Your SlideShare is downloading. ×
  • Like
Content  Classification And  Context  Based  Retrieval  System For  E  Learning
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Now you can save presentations on your phone or tablet

Available for both IPhone and Android

Text the download link to your phone

Standard text messaging rates apply

Content Classification And Context Based Retrieval System For E Learning

  • 456 views
Published

 

Published in Business , Education
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
456
On SlideShare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
6
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide

Transcript

  • 1. Content Classification and Context-Based Retrieval System for E-Learning Ankush Mittal , Pagalthivarthi V. Krishnan , Edward Altman International Forum of Educational Technology & Society , 2006
  • 2. Outline
    • Introduction
    • Automatic methodology for indexing of lecture videos
      • Formulation and analysis a state model for lectures
      • Video indexing features
      • Lecture video indexing
    • Experimental Result and applications
    • Conclusion
  • 3. Introduction
    • Base on Singapore-MIT Alliance(SMA) video database.
    • This paper issue of defining and automatically classifying the semantic fragment.
    • Target on the e-learning materials that in raw form as video, audio, slides.
    • Discuss how fragments can be contextually used for personal learning.
  • 4. Automatic methodology for indexing of lecture videos
    • Main problem : bridging the semantic gap between raw video and high level information required by students.
      • 1. Classify
      • 2. Discover relations
      • 3. Formation of a base for providing various users
  • 5. Formulation and analysis a state model for lectures
    • Temporal state model for lectures (Ex : Algorithm)
      • Introduction
      • Definitions & Theorems
      • Theory
      • Discussions
      • Review
      • Question and Answer
      • Sub-Topic
  • 6. Formulation and analysis a state model for lectures (cont.)
    • The semantic analysis of raw video steps:
      • 1. Extract low and mid level features.
      • 2. Classify
      • 3. Apply contextual info to determine higher level semantic events.
      • 4. Apply a set of high level constraints
  • 7. Video indexing features
    • Audio features
    • Video features
    • Text features
  • 8. Lecture video indexing
    • Deriving semantics from low-level features
    • Rule for indexing the slide :
      • Category 1 : Definitions / Theorems
      • Category 2 : Examples
      • Category 3 : Proof
      • Category 4 : Formulae
  • 9. Lecture video indexing (cont.)
    • Contextual searching
      • Manually enter the topic name for each video clip associated with the event
  • 10. Experimental Result and applications
    • Test the method on 26 lecture videos from Singapore-MIT Alliance course SMA5503.
  • 11. Experimental Result and applications (cont.)
    • Personalization
      • Student interested in this course can be divided 3 categories :
        • 1. viewing the lecture for the first time
        • 2. reviewing to brush up concepts
        • 3. reviewing for preparation of exam
  • 12. Experimental Result and applications (cont.)
    • Retrieving fragments of document
  • 13. Conclusion
    • video 分段的概念不錯 , 只是做法上的限制頗大
    • 在 user tracking 的地方 , 不但可用一般 sequence 來判斷他念過哪些 , 還可以藉由使用者的 review 次數 , 以及時間是否接近考試來回傳不同的資訊