USING DECISION TREE CLASSIFIER FOR ANALYZING STUDENTS’ ACTIVITIES
Journal Title: Journal of Information Technology and Application (JITA) - Year 2013, Vol 3, Issue 2
Abstract
In this paper students’ activities data analysis in the course Introduction to programming at Faculty of Electrical Engineering in East Sarajevo is performed. Using the data that are stored in the Moodle database combined with manually collected data, the model was developed to predict students’ performance in successfully passing the fi nal exam. The goal was to identify variables that could help teachers in predicting students’ performance and making specifi c recommendations for improving individual activities that could directly infl uence fi nal exam successful passing. The model was created using decision tree classifi er and experiments were performed using the WEKA data mining tool. The effect of input attributes on the model performances was analyzed and applying appropriate techniques a higher accuracy of the generated model was achieved.
Authors and Affiliations
Snježana Milinković, Mirjana Maksimović
Keywords
Related Articles
- EP ID EP244510
- DOI 10.7251/JIT1302087M
- Views 104
- Downloads 0
FUNCTIONAL DEPENDENCIES ANALYSE IN FUZZY RELATIONAL DATABASE MODELS
This paper presents a literature overview of Fuzzy Relational Database Models with emphasis on the role of functional dependencies in logical designing and modeling. The aim is the analysis of recent results in this fi e...
CONTEMPORARY JAVA WEB TECHNOLOGIES AS A SERVICE FOR THE UNIVERSITY EMPLOYEES
This paper describes the web application used by employees of the School of Electrical Engineering in Belgrade. The application is based on contemporary open source Java web technologies (including frameworks such as Spr...
AQUACULTURE CLOUD MANAGEMENT SYSTEM
This study proposes an aquaculture system combining wireless sensors with the Internet of Things and expert system concepts. Built on the accumulated expertise and experience of professionals and researchers, the knowled...
PACKET LOSS DIFFERENTIATION OVER MANET BASED ON A BP NEURAL NETWORK
An adaptive distributed routing algorithm is essential in MANETs, since there is no central routing system. Actually, there is no central point of coordination; each node is responsible for forwarding data packets to oth...
A NEW APPROACH TO COMPUTER ANALYSIS OF QUEUING SYSTEMS WITHOUT PROGRAMMING
The paper presents original object oriented programming system ARS for modelling and simulation queuing systems. Programming system was developed in programming language C++. It establishes connection with intrinsic, but...