Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Kalvi: An Adaptive Tamil m-Learning System
1. KALVI: An Adaptive Tamil
m-Learning System
Keshava Rangarajan
Chief Architect, Landmark (Halliburton) Corporation
Jayaradha Natarajan
Software consultant, TIBCO
Arivoli Tirouvingadame
Principal Member of Technical Staff, Oracle America, Inc.
2. Acknowledgements
The proposed Kalvi Learning Management System is
based on the Sakai project. A free trial hosted instance of
the Sakai CLE from Longsight
(https://trysakai.longsight.com/portal) was used during
this research. The authors would like to acknowledge the
contributions of all the people involved in Sakai project
and Longsight, and their numerous colleagues.
4. What is Learning Management System ?
•Wikipedia definition: A Learning Management System (LMS) is a software
application for the administration, documentation, tracking, reporting and
delivery of education courses or training programs.
Delivery of online
materials and
Tracking and
Registration for courses
reporting of
instructor lead e-
learning
learning courses
LMS
5. What are the characteristics of LMS ?
•Systems are web-based to facilitate “ anytime, any place,
any pace” access to training content and administration
•A robust LMS should be able to do the following:
•centralize and automate administration
•use self-service and self-guided services
•assemble and deliver learning content rapidly
•consolidate training initiatives on a scalable web-based platform
•support portability and standards Delivery of online
materials and
Tracking and
Registration for
•personalize content and enable instructor lead e-
courses
reporting of
learning
knowledge reuse learning courses
•deliver online training and webinars
LMS
6. What is Content Management System ?
•Wikipedia definition: A content management system (CMS) is a computer
program that allows publishing, editing and modifying content as well as
maintenance from a central interface.
கல்விக்
களஞசியம்
(CMS)
7. What are the characteristics of CMS ?
•CMS systems provide procedures to manage workflow in a collaborative
environment. These procedures can be manual steps or an automated
cascade.
•CMS platforms allow users to centralize data editing, publishing and
modification on a single back-end interface.
கல்விக்
களஞசியம்
(CMS)
8. Anatomy of an academic course …
Course
Module 1 Module 2 Module 3
(பகுதி) (பகுதி) (பகுதி)
11. A course is nothing but a directed cyclic graph
Reinforcement Reinforcement Reinforcement
learning learning learning
Learner’s Learner’s
Modules/ transition transition
Modules/ Modules/
Concepts/ Concepts/ Concepts/
Quizzes Quizzes Quizzes
12. What are the types of Academic courses ?
ACADEMIC
COURSE
Non-
adaptive
Adaptive
13. Non-adaptive course
Module n
Module 2
Module 1
•Connecting links/arcs are static, pre-determined globally and follow a pre-
determined path
14. Adaptive course
• Links are initially configured based on the information (descriptive attributes)
available about the learner.
• Additionally, there are many possible link flow paths.
• These paths are conditional, i.e. based on an ongoing evaluation/scoring of the
learner’s progress through the topics over a given period.
• Additional nodes/topics may be brought in dynamically based on a dynamic
evaluation of the learner’s level of knowledge as she/he progresses through the
course.
• The topics introduced are driven by analytical insight gained from community use.
16. What are the existing problems in
Tamil LMS ?
• Very few modern Learning Management Systems for education via Tamil language
especially ones that deliver content typically taught in other languages (like English)
• Even if they do exist, these LMS systems deliver content in a static fashion; they do
not take into account the user’s preferences, level of skill, learning goals and other
factors explicitly into account and use this as the basis for learning content delivery
and learn from user activity
18. Role of Data mining and Machine
Learning in LMS
• Learning management systems (LMS) and Learning Content management systems
(LCMS) deal with volumes of data.
• Users consuming the course material leave a trail of data while performing their
activities.
• These data can and needs to be mined to extract insight into learning patterns,
learner groupings, Topic classifications (eg: easy, difficult, etc.).
• Machine learning techniques like Dynamic Regression, Support Vector Machines
(SVM), Neural Net engines, etc. can be employed to mine the data to extract insight
10101
01111
11100
01010
10100
0010
Data Mining Machine Learning
19. What are the tools used in LMS?
LMS
Machine Learning
Intelligence
Automation
20. Where does Machine Learning fit in?
Descriptive attributes +
Knowledge level +
Ongoing evaluation/scoring Analytic insight
Linguistics (UIMA) +
Neural Net Engine/
Text SVM
Reinforced-knowledge
based (dynamic)
course path
21. Role of Analytics in LMS
• The broad promise of analytics is that new insights can be gained from in-depth
analysis of the data trails left by individuals in their interactions with others, with
information, with technology, and with organizations.
22. What are the types of Analytics in LMS ?
LMS
ANALYTICS
Learning
Analytics
Academic
Analytics
23. Learning Analytics
• Wikipedia definition: The measurement, collection, analysis and reporting of data
about learners and their contexts, for purposes of understanding and optimizing
learning and the environments in which it occurs. Learning analytics are largely
concerned with improving learner success.
24. Academic Analytics
• Wikipedia definition: The term for Business Intelligence used in an academic
setting. Academic analytics is the improvement of organizational processes,
workflows, resource allocation, and institutional measurement through the use of
learner, academic, and institutional data. Academic analytics, akin to business
analytics, are concerned with improving organizational effectiveness.
26. Adaptive e-Learning system
• An e-learning system should be designed to match students’ needs and
desires as closely as possible, and adapt during course progression. It is
considered to be adaptive if it is capable of:
– Modeling users, monitoring the activities of its users;
– Interpreting these on the basis of domain-specific models;
– Inferring user requirements and preferences out of the interpreted activities, appropriately
representing these in associated models; and
– Acting upon the available knowledge on its users and the subject matter at hand, to
dynamically facilitate the learning process.
27. Adaptive e-Learning system (Contd.)
• Adaptive e-learning system can be described as a personalized system,
which is able to:
– Perform content discovery and assembly
– Provide an adaptive course delivery, an adaptive interaction, and adaptive collaboration
support
29. Sakai project
• Sakai is a community of academic institutions, commercial organizations and
individuals who work together to develop a common Collaboration and
Learning Environment (CLE).
• The Sakai CLE is used for teaching, research and collaboration.
• It is a free, community source, educational software platform distributed
under the Educational Community License.
• Sakai is a Java-based, service-oriented application suite that is designed to
be scalable, reliable, interoperable and extensible.
• http://www.sakaiproject.org
• Kalvi LMS is based on the Sakai project.
30. What are the components of Kalvi LMS ?
Kalvi LMS
Kalvi
Server
Kalvi
Client
32. Kalvi Server
• Supports all the full-fledged features of a typical LMS.
• There is a central repository of the offered Course list.
• Adaptive Learning system is responsible for making the LMS adaptive.
• All data is persisted in a central backend database.
• Educators: Build and publish new courses via the publishing site.
• Students: Search the course list and select their courses of interest and take them
via the community site.
33. Kalvi Client
• Supports both web based and mobile clients.
• Students can take a course via mobile devices like iPad, iPhone, Android based
devices, etc.
• The mobile client downloads the course from the server and saves it locally. Along
with the course, the client piece of the Adaptive learning system pertinent to the
course is also downloaded to the mobile device.
• The student then takes the course in the mobile device.
• While taking a course from the mobile device, it is not required to stay connected
to the server. That is, courses can be taken from the mobile devices both in online
and offline modes.
• All the data obtained by monitoring and recording student activities during the
course life cycle are persisted in a local database in the mobile device.
• When they are connected, the Kalvi server and client can sync up periodically.
36. Ubiquitous application of Adaptive LMS
• Irrespective of the subjects and courses offered, the demography served, and the
medium of languages delivered to, the learning methodologies and techniques are
the same as they broadly rely on data mining, machine learning and analytics to
deliver adaptive learner-centric content in mobile form factors for the current and
next generation of learners.
• The promising aspect is that the proposed adaptive LMS system could be applied
ubiquitously !
37. Conclusion and future work …
• The key barrier here is not the veracity of the concept or the implementation of the
LMS but it is their incorporation into the current educational processes and culture
which is a rather static.
• This requires evangelization as well as a high level of engagement from all
participants in the education process to effect a change.
39. References
•U.S. Department of Education - "Enhancing Teaching and Learning Through
Educational Data Mining and Learning Analytics", an Issue brief.
http://www.ed.gov/edblogs/technology/files/2012/03/edm-la-brief.pdf
•George Siemens & Dragan Gasevic, Caroline Haythornthwaite & Shane Dawson,
Simon Buckingham Shum & Rebecca Ferguson, Erik Duval & Katrien Verbert,
Ryan S. J. d. Baker - Society for Learning and Analytics Research - "Open
Learning Analytics: an integrated & modularized platform", July 28, 2011
http://solaresearch.org/OpenLearningAnalytics.pdf
•http://www.sakaiproject.org/
•http://en.wikipedia.org/wiki/Sakai_Project
•http://en.wikipedia.org/wiki/Machine_learning
•http://www.longsight.com/
•https://trysakai.longsight.com/portal
•https://moodle.org/
•www.apple.com/ipad
•www.apple.com/iphone