Effects of feature selection on the identification of students with learning disabilities using ANN

Authors:
Tung-Kuang Wu;Shian-Chang Huang;Ying-Ru Meng
Affiliations:
Dept. of Information Management, National Changhua University of Education;Dept. of Business Administration, National Changhua University of Education;Dept. of Special Education, National HsinChu University of Education
Venue:
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Year:
2006

Citing 5
Cited 0

A Neural Network Prediction Model for a Psychiatric Application

ICCIMA '05 Proceedings of the Sixth International Conference on Computational Intelligence and Multimedia Applications
A GA-based RBF classifier with class-dependent features

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models

Expert Systems with Applications: An International Journal
Dimensionality reduction using genetic algorithms

IEEE Transactions on Evolutionary Computation
Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Due to the implicit characteristics of learning disabilities (LD), the identification and diagnosis of students with learning disabilities has long been a difficult issue. Identification of LD usually involves interpreting some standard tests or checklist scores and comparing them to norms that are derived from statistical method. In our previous study, we made a first attempt in adopting two well-known artificial intelligence techniques, namely, artificial neural network (ANN) and support vector machine (SVM), to the LD identification problem. The preliminary results are quite satisfactory, and indicate that we may be going in the right direction. In this paper, we go one step further by combining various feature selection algorithms and the ANN model. The outcomes show that the correct identification rate has improved quite a lot over what we achieved previously. The combined selected features and the ANN classifier can be used as a strong indicator in the LD identification process and improve the accuracy of diagnosis.