Evaluation of Regional Benchmark Impact in EDM

Paper Title : Evaluation of Regional Benchmark Impact in EDM
Author(s):  P. V. Praveen Sundar, A.V. Senthil Kumar
Published in:  International Journal of Computer Science Issues (IJCSI)
Volume/Issue:  Vol. 10, Issue 2, No 2, March 2013, PP: 531-535
ISSN : 1694-0784

ABSTRACT: The main objective of educational institutions is to provide high quality of education. Providing a high quality of education depends on predicting the unmotivated students and motivates them before they enter into the final examination. There are so many factors which leads to unmotivated the students, such as college infrastructure, their living area, family annual income, Parents qualification, Past academic performance, students own interest on the course, other habits of the student, etc., There are many researches  undertaken on the above factors and predict the unmotivated students, In this paper we mainly focus on how the geographical region plays a role on student’s academic performance.

KEYWORDS: Educational Data mining, Classification, Hidden naive Bayes, Place  based learning.
 
Download Full Text

To Cite this paper

Praveen Sundar P.V., A.V.Senthil Kumar : Evaluation of Regional Benchmark Impact in EDM. (IJCSI) International Journal of Computer Science Issues, Vol. 10, Issue 2, No 2, PP: 531-535 March 2013.

A Hybrid Classification Method for Disengagement Detection in Online Learning

Paper Title : A Hybrid Classification Method for Disengagement Detection in Online Learning
Author(s):  P. V. Praveen Sundar, A.V. Senthil Kumar
Published in:   International Journal of Education and Information Studies (IJEIS)
Volume/Issue:   Vol. 05, Issue 01 ( 2015), ||V1|| PP 67-74
ISSN : 2277- 3169

Abstract : The main aim of the online learning system is to meet the requirements of the learners and to make efficient for learners where the aspects and complexity are taken into consideration. The learner’s motivational states are undertaken by many attempts, mainly by using design. Motivations are started by using analysis of log file. Firstly, the disengaged learners are identified moderately, and then visualize the disengaged learners which includes evaluation of many motivational characteristic for learning. For improvement in learning, data mining and machine learning methods will provide us meaningful data and valuable information. The performances of Bayesian classifiers endure in the field where it involves correlated features. Naïve Bayesian classification with PSO method is already implemented in many fields, the main problem in PSO is its tendency of trapping into local optima. To overcome this problem, this research presents the hybrid algorithm by combining fast PSO and Naïve Bayesian classifier for classification to aid in the prediction of disengagement. According to the characteristics of the data, our proposed method improves the classification accuracy and avoids the loss of information. This study results showed that the method was feasible and effective.

Keywords-- Online learning, Log File Analysis, Disengagement Detection, Bayesian classifiers, Particle Swarm Optimization, Quasi Framework.

Download Full Text

To Cite this paper

P.V. Praveen Sundar, A.V. Senthil Kumar,"A Hybrid Classification Method for Disengagement Detection in Online Learning", International Journal of Education and Information Studies (IJEIS), Volume 5, 2015 PP: 67-74.   

A Novel Disengagement Detection Strategy for Online learning using Quasi Framework

Paper Title : A Novel Disengagement Detection Strategy for Online learning using Quasi Framework
Author(s):  P. V. Praveen Sundar, A.V. Senthil Kumar
Conference : IEEE International Advance Computing Conference (IACC) – 2015,  Bengaluru, June 12,13th, 2015.
Published in:   Special Issue of IEEE xplore
Print ISBN: 978-1-4799-8046-8 

Abstract:
The online learning gains more popularity in recent days; its key success is delivering content over internet and can be accessed by students from anywhere and anytime. In general, attraction is the quality of arousing interest. Similarly, motivation is the other hand to support for learning. Since, the online learning has less control over students compared to the conventional teaching method. Therefore engagement of student gets more importance on online learning. Most of the learning systems stores learners activities in log files and their profile related informations in database. Usually log file analysis alone could not have enough data to find out disengagement. Thus we integrate the log file information with database and develop a novel disengagement detection strategy using quasi framework. This study result reveals that quasi framework is effective in term of quality compared to previous proposals.

Keywords:
Disengagement Detection, EDM, Log File Analysis, Quasi, Online Learning

Download Full Text

To Cite this Paper
  
Sundar, P.V.P.; Senthil Kumar, A.V., "A novel disengagement detection strategy for online learning using quasi framework," in Advance Computing Conference (IACC), 2015 IEEE International , vol., no., pp.634-638, 12-13 June 2015
doi: 10.1109/IADCC.2015.7154784
keywords: {Internet;computer aided instruction;Internet;disengagement detection strategy;log file analysis;online learning;quasiframework;Benchmark testing;Indexes;Proposals;Reliability;Disengagement Detection;EDM;Log File Analysis;Online Learning;Quasi} 

An Enhanced Disengagement Detection in Online Learning using Quasi Framework

Paper Title : An Enhanced Disengagement Detection in Online Learning using Quasi Framework
Author(s):  P. V. Praveen Sundar, A.V. Senthil Kumar
Conference : International Conference on Advances in Applied Engineering and Technology – 2015,  Syed Ammal Engineering College, Ramanathapuram, May 14-16, 2015.
Published in:   Special Issue of International Journal of Applied Engineering Research (IJAER)
Volume/Issue:   Vol. 10, Issue 55 (2015),  PP 1298-1302
Online ISSN 1087-1090, Print ISSN 0973-4562


Abstract
Educational software strives to meet the learner‟s needs and preferences in order to make learning more efficient. For successful E-learning, an engagement and disengagement are the two important aspects. Learners‟ engagement is a successful indicator of their motivation, acceptance and attachment to the learning activity. By tracing the disengaged learners in E-learning, will provide us the possibility to get involved in motivating the learner at proper time. This disengagement can be detected by observing the learner‟s action in E-learning. In an e-learning environment, various attributes which is relevant for predicting disengagement is identified in log–file analysis so far. This work extended an events and attributes for detecting disengagement in e-learning system using mouse dynamic. Here, mouse-dynamic is included as event (scroll wheel used, no. of clicks are attributes) with other previously identified events for predicting disengagement which is derived from log data observations. This improves the prediction performance of disengaged learners and it becomes very compatible in e-learning.

Keywords: E-learning, disengagement detection, log data analysis, mouse dynamic model.

Download Full Text

To Cite this paper


    P.V.Praveen Sundar, A.V.Senthil Kumar, ”An Enhanced Disengagement Detection in Online Learning using Quasi Framework”, In Proceedings of International Conference on Advances in Applied Engineering and Technology(ICAAET) – 2015, May 14-16, 2015, Ramanathapuram, Tamilnadu, India,  International Journal of Applied Engineering Research(IJAER), Special Issue Vol. 10 No.55 (2015), PP- 1298-1302.

Disengagement Detection in Online Learning using Quasi Framework

Paper Title : Disengagement Detection in Online Learning using Quasi Framework
Author(s):  P. V. Praveen Sundar, A.V. Senthil Kumar
Published in:   IOSR Journal of Engineering (IOSRJEN)
Volume/Issue:   Vol. 05, Issue 01 (January. 2015), ||V1|| PP 04-09
ISSN (e): 2250-3021, ISSN (p): 2278-8719

Abstract: - Online Learning enables to deliver both learning and information dynamically. It allows tapping the knowledge of experts and non-experts and catapulting those messages beyond classroom walls and into the workplace but it is more difficult to assess a learner’s motivation. In traditional classroom learning, when a student shows signs of de-motivation, teachers know how to motivate their students and how to optimize their instruction. But in On-line learning it is difficult to measure their disengaged level. By tracing the disengaged learners in online learning, will help us to motivate the learners at proper time. Thus making an online learning to be a successful one. Thus we propose a new framework called Quasi Framework, which is trying to measure the significant relationship between disengagement level and their academic achievement. In this paper we compare our proposed framework with ihelp, a web based learning system. 

Keywords: Disengagement Detection, Online Learning, EDM, Log File Analysis

Download Full Paper

To Cite this paper 

Praveen Sundar P.V, A.V.Senthil Kumar," Disengagement Detection in Online learning using Quasi framework", IOSR Journal of Engineering (IOSR JEN), Volume 5, Issue-I,Version-l, PP: 4-9,2015.

 

Quasi Framework: A New Student Disengagement Detection In Online Learning

Paper Title : Quasi Framework: A New Student Disengagement Detection In Online
Learning

Author(s):  P. V. Praveen Sundar
Published in:   International Journal of Engineering Research & Technology
Volume/Issue:   Vol.1 - Issue 10 (December - 2012)
e-ISSN:   2278-0181

Abstract:

Educational Data Mining (EDM) has emerged as independent research area in recent years. Moreover student learning environment also rapidly move towards online. Compare to traditional teaching method, online tutoring will attracts younger generations. However student engagement is an important aspect of effective learning. Most of the students performed well in their academic performance and spent more time with internet too. Thus measuring disengagement is likely to help poor performance students. In this paper we propose a new framework called Quasi Framework, which is trying to measure the significant relationship between disengagement level and their academic achievement. 

Keywords: Disengagement Detection, Online Learning, EDM, Student Performance Prediction

  

Download  Full Paper

To Cite this paper, 

P. V. Praveen Sundar . " Quasi Framework: A New Student Disengagement Detection In Online Learning ", Vol.1 - Issue 10 (December - 2012) , International Journal of Engineering Research & Technology (IJERT) , ISSN: 2278-0181 , www.ijert.org