Professional Documents
Culture Documents
Arunkumar Ravichandran
Chellam Srinivasan
Susan Elias
context-aware
I. INTRODUCTION
The exponential growth of computing technology and the
internet over the past few decades have paved way for the
extensive growth of e-learning systems on the web. Most of
the present day e-learning platforms like the MOOCs
(Massively open online courses) offer fixed course content
and are supported by various universities. Very less effort has
been made towards creating an open repository of learning
objects to which anyone can contribute and access. One such
initiative is the National Repository of Open Educational
c
978-1-4799-6876-3/14/$31.00 2014
IEEE
301
302
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
x1
x 2
x3
T 1
T 2
T 3
1
O
((T j )T X (i ) y (i , j ) ) 2 ( j )
2 i:r (i , j ) 1
2c
(T
( j) 2
k
(1)
k 1
T k( j ) : T k( j ) D{
[(T
) X (i ) y (i , j ) ] X k(i ) }
( j) T
i:r ( i , j ) 1
( j)
k
: T
( j)
k
D{
[(T
(for k
( j) T
) X
(i )
y
(i , j )
]X
(i )
k
OT k( j ) }
i:r ( i , j ) 1
(for k z 0 )
0)
where
(2)
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
303
( j)
( j) T
(i )
304
scnew
r
sc R
sc
(3)
2)
Learning styles / Preferences: The learning
style/preferences of each student is given by the parameter
vector of the student, the elements of which gives the degree
to which the student likes the various types of contents viz.,
mathematical, theoretical and illustrative. As shown earlier,
this parameter vector is found using gradient descent that uses
the past ratings given by that student. Thus, the ratings act as
an implicit factor in learning the learning preferences of
students.
B. Adaptive Presentation:
At each control place following a level of learning objects, the
feedback is obtained. Depending on the feedback, the contents
offered to the user varies. The different cases are explained as
follows:
a) Pre-requisite deficiency: In case the feedback obtained
from the user states that he did not possess the prerequisite
knowledge to understand the content presented, the
communicating feature of CDPN[27] is used. The prerequisite
petri net which was formed initially during authoring for the
particular level/cluster is then offered by setting the
appropriate global variable, on completion of which the
control shifts back to the original course.
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
init
{
Student_cluster();
Preq_petris_init();
For all i
{
=0;
}
}
Is_11
{
If(j=1)
Enable
Else
Disable
}
play_content
{
Show_content();
}
Is_13
{
If(j=3)
Enable
Else
Disable
}
Is_12
{
If(j=2)
Enable
Else
Disable
}
Is_22
{
If(j=2)
Enable
Else
Disable
}
Is_23
{
If(j=3)
Enable
Else
Disable
}
Is_24
{If(j=4)
Enable
Else
Disable
}
Is_21
{
If(j=1)
Enable
Else
Disable
}
Is_prev
{If( =1)
{Enable
}
Else
{disable }
}
Is_prev
{
If( =1)
Enable
Else
disable
}
Is_end()
{
If(end==1)
{
;
}
Else
Disable
;
}
Choose_content
{
If( )
{
For(j=1 to no of contents)
{
}
Content_sort();//in descending
order
J=1;
;
}
Else
{
j++;
}
}
Choose_content
{
If( )
{
For(j=1 to no of contents){
}
Content_sort();//in descending order
J=1;
;
}
Else
j++;
If(i!=1)
{if )
{
Goto_petri();
}
If( ){
i--;}
}
Get_feedback
{
if )
{
Goto_petri();
}
If( )
{
i--;
}
If(content_okay()==1&& i==n)
{
End=1;
}
}
end
{ terminate_all();
//deallocate all
memory and
initializations.
}
Goto_petri();
{ G=i;
//set global variable based on
level of course
}
Figure 2. Petri net model for a sample course with two levels of sub-topics
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
305
2 (i , j ):r (i , j ) 1
2i1k1
2j1k 1
xk(i )
[(T
xk(i ) D{
) x (i ) y (i , j ) ]T k( j ) Oxk(i ) }
( j) T
T k( j ) T k( j ) D{
[(T
) x (i ) y (i , j ) ]xk(i ) OT k( j ) } (5.b)
( j) T
i:r ( i , j ) 1
where
ns is the number of students.
nc is the number of contents.
r(i,j)=1 if student j rated content i.
y ( i , j ) is the rating given to content i by student.
(4)
306
(5.a)
j:r ( i , j ) 1
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
REFERENCES
[1] Zaiane, O.R., Building a recommender agent for e-learning
systems, Proceedings.,Proceedings of the International
Conference on Computers in Education, 2002.
[2] Khairil Imran Bin Ghauth, Nor Aniza Abdullah, Building an
E-Learning recommender system using Vector Space Model
and Good Learners average rating., Proceedings of the Ninth
IEEE International Conference on Advanced Learning
Technologies, 2009.
[3] E. Alfonseca, P. Rodrguez, and D. Prez, An approach for
automatic generation of adaptive hypermedia in education
with multilingual knowledge discovery techniques.,
Computers & Education, vol. 49, pp. 495513, 2007.
[4] C.-M. Chen, H.-M. Lee, and Y.-H. Chen, Personalised
elearning system using item response theory Computers &
Education, vol. 44, pp. 237 - 255, 2005.
[5] Dagger D., Wade V., Conlan O., Personalisation for All:
Making Adaptive Course Composition Easy., Special issue
of the Educational Technology and Society journal, IEEE
IFETS, 2005.
[6] Kayama, M., Okamoto, T., A Knowledge based navigation
system with a semantic map approach for exploratory
learning in Hyperspace.
Proceedings of International
Conference ISSEI'2000, 14 - 18 August, 2000.
[7] Leune, K., W.J. van den Heuvel, Papazoglou M.P.,
Exploring a multi-faceted framework for SOC: How to
develop secure webservice interactions?, Proceedings of the
14th international workshop on RIDE, USA, 2004, pp. 485501.
[8] Peter Brusilovsky, KnowledgeTree: a distributed architecture
for adaptive e-learning., Proceedings of the 13th international
World Wide Web conference on Alternate track papers &
posters Pages 104- 113., New York, NY, USA May 17 22, 2004.
[9] Y. Semet, E. Lutton and P. Collet, Ant colony optimisation
for E-Learning: observing the emergence of pedagogic
suggestions, Proceedings of the 2003 IEEE Swarm
Intelligence Symposium, Indianapolis, 24-26 April 2003, pp.
46-52P.
[10] Sarath Chandar, S. G. Dheeban, Deepak V, Susan Elias,
Personalized e-course composition approach using digital
pheromones in improved particle swarm optimization, in the
proceedings of the Sixth International Conference on Natural
Computation (ICNC 2010), China, pp.2677-2681. IEEE
Press., 2010.
[11] Gerhard Weber, Adaptive learning systems in the World
Wide Web, Proceedings of the seventh international
conference on User modeling[C], Banff: Springer-Verlag
New York, Inc. 1999, 371377.
[12] Elaine Rich, User Modeling via Stereotypes, Cognitive
Science, Volume 3, issue 4 (1979):329-354.
[13] Nathaniel Good, J. Ben Schafer, Joseph A. Konstan, Al
Borchers, Badrul Sarwar, Jon Herlocker, and John Riedl,
Combining Collaborative Filtering with Personal Agents for
Better Recommendations., in The Sixteenth National
Conference on Artificial Intelligence (AAAI-99), Orlando,
Florida, 1999.
[14] Gallego D., Barra E., Gordillo A., Huecas G., Enhanced
recommendations for e-Learning authoring tools based on a
proactive context-aware recommender. In the proceedings of
IEEE Frontiers in Education Conference, 2013.
[15] Voula Gkatzidou and Elaine Pearson, Exploring the
development of adaptable learning objects. A practical
approach., in the proceedings of 10th IEEE International
Conference on Advanced Learning Technologies, 2010.
[16] Boyan Bontchev and Dessislava Vassileva, Courseware
authoring for adaptive e-learning , Proceedings of the 2009
International Conference on Education Technology and
Computer, 2009.
2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE)
307