Discovering student learning styles in engineering mathematic at Politeknik Merlimau using neural network techniques

Mat Esa, Asmarizan (2015) Discovering student learning styles in engineering mathematic at Politeknik Merlimau using neural network techniques. Masters thesis, Universiti Teknikal Malaysia Melaka.

[img] Text (24 Pages)
DISCOVERING STUDENT LEARNING STYLES IN ENGINEERING MATHEMATICS AT POLITEKNIK MERLIMAU USING NEURAL NETWORK TECHNIQUES (24 pgs).pdf - Submitted Version

Download (447kB)
[img] Text (Full Text)
Discovering student learning styles in engineering mathematic at Politeknik Merlimau using neural network techniques.pdf - Submitted Version
Restricted to Registered users only

Download (2MB)

Abstract

The identification of students’ learning style in learning mathematics is important for educators in choosing an effective teaching approach/methodology. Students from different field of studies to complete were asked the Index Learning Styles questionnaire to identify the student’s learning style of learning DBM1013 - Engineering Mathematics. This technique is used to consider their learning styles and how to improve students’ performance in learning DBM1013 – Engineering, Mathematics, the questionnaires were evaluated to identify the best learning styles used by students in learning Engineering Mathematics. However, the problem with this method is the time spent by students in answering questions and the accuracy of the results obtained. If questionnaires are too long, students tend to choose both answers arbitrarily instead of thinking about the result of the student’s learning style observed through analysis. This research identified the classification of students learning styles based on the Felder Silverman Learning dimension. Four learning dimension has been classified by using backpropagation neural networks. The algorithm has been run on training, validation and testing, training process data and 20 neurons. The result shows that the neural network is able to identify the students' learning styles according to the dimension with satisfying result.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Neural networks (Computer science)
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA76 Computer software
Divisions: Library > Tesis > FTMK
Depositing User: Muhammad Afiz Ahmad
Date Deposited: 18 Mar 2016 02:55
Last Modified: 06 Oct 2022 09:23
URI: http://eprints.utem.edu.my/id/eprint/15877
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item