Visual Analysis of Educational Data using Neural
Network based Clustering and Classification
Approach
Journal:
GRENZE International Journal of Computer Theory and Engineering
Authors:
Pratiyush Guleria, Manu Sood
Volume:
1
Issue:
1
Grenze ID:
01.GIJCTE.1.1.543
Pages:
62-68
Abstract
To increase the quality of education and to find solution to problems arising from
complex educational dataset and competitive environment among the academic institutions,
Educational Data Mining is receiving great attention. Student’s performance is of great
concern to the higher education. In this paper, we have applied two approaches for
educational data mining. The first approach is based on self-organizing map (SOM) which
is a type of ANN (Artificial neural network) that is trained using unsupervised learning to
produce low-dimensional views of high-dimensional data. Using this approach, we have
clustered students based on certain attributes into natural classes so that similar classes are
grouped together. The second approach uses pattern recognition through two-layer feedforward
network to classify inputs into a set of target categories.