Conference PaperPDF Available

Online Learning -CBR Approach

Authors:
Mahadev Patil at Bharati Vidyapeeth's Abhijit Kadam Institute of Management and Social Sciences
Mahadev Patil
  • Bharati Vidyapeeth's Abhijit Kadam Institute of Management and Social Sciences
Pallavi Jamsandekar at Bharati Vidyapeeth Deemed University
Pallavi Jamsandekar
Download full-text PDF
Read full-text
Download citation

Abstract

Online learning is becoming very popular where internet provides wide variety of tools, aids that provides the learning material (notes, question-answers, assignments, problems). An internet is a unique platform to connect learners with educational resources. Many researchers have focused on developing e-learning tools to facilitate the students. But, they neglect the learning behavior of the students, their difficulty levels and the essential things required for their courses. Therefore, in our system we focus the CBR approach in students learning. In our proposed system we can generate the appropriate course material as per the work background of the students through online learning.
Content uploaded by Mahadev Patil
Author content
All content in this area was uploaded by Mahadev Patil on Aug 16, 2022
Content may be subject to copyright.
2nd National Conference on Computer, Communication & Information Technology
Feb. 15-16, 2013
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Sinhgad Institute of Computer Sciences (MCA), Pandharpur (MS), India 177
Online Learning – CBR Approach
Dr. P. P. Jamsandekar1 & M. K. Patil2
Abstract: Online learning is becoming very popular where
internet provides wide variety of tools, aids that provides
the learning material (notes, question – answers,
assignments, problems). An internet is a unique platform to
connect learners with educational resources. Many
researchers have focused on developing e-learning tools to
facilitate the students. But, they neglect the learning
behavior of the students, their difficulty levels and the
essential things required for their courses. Therefore, in our
system we focus the CBR approach in students learning. In
our proposed system we can generate the appropriate
course material as per the work background of the students
through online learning.
Keywords: CBR, e-learning
1. INTRODUCTION
The major challenges in teaching are to improve the
instructional productivity and quality learning. A case
based reasoning (CBR) system can be seen as a special
type of knowledge based system2. Case based systems
deal with cases or episodes which represent instances of
concepts or their generic form [3].
FIG. 1: CBR CYCLE [1]
---------------------------------------------------------------------------
1. Professor, Bharati Vidyapeeth Deemed University,
Institute of Management of Rural Development, Sangli
pallavi.jamsandekar@yahoo.com
2. Assistant Professor, Bharati Vidyapeeth Deemed
University, Abhijit Kadam Institute of Management
and Social Sciences, Solapur
patilmahadevk@gmail.com
In general, CBR cycle can be described by the following
four processes [2]:
- Retrieve the most similar case or cases
- Reuse the information and knowledge in that case to
solve the problem
- Revise the proposed solution
- Retain the parts of this experience likely to be
useful for future problem solving.
Online learning where students have different
behavior, culture. In this paper, we conceptualize a
system to support students and their learning behavior.
We kept the profile of the students in a Case Base. The
system maintains the behavior of students, the pattern
through which information retrieved. The Case Base
holds knowledge base, learning style, and interesting
field. The system facilitates the notes, points, learning
content and instructional material [5].
2. PROPOSED CBR SYSTEM
The proposed system is based on finding the different
cases, the learning patterns of the students. It preserves
past cases in Case Base. A system has basic three
components Student, Teaching Aid and Course. All these
components have an interface through which students
can post the cases, problems, requirements5.
FIG. 2: ONLINE LEARNING SYSTEM
The following characteristics that fulfill the CBR
approach for student modeling:
1) In the learning environment students, teaching aids
and corresponding study material are kept across
the network.
2) The student’s behavior, background knowledge, and
skills are kept in Student Case Base of CBR System.
2nd National Conference on Computer, Communication & Information Technology
Feb. 15-16, 2013
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Sinhgad Institute of Computer Sciences (MCA), Pandharpur (MS), India 178
3) Students generally attempt to register in various
courses at the same time. The system highlights the
common features and categorizes the same.
3. STUDENT MODULE
The process of student modeling is shown in figure
below. The following activities take place during the
student modeling when the student interacts with the
system.
FIG. 3: CBR BASED MODEL [4]
Inputting a new case
A new case means the learner unable to get the
desired solution. The new case may be processed and
further treatment, assessment arranged by the CBR
system. The reasoning mechanism of CBR will search
for the most similar case in order to support the
activities.
Analyze an inquiry
It is very difficult to analyze the cases by the learners.
We maintain an index, for case evaluation, so that is easy
to analyze the case and provide the desired solution.
Case retrieval
The case-based reasoning system saves a lot of data
for reference. It holds the cases in Case Base.
It locates the solution for the most similar case by
comparing the similarities. It will provide an
approximate appropriate result to the learners. We are
using the case retrieval methods such as inductive
learning, knowledge inference, nearest neighbor. It is
easy to get the instruction manuals, notes to the learners
by effectively applying the case retrieval technique.
Case adaptation and reuse
It will be possible that, we need to modify the
retrieved case. We need to use the different adaption
methods in order to solve the problems of new inputted
case by the learner. We are applying exact adaptation,
interpolation method or adaptation rules.
Revision of a case
When the solutions of the similar cases that were
picked out are not suitable for the new case, revisions
can be used. A new solution will be generated and it is
treated as a final one.
Retaining a case
Save the case into case base to enhance its
completeness and to consolidate the self-learning
mechanism of the system.
4. ARCHITECTURAL VIEW
The architecture focuses on indexing as the key to
reuse of what is learned from experience. In addition to
having experiences, students should reflect on and assess
those experiences to extract both what might be learned
from them and the circumstances in which those lessons
might be appropriately applied.
The CBR cycle through which an application of what
they are learning, interpretation of feedback, and
explanation and revision of conceptions several times.
Online learning by a CBR approach focuses on the
role previous experience plays in reason- ing suggests
that learners should be encouraged to reuse their own
previous experiences. It also suggests that they might be
helped along to solve more complex problems than they
could by themselves by having access to the cases
(experiences of others).
2nd National Conference on Computer, Communication & Information Technology
Feb. 15-16, 2013
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Sinhgad Institute of Computer Sciences (MCA), Pandharpur (MS), India 179
The architectural module has divided into basic
components Student Module, Expert Module and
Teaching & Course Module and has a basic interface
with support of Case Base and internet e-resources.
The interfaces of student module, is an interface
between the course & teaching aid in support of expert
module. The expert module maintains the record of
student profile while operating the system. The expert
module identifies the cases raised by the learner and their
requirements.
The course system manages the course material as
per student’s requirement. The teaching aid decides the
topic or lessons, to be supplied to the students according
to student’s background. The student module keeps the
record in case base for future reference and manages the
student performances and course material accordingly.
Following are the basic operations that can be carried
out while interacting with CBR System.
Student Module: To analyze the students learning
behavior, pattern, the problems given to the system
Expert Module: To retrieve the desired solution from the
case base
Course: To store and process, categories the problem
domain in a course
Teaching AID: The information content, study material
The student gets interacted with the CBR System via
an interface. The student post their queries, cases to the
CBR system through system module. The cases is
compared with the existing available cases. These past
cases are stored in case base. If the new case appeared,
then it will be handled by the CBR Cycle. The student
retrieves the desired solution via Course, Teaching aid
via internet. The educational material in hypermedia
form in a Web-based educational system makes learning
a task-driven process such as E-Resources, Tutoring tool
and teaching agents.
5. CONCLUSION
CBR approach emphasizes the need for students
actually to carry out and test their ideas, not just think
about them.
CBR-based online learning is for personalized
knowledge database and self assessment analysis system.
The proposed learning system considers the subject
difficulty level to a successive level to enhance the
students leaning behavior.
This paper makes the basic contribution to generate
appropriate course materials to learners based on
individual learner requirements, and help them to learn
more effectively in a Web-based environment.
6. REFERENCES
[1] Janet L. Kolodner, Jakita N. Owensby, and Mark Guzdial (2008).
Case Based Learning Aids. New York Springer. 32, pp. 829 – 861
[2] Rajendra Akerkar (2012). Introduction to AI, PHI Eastern
Economy Edition.
[3] Campbell, J M and Smith S D (2006). CBR research using the
‘Think’, ‘Plan’, ‘Do’ classification method. Association of
Researchers in Construction Management. pp. 177-186.
[4] Mu-JungHuang, Hwa-ShanHuang and Mu-YenChen (2006).
Constructing a personalized e-learning system based on genetic
algorithm and case-based reasoning approach. Ecpert System
with Applications. Elsevier Publication pp.1-9.
[5] O. P. Rishi, Rekha Govil, and Madhavi Sinha (2007). Distributed
Case Based Reasoning for Intelligent Tutoring System: An Agent
Based Student Modeling Paradigm. World Academy of Science
& Engineering pp.273 – 276
AI-VT: An Example of CBR that Generates a Variety of Solutions to the Same Problem: 26th International Conference, ICCBR 2018, Stockholm, Sweden, July 9-12, 2018, Proceedings
Chapter
  • Jul 2018
  • Lect Notes Comput Sci
AI-Virtual Trainer (AI-VT) is an intelligent tutoring system based on case-based reasoning. AI-VT has been designed to generate personalised, varied, and consistent training sessions for learners. The AI-VT training sessions propose different exercises in regard to a capacity associated with sub-capacities. For example, in the field of training for algorithms, a capacity could be “Use a control structure alternative” and an associated sub-capacity could be “Write a boolean condition”. AI-VT can elaborate a personalised list of exercises for each learner. One of the main requirements and challenges studied in this work is its ability to propose varied training sessions to the same learner for many weeks, which constitutes the challenge studied in our work. Indeed, if the same set of exercises is proposed time after time to learners, they will stop paying attention and lose motivation. Thus, even if the generation of training sessions is based on analogy and must integrate the repetition of some exercises, it also must introduce some diversity and AI-VT must deal with this diversity. In this paper, we have highlighted the fact that the retaining (or capitalisation) phase of CBR is of the utmost importance for diversity, and we have also highlighted that the equilibrium between repetition and variety depends on the abilities learned. This balance has an important impact on the retaining phase of AI-VT.
View
Theory and Practice of Case-Based Learning Aids
Article
Full-text available
Case-based reasoning, inspired by people, was developed as a model for creating intelligent systems – systems that could reason by reference to their previous experiences. Such systems, we said, had the potential to behave more like real experts than could traditional expert systems. Reasoning based on experience would allow them to be more flexible and less brittle than rule-based systems, and, with learning from experience built into their architectures, they would become more capable over time (Kolodner & Simpson, 1989). Many experimental automated case-based reasoners have been created (see the lists, e.g., in Kolodner, 1993) and, indeed, CBR has proven to be quite a useful technology (refs). More interesting to us, however, are the implications case-based reasoning holds as a model of cognition – implications about what it means to be a learner and implications about learning and education. Case-based reasoning (CBR), as a cognitive model, values the concrete over the abstract (Kolodner, 1993). While most traditional theories of cognition emphasize how general-purpose abstract operators are formed and applied, case-based reasoning makes concrete cases, representing experience, primary. CBR suggests that we think in terms of cases — interpretations of our experiences that we apply to new situations. To find the milk in a supermarket I've never been in, for example, I walk around the perimeter of the store until I reach the dairy section. Why? Because the dairy section of the supermarket I usually shop in is around its perimeter. When I throw a ball in the air, I expect it to come down because that's what I've always seen before. When I do strategic planning for my organization, I call on previous situations to suggest strategies and tactics and to warn of pitfalls. When I plan a dinner party, I consult menus I've served before as part of my planning; I may even serve the same meal I served another time if it worked well and different guests are invited this time. Case-based reasoning also helps us understand how we develop expertise and how an expert uses his/her own experiences and those of others to reason and learn. Consider, for example, an architect designing an office building. She calls on her experiences and those of others who have designed buildings that address similar needs to make decisions about how to proceed. She knows that many modern office buildings have atriums. Should this new building have an atrium? To answer that, she first looks at the reasons for including atriums in those buildings. In some, it was to provide light to inside offices; in others to provide a friendly informal space to meet. Are those goals in the new design? They are, but she wonders whether the noise of a central meeting space might be problematic. She examines those buildings again, looking at the effects of the atriums on use of its offices. Indeed, some did cause too much noise, but others were quite successful. Why did some succeed and some fail? The architect looks to see the reasons for failures. Will they be present in the new building? If so, is there a way to avoid the failure by doing it another way (perhaps suggested by one of the successful atria) , or should an atrium not be used? As a theory of learning, case-based reasoning has much in common with constructivism: both claim that an individual builds his/her knowledge for him/herself from experience. Both 2 see learning as active; the learner plays an intentional role in deciding what to learn and in going about the activities of learning. Case-based reasoning also has much in common with constructionism (an approach to education): both approaches value learning from concrete experiences and the interpretations of the individual. But case-based reasoning goes further than both constructivism and constructionism; it defines a model of cognition (including processes and knowledge structures) that can be turned to for advice and predictions and that can be simulated on a computer as a test of ideas. Like constructivism and constructionism, case-based reasoning has lessons for the teacher and for the designer of technological learning aids. Case-based reasoning makes suggestions about how to orchestrate and facilitate students' experiences so that they can draw productive lessons from their experiences and makes suggestions about how to encourage transfer so that lessons learned might be applied in more than one situation. It suggests help students might need so that they can turn their experiences into accessible and easily reusable cases in their memories. In this chapter, we first review case-based reasoning as a model of cognition and describe its critical features. Then, we present its implications for supporting learning with and without technology. Finally, we review some examples from the research community of applying the lessons of case-based reasoning to promote learning.
View
Distributed Case Based Reasoning for Intelligent Tutoring System: An Agent Based Student Modeling Paradigm
Article
Full-text available
  • Jan 2007
Online learning with Intelligent Tutoring System (ITS) is becoming very popular where the system models the student's learning behavior and presents to the student the learning material (content, questions-answers, assignments) accordingly. In today's distributed computing environment, the tutoring system can take advantage of networking to utilize the model for a student for students from other similar groups. In the present paper we present a methodology where using Case Based Reasoning (CBR), ITS provides student modeling for online learning in a distributed environment with the help of agents. The paper describes the approach, the architecture, and the agent characteristics for such system. This concept can be deployed to develop ITS where the tutor can author and the students can learn locally whereas the ITS can model the students' learning globally in a distributed environment. The advantage of such an approach is that both the learning material (domain knowledge) and student model can be globally distributed thus enhancing the efficiency of ITS with reducing the bandwidth requirement and complexity of the system. Keywords—CBR, ITS, Student Modeling, Distributed System, Intelligent Agent.
View
CBR research using the 'think', 'plan', 'do' classification method
Article
  • Oct 2006
Recent skill shortages in the UK Construction Industry have undoubtedly lead to a loss of tacit knowledge and experience. In addition, clients' need for greater value and better construction services results in companies striving for competitive advantage by becoming more efficient in the way they manage their knowledge systems and resources. Although Case-based reasoning (CBR) originated in artificial intelligence research, it has transcended barriers between technology and methodology to become applicable in many industrial and research fields. Research and applications have shown CBR can emulate human reasoning and decision making processes and as such a wide variety of construction tasks have been used in case studies. Furthermore, CBR applications may cover many areas of a project life cycle, but the extent of coverage was generally unknown. By mapping an innovative three-stage classification method to the accepted model of a project life cycle, past CBR research can be grouped and inspected. This 'think', 'plan, and 'do' classification method has shown imbalance of CBR research applications within the construction industry with little aid to those involved in the 'doing' phases. The 'think', 'plan', 'do' classification method has identified potential areas where the further application of CBR may prove useful within infrastructure management, and in particular within an educational role for safety and risk management.
View
Constructing a personalized e-learning system based on genetic algorithm and case-based reasoning approach
Article
  • Oct 2007
  • EXPERT SYST APPL
The Internet and the World Wide Web in particular provide a unique platform to connect learners with educational resources. Educational material in hypermedia form in a Web-based educational system makes learning a task-driven process. It motivates learners to explore alternative navigational paths through the domain knowledge and from different resources around the globe. Consequently, many researchers have focused on developing e-learning systems with personalized learning mechanisms to assist on-line Web-based learning and to adaptively provide learning paths. However, although most personalized systems consider learner preferences, interests and browsing behaviors when providing personalized curriculum sequencing services, these systems usually neglect to consider whether learner ability and the difficulty level of the recommended curriculums are matched to each other.Therefore, our proposed approach is based on the evolvement technique through computerized adaptive testing (CAT). Then the genetic algorithm (GA) and case-based reasoning (CBR) are employed to construct an optimal learning path for each learner. This paper makes three critical contributions: (1) it presents a genetic-based curriculum sequencing approach that will generate a personalized curriculum sequencing; (2) it illustrates the case-based reasoning to develop a summative examination or assessment analysis; and (3) it uses empirical research to indicate that the proposed approach can generate the appropriate course materials for learners, based on individual learner requirements, to help them to learn more effectively in a Web-based environment.
View