate the other educational
institution, and we were able to obtain the students’
profile and grades in that course unit. In the following
paragraph we will explain our process in detail.
When students sign up and complete their profile
information during the sign-up process, they include the
completed course units from different educational
institutions. The system then will query the Semantic
Web files (TURTLE) of that institution to get the
student’s profile, verify the student’s grade and determine
if the student passed the course unit according to the
passing grades imposed by the subject matter expert of
each educational institution using our system. If there is
no result to ensure that the student has passed one
particular course unit in the past, the student will be
presented with a quiz for this course unit. If the student
successfully passes this quiz (it is a computerized quiz
provided by our system), the course unit will be marked
as completed. However, if the student does not pass the
quiz, the student must go through the course unit’s
learning materials, and then re-take the quiz until the
student successfully completes the course unit.
II. R
ELATED WORK
In 2011, Bhatia et al. [6], explains that the Semantic
Web is an augmentation of the current Web, in which data
is characterized to empower computers and individuals to
work with better coordination. This coordination is taken
into account in our study, as we plan to communicate with
various educational institutions in order to verify the
students’ claims.
In 2013, Hadi et al. [7], stated that the internet
changed the way we collect and deliver information. In
their paper, they have expressed that the methodology of
executing RDF queries against the Semantic Web
information will require an exact match between the
inquiry structure and the RDF content. They have
addressed this problem by converting RDF content into a
matrix of features and treated queries as a classification
problem. They have effectively built up a working model
framework that exhibited the appropriateness of their
methodology. This approach was taken into consideration
in our research because we use RDF queries against the
Semantic Web data (but not applied yet).
In 2013, Soualah et al. [8], stated that new technical
capacities exist in the area of learning because of the
improvements to mobile phones and wireless
technologies. They expressed that mobile learning (m-
learning) is a natural extension of eLearning. It has the
ability to make learning available on a wide scale because
of the rapid advancements in the wireless technologies
and the broad utilization of mobile devices. They also
stated that learners have different backgrounds,
objectives, and are located in different learning
environments (heterogeneity of time, learning time,
visual support, ambient noise, etc.). In summary, by
having more information about the learners, we can adjust
the learning strategies to satisfy every learner’s needs.
The approach employed by Soualah et al., consists of two
levels:
1. Semantic level aims to express semantic
characteristics of learning contents and learner
context.
2. Behavioral level provides users with only the
most relevant information.
This approach makes use of learning practices already
employed in eLearning systems, and adapts them to
mLearning. It is this idea that is fundamental to our
current work since the new technical capacities provides
a greater amount of possible tools to enhance learning.
In 2014, Grivokostopoulou et al. [9], stated that
eLearning frameworks are turning into crucial means of
education delivery. Information delivery is one of the
current work fundamentals. We would like to clarify the
eLearning term which is defined as “eLearning is learning
utilizing electronic technologies to access educational
curriculum outside of a traditional classroom. In most
cases it refers to a course, program or degree delivered
completely online.” [10].
In 2015 Walia et al. [11], stated that the Semantic Web
approach to eLearning provides relevant and meaningful
information to the learner. However, the human mind
develops its own cognitive structure based on personal
experiences and background. In this method of eLearning
the Semantic Web is clear by adding the human
conceptual representation and has a mechanism to use the
learner profile and experience. Providing relevant and
meaningful information to the learner are at the center of
our research.
As previously mentioned, various related works have
contributed to the foundation of our research. The
following papers address security issues of the Semantic
Web that are relevant to our research, since we have to
secure sensitive data.
In their research, Kagal et al. [12], 2003 concluded
that in order to secure the Semantic Web the following
two fundamental parts are required. The first part calls for
a semantic strategy that characterizes security necessities.
While the second part consists of a distributed policy
management approach. According to Kagal et al., 2003 in
distributed policy management, each entity can determine
its own particular strategy for security and privacy. It is
essential for web entities to have the capacity to clearly
express their security. In order to achieve this end goal,
they utilize a policy language according to a semantic
language to markup security information for web entities.
Furthermore, Kagal and collaborators developed two
based security frameworks that include one for
distributed environments, and one for supply chain
management.
In 2003, Thuraisingham’s paper [13], provided an
overview of the Semantic Web and discussed security
issues. Furthermore, he stated that security must apply to
all of the Semantic Web layers. Thuraisingham suggested
that the security of the Semantic Web should start at the
beginning of the project. In addition, he concluded that
there are situations in which 100% security should be
guaranteed, however he acknowledged that there are
situations that do not require 100% security.
3
At this stage we have not incorporated any security
policy because it is not in the scope of our research.
However, we intend to incorporate a security policy in a
later stage of our research. In 2015, we demonstrated that
the Learning Path Graph, which is a proficient
representation of online courses in the computer based
usage of an educational framework [14]. This adaptive
learning system is displayed as weighted directed graphs,
where each course unit is represented by a node in the
graph as shown in Figure 1. The Learning Path Graph
represents the structure of domain knowledge, learning
goals, and all available learning paths.
Figure 1. Learning Path Graph
In this study we implement an optimal adaptive
learning path algorithm utilizing learner information from
the learner's profile to enhance specific end goals. As well
as to provide suitable content sequence in a dynamic
structure for every learner [14]. This research intends to
show how to optimize an Adaptive Mobile Learning
System by using the Learning Path Graph (LPG).
Furthermore, we intend to demonstrate how to customize
the students’ profiles by using the Semantic Web in order
to provide credit to students for the course units
completed in other accredited educational institutions.
This research describes the conceptual framework of an
Adaptive Mobile Learning System and how the students’
profiles are used to adjust the learning path whereby
making the learning path more dynamic. This means that
when the student learns a course unit, there will be an
adjustment to the learning path and a new optimal path
will be generated. The interesting point in this research is
the ability to use the Semantic Web to exchange the
student’s information among the educational institutions
and to credit the students for the course unit that they have
already completed. This feature may have the potential to
boost the efficiency of adaptive learning systems and
increase the chance for the student’s success.
III. A
DAPTIVE M
-
LEARNING SYSTEM ARCHITECTURE
An Adaptive m-learning system consists of several
modules as shown in Figure 2. Typically, the System
Interface contains an Admin Interface Module (AIM), an
Instructor Interface Module (IIM) and Student Interface
Module (SIM). This interface allows administrators,
instructors and students to access our AML system.
A. System Interface.
1. Admin Interface Module (AIM)
2. Instructor Interface Module (IIM)
3. Student Interface Module (SIM)
B. Student Profile Module (SPM)
C. Learning Style Module (LSM)
D. Domain Concept Module (DCM)
E. Course Content Module (CCM)
F. Learning Path Generation Module (LPM)
G. Student Assessment Module (SAM)
H. Adaptive Engine Module (AEM)
The Adaptive Engine Module performs two tasks:
the first task is to find all the personal learning paths using
adaptive algorithms according to the student’s profile.
The second task is to retrieve the related teaching material
according to the student’s learning style.
Figure 2. Adaptive m-learning system Architecture
IV.
PROPOSED CONCEPTUAL FRAMEWORK
Ontology as a term is derived from the Greek words
onto, which means being, and the word logia, which
means written or spoken discourse. Ontology means
different things to different people. In philosophy, it
represents the study of the existence and nature of being.
In the Semantic Web, ontologies are formal definitions
or representations of vocabularies or knowledge that
allow the user to define resource classes, resource
properties, and relationships between resource class
members [15, 16].
Eisenstadt and Vincent [17] said that “An ontology is
a partial specification of a conceptual vocabulary to be
used for formulating knowledge-level theories about a
domain of discourse.” . As we can see in Figure 3 the
three parts of the RDF Triple
Figure 1- Resource Description Framework (RDF) Triple.
For example, as shown in Figure 4, the triple "(John)
(Knows) (Jane)," (John) is the subject, (Knows) is the
predicate, and (Jane) is the object.
Figure 2-Parts of the Triple.
4
Using TURTLE syntax, it can be written as shown in
Figure 5.
Figure 3 - Parts of the Triple in TURTLE format.
Advantages of using ontologies:
There are several advantages of ontologies including:
1. Publishing data using common vocabulary and
grammar.
2. Preserving data semantic description is in ontologies
3. Data is ready for inference.
4. Better visibility.
5. Extensibility.
6. Flexibility.
7. Visibility
8. Inferenceability
9. Ability to add new properties at any time without
breaking compatibility [18, 19].
Table 1 is a rough interpretation of terms used to
describe relational databases and ontologies.
T
ABLE
1-
R
ELATIONAL
D
ATABASE AND
O
NTOLOGY
[19]
Relational database Ontology
row subject
column predicate
table data literal nodes
The language that is used to query ontologies is
SPARQL (SPARQL Protocol and RDF Query
Language) which is a set of W3C standards for querying
and updating data conforming to the RDF (Resource
Description Framework) model.[15]
In Figure 6 we show the student’s properties.
Figure 6 -Student’s Properties
As we see in Figure each student has the following
properties:
ID, Given Name, Family Name, Email, Street Address,
Address Locality, Address Region, Postal Code, Address
Country, and Student Group
In
Figure
7 we have the students’ file in the TURTLE
format. We have used some vocabulary from different
schemas as follows:
@prefix d: <http://adaptivemobilelearning.com/ns/data#>
@prefix person:<http://schema.org/Person>
@prefix address: <http://schema.org/>
@prefix place: <http://schema.org/Place/>
@prefix aiiso: <http://purl.org/vocab/aiiso/schema#>
@prefix contains:<http://schema.org/hasPart>
@prefix teach: <http://linkedscience.org/teach/ns#>
@prefix completed: https://schema.org/Completed
Those are the available schemas that we were able to
map our data files to, they might not be an exact match
but that is not what our paper is studying, as our paper is
a demonstration on how to obtain the student’s results
from another educational institution using the Semantic
Web.
As shown if Figure 7 the students.ttl file.
Figure 7 - Students’ Data in TURTLE Format
We are going to use the SPARQL query to select
students in CT.
In Figure 8 we have a SPARQL query that is going to
be run against thestudents.ttl TRUTLE file.
Figure 8 - SPARQL Query for students in CT
In Table 2 we can see the result of executing the query in Figure 8
Table 2 - Result of query from Figure
Last First City State
Doe John Stratford CT
Miles Richard Bridgeport CT
Let’s add one more condition that the city is
Stratford as shown if Figure 9.
Figure 4 - Query for students in city=Stratford and state=CT
SELECT ?Last ?First ?City ?State
WHERE {
?student person:givenName ?First ;
person:familyName ?Last ;
place:address ?postalAddress .
?postalAddress
address:addressLocality ?City;
address:addressRegion ?State;
address:addressRegion ? 'CT';
address:addressLocality ? 'Stratford';
}
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
foaf:Samir foaf:Knows foaf:Ibrahim .
# filename: Students.ttl
@prefix d: <http://adaptivemobilelearning.com/ns/data#> .@prefix
address:<http://schema.org/> .
@prefix place:<http://schema.org/Place/>.
@prefix teach: <http://linkedscience.org/teach/ns#> .
@prefix person:<http://schema.org/Person> .
d:122874839
person:givenName " Richard " ;
person:familyName "Miles" ;
person:email " Richard.Miles@abc.com" ;
teach:StudentGroup "Under Graduate" ;
place:address [ a address:PostalAddress;
address:addressCountry "USA";
address:addressLocality "Bridgeport";
address:addressRegion "CT";
address:postalCode "06604";
address:streetAddress "328 Park Ave." ].
…… more records
SELECT ?Last ?First ?City ?State
WHERE {
?student person:givenName ?First ;
person:familyName ?Last ;
place:address ?postalAddress .
?postalAddress
address:addressLocality ?City;
address:addressRegion ?State;
address:addressRegion ? 'CT';
}
5
The only student in our student’s table who lives in
Stratford is John Doe as shown in table 3, and the result
of running the query confirms that.
Table 3- Result of query from Figure 4
Last First City State
Doe John Stratford CT
Implementing dotNetRDF [14, 15, 20]
We used the dotNetRDF, were dotNetRDF Project
aims to create an Open Source .Net Library using the
latest versions of the .Net Framework for providing a
powerful and easy to use API to work with RDF
(Resource Description Framework), SPARQL and the
Semantic Web. The primary goal is to provide an efficient
method to work with reasonable amounts of RDF in .Net.
Using dotNetRDF is extremely simple. Reading
TURTLE files can be done as follows. The following
snippet loads the Turtle files to an in-memory structured
Graph. In Figure 10, Loading TURTLE files to memory.
Figure 10 - Loading the TURTLE files to memory
Here IN Figure 11, is the SPARQL Query that is
going to be executed on the Graph g.
Figure 11 - A SPARQL query on the files that are loaded
in Figure
The SPARQL queries can be executed with ExecuteQuery
method as shown in Figure 12
Figure 12 - Executing the query in Figure 11
The query is going to display Last Name, First Name
and Course unit where first name equals Richard, Last
Name equals Miles, and the course unit equals
Introduction.
We were able to get the students information about the
completed course units by supplying the parameters,
firstName, lastName and course unit to the controller via
the view and obtain data regarding if the course unit was
passed by the student or not.
Then this information can be used to update the
student’s profile and then adjust the learning path to make
it more adaptive according to the following system
diagram Figure .
Figure 13- System Diagram
As we can see from Figure 13, when the student
registers and complete the questionnaire if there are
claims about successfully completing a course unit at
another educational institution. The system will then
query the TURTLE files located in that institution’s
website to verify the claim. Once the claim is verified the
course unit will be marked as completed and then the
system will check if the required course units to complete
this course are successfully completed. The system then
will mark the Course as completed otherwise the student
has to complete the course unit quiz successfully in order
to mark this course unit as completed, in case the student
does not pass the quiz, the student will be able to select
one of the available course units and go through its
materials and then re-take the quiz. Upon passing it
successfully, the course unit will be marked as completed
and then the system will check if the required course
units to complete this course were successfully
completed then the system will mark the Couse as
completed.
We have a student with the following attributes:
1. ID =122874839
2. Given Name ="Richard"
3. Family Name = "Miles"
4. Email = "richard.miles@abc.com"
5. Student Group = "Under Graduate"
//Query the data with SPARQL
Object results = g.ExecuteQuery(query);
SELECT ?First ?Last ?CourseUnit
WHERE {
?student person:givenName ?First ;
person:familyName ?Last ;
person:givenName '" + firstName + @"' ;
person:familyName '" + lastName + @"' ;
completed:Completed ?ct .
?ct aiiso:Module ? CourseUnit;
aiiso:Module '" + CourseUnit + @"' . }
using VDS.RDF;
using VDS.RDF.Parsing;
(...)
//Create a Symantic Web Graph
Graph g = new Graph();
UriLoader.Load(g, new
Uri("http://hamadafamily.com/sparql/Faculty.ttl"));
(...)
6
Postal Address:
1. Street Address "328 Park Ave.
2. Address Locality = "Bridgeport"
3. Address Region = "CT"
4. Postal Code = "06604"
5. Country = "USA"
Richard Miles has completed the following course
units:
1. Introduction
2. Arrays
The Introduction and Arrays are Parts Of course 390
which has the following attributes:
1. Study Program = "CPSC"
2. Course Title = "Programming Pact"
3. Building = "Main Campus"
4. ects “Credits” = "6"
5. Student Group = "Undergraduate"
We can also query that the grade is in a specific
acceptable range as described in The Semantic Web:
Real-World Applications from Industry book to using
RUD (University Resource Descriptor), SUD (Student
University Descriptor), RQL (RDF Query Language),
RDQL (RDF Data Query Language), SWRL (Semantic
Web Rule Language) or Buchingae and SPARQL as
shown in Figure 14, we can query the students with GPA
> 3.5 [21].
Figure 14 - Querying Students with GPA > 3.5
V.
CONCLUSION AND FUTURE DIRECTIONS
This experiment has shown that we can use the
Semantic Web with Adaptive Mobile Learning to
enhance the courses making them more dynamic. The
Semantic Web obtains the information about completed
course units which are applied to the Learning Path
Graph, and a new optimal path is generated.
Furthermore, if the student completes the target module,
the student does not have to complete the rest of the
modules. We can also prevent teaching the same course
unit for the student more than one time. Thus, the
proposed approach can significantly improve the cost
effectiveness for the students, and they can manage their
time more efficiently.
Since there is a pre-test component to each course,
we make sure that the students have the required
knowledge needed in order to complete the course units.
The presented approach is expected to improve the
performance of adaptive mobile learning and provides a
learning experience to students that is more personalized
and dynamic.
R
EFERENCES
[1] P. Sahai and M. Darbari, "Adaptive e-learning using
Granulerised Agent Framework," International Journal of
Scientific & Engineering Research, vol. 5, 2014.
[2] J. Thompson. (2014, Adaptive Learning: Types of
Adaptive Learning. Available:
http://teacherhelpguide.wikispaces.com/file/view/Adaptive
+Learning+-Types+of+Adaptive+Learning.pdf
[3] W3.org. (25 Oct. 2015). SPARQL 1.1 Protocol. Available:
http://www.w3.org/TR/sparql11-protocol/
[4] (2016). RDF Current Status Available:
https://www.w3.org/standards/techs/rdf#w3c_all
[5] (2016). Turtle - Terse RDF Triple Language. Available:
https://www.w3.org/TeamSubmission/turtle/
[6] C. S. Bhatia and S. Jain, "Semantic Web Mining: Using
Ontology Learning and Grammatical Rule Inference
Technique," in 2011 International Conference on Process
Automation, Control and Computing (PACC), 2011, pp. 1-
6.
[7] A. S. Hadi, P. Fergus, C. Dobbins, and A. M. Al-Bakry, "A
Machine Learning Algorithm for Searching Vectorised
RDF Data," in 2013 27th International Conference on
Advanced Information Networking and Applications
Workshops (WAINA), 2013, pp. 613-618.
[8] F. Soualah-Alila, F. Mendes, and C. Nicolle, "A Context-
Based Adaptation In Mobile Learning," IEEE Computer
Society Technical Committee on Learning Technology
(TCLT), vol. 15, p. 5 pages, 2013.
[9] F. Grivokostopoulou, I. Perikos, and I. Hatzilygeroudis,
"Utilizing semantic web technologies and data mining
techniques to analyze students learning and predict final
performance," in 2014 International Conference on
Teaching, Assessment and Learning (TALE), 2014, pp. 488-
494.
[10] (20 Mar. 2016). Erasmus+ - EACEA - European
Commission. Available:
https://eacea.ec.europa.eu/erasmus-plus_en
[11] A. Walia, N. Singhal, and A. K. Sharma, "A Novel E-
learning Approach to Add More Cognition to Semantic
Web," in 2015 IEEE International Conference on
Computational Intelligence & Communication Technology
(CICT), 2015, pp. 13-17.
[12] L. Kagal, T. Finin, and A. Joshi, "A policy based approach
to security for the semantic web," in International Semantic
Web Conference, 2003, pp. 402-418.
[13] B. Thuraisingham, "Security issues for the semantic Web,"
in 27th Annual International Computer Software and
Applications Conference (COMPSAC), 2003, pp. 633-638.
[14] I. A. Alshalabi, S. Hamada, and K. Elleithy, "Automated
adaptive learning using smart shortest path algorithm for
course units," in 2015 IEEE Long Island Systems,
Applications and Technology Conference (LISAT 2015),
2015, pp. 1-5.
[15] B. DuCharme, Learning Sparql: O'Reilly Media, Inc., 2013.
[16] J. H. Sofia, B. D. Sofia, A. D. José, and J. H. Leontios,
Fuzzy Logic-Based Modeling in Collaborative and Blended
Learning. Hershey, PA, USA: IGI Global, 2015.
[17] M. Eisenstadt and T. Vincent, The knowledge web:
Learning and collaborating on the net: Routledge, 2012.
[18] L. Ding, P. Kolari, Z. Ding, and S. Avancha, "Using
ontologies in the semantic web: A survey," in Ontologies,
ed: Springer, 2007, pp. 79-113.
[19] J. Gajek. (28 Oct. 2015). Ontology, Notation 3, and
SPARQL. Available:
http://www.codeproject.com/Articles/156888/Ontology-
Notation-and-SPARQL
[20] (14 Apr. 2016). dotNetRDF - Semantic Web, RDF and
SPARQL Library for C#/.Net. Available:
http://dotnetrdf.org/
[21] J. Cardoso, "Developing course management systems using
the Semantic Web," in The Semantic Web. vol. Chapter 10,
ed: Springer, 2008, pp. 169-188.
SELECT ?x,?c,?z
WHERE
(?x <http://apus.uma.pt/RUD.owl#HasGPA> ?y),
(?x <http://apus.uma.pt/RUD.owl#Studies> ?c),
(?y <http://apus.uma.pt/RUD.owl#Value> ?z)
AND ?z>3.5
7
Samir Hamada received the B.Sc. in Accounting from
Ain Shams University, Cairo, Egypt in 1989, and the
Master Degree of Computer Science from University of
Bridgeport, Connecticut-USA in 2001; in 2008 he joined
University of Bridgeport as Ph.D. Student in computer
science and engineering at the University of Bridgeport,
Connecticut-USA. Worked as an IT Manager for
Atlantica Insurance Firm formally known as Action Auto
Insurance From 2003 to Present, Samir thought the Data
Computer Communication in the Spring and Fall of
2010, He also thought the course of Pre Calculus in the
spring of 2011 and on Spring 2014 C++ and Data
Structure, and currently teaching Mobile
Communication, C++ and Data Structure. Worked in
many Web development projects for Boehringer
Ingelheim USA Corp, Publics Modem, Modem Media,
Noble Americas, Dakota, Osprey, Byte Inter Active,
Visual Concepts, Family Time, He was the web master
for Connecticut Golf Club from 2005 till 2010.He was
the only student to receive the First Info Tech scholarship
at the University of Bridgeport at the year of 2000. He
also received the General Diploma for Management
Sciences in 1993 from the Sadat Academy, Cairo –
Egypt.
Ibrahim M Alkore Alshalabi received the B.Sc. in
Computer Science from Al-Isra Private University,
Amman, Jordan in 1997, and the MCA( Master of
Computer Applications ) from Bangalore University -
India in 2007. In 2009 he joined University of Bridgeport
as Ph.D. student in computer science and engineering at
the University of Bridgeport, Connecticut-USA. From
1997 to 2004, he was Assistant Lecturer in Ma'an
Community College - Al-Balqa Applied University-
Jordan. From 2007 to 2009 he joined Al-Hussein Bin
Talal University-Jordan as assistant lecturer. Ibrahim M
Alkore Alshalabi has research interest is in the general
area of E-Learning, M-Learning, wireless
communications and networks.He actively participated
as a committee member of International Conference on
Engineering Education, instructional technology,
Assessment, and E-Learning (EIAE 10, EIAE 11).
Ibrahim M Alkore Alshalabi is a member of the
International Joint Conferences on Computer,
Information, and Systems Sciences, and Engineering
(CISSE) and Ibrahim M Alkore Alshalabi is a member
of IEEE.
Dr. Khaled Elleithy is the Associate Vice President for
Graduate Studies and Research at the University of
Bridgeport. He is a professor of Computer Science and
Engineering. He has research interests in the areas of
wireless sensor networks, mobile communications,
network security, quantum computing, and formal
approaches for design and verification. He has published
more than three hundreds research papers in international
journals and conferences in his areas of expertise.
Dr. Elleithy is the editor or co-editor for 12 books by
Springer. He is a member of technical program
committees of many international conferences as
recognition of his research qualifications. He served as a
guest editor for several International Journals. He was
the chairperson for the International Conference on
Industrial Electronics, Technology & Automation, IETA
2001, 19-21 December 2001, Cairo – Egypt. Also, he is
the General Chair of the 2005, 2006, 2007, 2008, 2009,
2010, 2011, 2012, 2013, and 2014 International Joint
Conferences on Computer, Information, and Systems
Sciences, and Engineering virtual conferences.
Dr. Joanna A. Badara holds a Ph.D. (Teacher
Preparation/Science Education) from University of
Tennessee–Knoxville and an M.Phil. (Microbiology &
Immunology) from University of Edinburgh, Scotland.
Prior to completing her doctoral work, she has worked as
a research scientist in the biomedical field for about ten
years, having been affiliated with Weill Medical College
of Cornell University and Mount Sinai School of
Medicine, in New York City. Her passionate interest in
the exploration of connections between scientists’
epistemologies and the teaching of science led her to
pursuing doctoral studies in Science Education. She has
taught a multitude of core Biology courses for
Biology/Pre-Medical undergraduates and mentored
student research projects in this field. Dr. Badara is
currently a faculty member at University of Bridgeport,
where she teaches core research courses in the doctoral
(Ed.D.) program, Science Education courses in the
Science Teacher Preparation program, and History and
Philosophy of Science courses at the undergraduate
level. She has been the recipient of several grants for
research, including a National Science Foundation grant
for conducting research on the teaching of science in
urban school districts. She has presented her work at
national and international conferences in the field of
STEM education.
... In 2015, Alshalabi, Hamada, et al. [12,13] demonstrated the Learning Path Graph (LPG) that is a good representation of online courses in a computer-based usage of an educational framework. This adaptive learning system is displayed as weighted directed graphs, where each course unit is represented by a node on the graph. ...
... Bloggs Joe Stratford CT Implementing dotNetRDF [13,14,19] The dotNetRDF project aimed to create an open source .Net library using the latest versions of the .Net framework to provide a powerful and easy-to-use API to work with RDF, SPARQL, and the Semantic Web. The primary goal is to provide an efficient method for working with reasonable amounts of RDF in .Net. ...
Article
Full-text available
In this paper, we present a conceptual framework for using the Semantic Web to get student data from other educational institutions, enabling the educational institutions to communicate and exchange student data. Educational institutions could then use this information to adjust the students' profiles and modify their learning paths. Semantic Web will create a more personalized dynamic course for each student, according to his/her ability, educational level, and experience.
... Also need to implore a machine learning approach than using the Index of Learning Style (ILS) questionnaire in capture the learners' behaviour information because the latter would not best capture the learning behaviour of a learner through a question and answer mode. [12] developed automated adaptive mobile learning system using the semantic web. The authors argued that to the best of their knowledge, there has not been any research that attempts to make the course adaptive in terms of previously completed materials by the students at another educational institution by using the Semantic Web to communicate directly with various educational institutions' systems to acquire the students' ...
... However, m-learning is the popular mobile application as it can promote anywhere and anytime learning for the learners efficiently [12,13]. Additionally, m-learning is also well known for supporting personalized learning [14,15] including this paper. ...
... From the previous e-learning research, there are three important modules [6,10], which are described as follows. ...
Conference Paper
Full-text available
The graph is a significant, considerable, and efficient representation of online courses in the computer based implementation of an educational system. E-learning and M-learning systems are modeled as weighted directed graphs where each node represents a course unit. The learning Path Graph represents and describes the structure of domain knowledge as well as the learning goals and all available learning paths. In this paper we propose an optimal adaptive learning path algorithm using learner information from the learner's profile to improve E-learning and M-learning system in order to provide suitable course content sequence in a dynamic form for each learner.
Conference Paper
Full-text available
E-learning systems are becoming a fundamental mean of education delivery. Recently, data mining techniques have been utilized by tutors and researchers to analyze students learning with the aim to get deeper sight of it and improve the quality of the educational procedures. In this paper, we present a methodology to analyze students learning and extract semantic rules that can be used to predict student's final performance in the course. Specifically, the students' performance at interim tests during the semester is analyzed and the methodology utilizes decision trees and extracts rules to make predictions regarding the student's final performance in the course. The methodology has been integrated in an educational system used to assist students in learning the Artificial Intelligence (AI) course in our university. The educational system utilizes semantic web technologies such as ontologies and semantic rules to enhance the quality of the educational content and the delivered learning activities to each student. The methodology can assists the system and the tutor to get a deeper insight of the students' performance, trace students that are underachieving or in the edge to fail the final exams and also offer proper recommendations and advises to each one and drive broader pedagogical improvements.
Conference Paper
Full-text available
The Internet has fundamentally changed the way we collect, access, and deliver information. However, this now means that finding the exact information we need is a significant problem. While search engines can find information based on the keywords we provide, using this technique alone is insufficient for rich information retrieval. Consequently, solutions, which lack the understanding of the syntax and semantics of content, find it difficult to accurately access the information we need. New approaches have been proposed that try to overcome this limitation by utilising Semantic Web and Linked Data techniques. Content is serialised using RDF, and queries executed using SPARQL. This approach requires an exact match between the query structure and the RDF content. While this is an improvement to keyword-based search, there is no support for probabilistic reasoning to show how close a query is to the content being searched. In this paper, we address this limitation by converting RDF content into a matrix of features and treat queries as a classification problem. We have successfully developed a working prototype system to demonstrate the applicability of our approach.
Article
Full-text available
Recent developments on mobile devices and wireless technologies enable new technical capabilities for the learning domain. Nowadays, learners are able to learn anywhere and at any time. The dynamic and continually changing learning setting in learner’s mobile environment gives rise to many different learning contexts. The challenge in context-aware mobile learning is to develop an approach building the best learning content according to dynamic learning situations. This paper aims to develop an adaptive system based on the semantic modeling of the learning content and the learning context. The behavioral part of this approach is made up of rules and metaheuristics to optimize the combination of pieces of learning content according to learner’s context.
Conference Paper
Full-text available
Along with developing specifications for the description of meta-data and the extraction of information for the Semantic Web, it is important to maximize security in this environment, which is fundamentally dynamic, open and devoid of many of the clues human societies have relied on for security assessment. Our research investigates the marking up of web entities with a semantic policy language and the use of distributed policy management as an alternative to traditional authentication and access control schemes. The policy language allows policies to be described in terms of deontic concepts and models speech acts, which allows the dynamic modification of existing policies, decentralized security control and less exhaustive policies. We present a security framework, based on this policy language, which addresses security issues for web resources, agents and services in the Semantic Web.
Article
E-Learning approach using semantic web provides relevant and meaningful information to the learner but human mind designs its own cognitive structure of the information which is fuzzy and uncertain. When knowledge structure of any domain is large and well connected then it is very easy to learn and acquire semantically connected knowledge. An E-Learning approach is designed where the semantic web is made more meaningful by adding human conceptual representation and reasoning mechanism to learn based upon the knowledge, profile and experience of learner.
Book
Technology has dramatically changed the way in which knowledge is shared within and outside of traditional classroom settings. The application of fuzzy logic to new forms of technology-centered education has presented new opportunities for analyzing and modeling learner behavior. Fuzzy Logic-Based Modeling in Collaborative and Blended Learning explores the application of the fuzzy set theory to educational settings in order to analyze the learning process, gauge student feedback, and enable quality learning outcomes. Focusing on educational data analysis and modeling in collaborative and blended learning environments, this publication is an essential reference source for educators, researchers, educational administrators and designers, and IT specialists. This premier reference monograph presents key research on educational data analysis and modeling through the integration of research on advanced modeling techniques, educational technologies, fuzzy concept maps, hybrid modeling, neuro-fuzzy learning management systems, and quality of interaction.
Article
Nowadays the Web has proved to be as a rich and extraordinary data source of information, where multiple domains can be accessed and mined. Mining Web data is referred as Web Mining. Some of the objectives of mining web data include finding relevant information discovering new knowledge from web personalized, web synthesis and learning about individual users. Amongst these the most common use is finding relevant information. We simply specify a set of keywords or query as a request or a reference and we get a list of pages, ranked as per similarity of query. Currently searching web face with one problem that many times outcome is not satisfactory because of irrelevance of the information. Searching the exact information from such a huge repository (1) of unstructured web data is still main area of research interest. One solution to this problem is Semantic Web. The Semantic Web is an extension of current Web in which information is given as well defined meaning, hence enabling computers and people to work with better coordination. By using the existing web semantically new semantically structure can be exploited, and then the results of web mining can be improved, thereby building semantic Web (2). Semantic Web leads the idea of Ontology learning. Ontology learning, through which the outcome leads from the web unstructured data towards the exactness. Many researchers have suggested variety of methods for ontology learning especially concerned to specific data types. In this paper we suggest the process of Ontology learning for the extraction of semantics through Grammatical Rule Extraction Technique.
Chapter
The Semantic Web is well recognized as an effective infrastructure to enhance visibility of knowledge on the Web. The core of the Semantic Web is “ontology”, which is used to explicitly represent our conceptualizations. Ontology engineering in the Semantic Web is primarily supported by languages such as RDF, RDFS and OWL. This chapter discusses the requirements of ontology in the context of the Web, compares the above three languages with existing knowledge representation formalisms, and surveys tools for managing and applying ontology. Advantages of using ontology in both knowledge-base-style and database-style applications are demonstrated using three real world applications.