Effects of Feature Selection on the Identification of Students with Learning Disabilities Using ANN

  • Tung-Kuang Wu
  • Shian-Chang Huang
  • Ying-Ru Meng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)


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.


Support Vector Machine Artificial Neural Network Feature Selection Artificial Neural Network Model Learn Disability 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kirk, S.A.: Behavioral diagnosis and remediation of learning disabilities. In: Proceedings of the Conference on the Exploration into the Problems of the Perceptually Handicapped Child, Evanston, IL (1963)Google Scholar
  2. 2.
    Fletcher, J.M., Coulter, W.A., Reschly, D.J., Vaughn, S.: Alternative Approach to the Definition and Identification of Learning Disabilities: Some Questions and Answers. Annals of Dyslexia 54(2), 304–331 (2004)CrossRefGoogle Scholar
  3. 3.
    Schrag, J.: Discrepancy approaches for identifying learning disabilities. National Association of State Directors of Special Education, Alexandria (2000)Google Scholar
  4. 4.
    Wu, Tung-Kuang, Hwang, S.-C., Meng, Y.-R.: Identifying and Diagnosing Students with Learning Disabilities using ANN and SVM. In: Proceedings of the 2006 IEEE International Joint Conference on Neural Networks, Vancouver, BC, Canada, July 16-21 (2006)Google Scholar
  5. 5.
    National Health Interview Survey (2006) (extracted on January 16, 2006),
  6. 6.
    Moore, G.B.: Robotics, Artificial Intelligence, Computer Simulation: Future Applications in Special Education. In: COSMOS Corp., Washington, DC (1985)Google Scholar
  7. 7.
    Hofmeister, A.M., Ferrara, J. M.: Artificial Intelligence Applications in Special Education: How Feasible? Final Report, Logan, Utah State U. (1986)Google Scholar
  8. 8.
    Hofmeister, A.M., Lubke, M.M.: Expert Systems: Implications for the Diagnosis and Treatment of Learning Disabilities. Learning Disability Quarterly 11(3), 287–291 (1988)CrossRefGoogle Scholar
  9. 9.
    Geiman, R.M., Nolte, W.L.: An Expert System for Learning Disability Diagnosis. In: Proceedings of the IEEE Conference on System Engineering, August 1990, pp. 363–366 (1990)Google Scholar
  10. 10.
    Baer, R.: Referral Consultant: An Expert System for Guiding Teachers in Referring Students for Special Education Placement, Logan, Utah State U., Center for Persons with Disabilities (1991)Google Scholar
  11. 11.
    Vinsonhaler, J.: Using an Experts System to Study the Classroom Placement Decision for Students Who Are Deaf or Hard-of-Hearing. Journal of Special Education Technology 12(2), 135–148 (1993)MathSciNetGoogle Scholar
  12. 12.
    Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., Vanthienen, J.: Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society 54, 627–635 (2003)MATHCrossRefGoogle Scholar
  13. 13.
    Razi, M.A., Athappilly, K.: A comparative analysis of neural network (NNs), nonlinear regression and classification and regression tree (CART) models. Expert Systems with Application 29, 65–74 (2005)CrossRefGoogle Scholar
  14. 14.
    NeuroDimension Incorporated, What is a Neural Network?,
  15. 15.
    Sordo, M.: Introduction to Neural Networks in Healthcare. OpenClinical.:Knowledge Management for Medical Care, Harvard (2002)Google Scholar
  16. 16.
    Mead, W.C.: Development of Neural Network Tools and Techniques for Arithmetic Training of Children with Learning Disabilities: Phase I - Theory and Simulations. In: AERA 1997, Chicago, IL, March 24-28 (1997)Google Scholar
  17. 17.
    Linstrom, K.R., Boye, A.J.: Neural Network Prediction Model for a Psychiatric Application. In: Proceedings of the Sixth International Conference on Computational Intelligence and Multimedia Applications (2005)Google Scholar
  18. 18.
    Fu, X.J., Wang, L.P.: Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance. IEEE Trans. System, Man, Cybernetics, Part B 33, 399–409 (2003)CrossRefGoogle Scholar
  19. 19.
    Fu, X.J., Wang, L.P.: A GA-Based Novel RBF Classifier with Class-Dependent Features. In: Proc. 2002 IEEE Congress on Evolutionary Computation (CEC 2002), vol. 2, pp. 1890–1894 (2002)Google Scholar
  20. 20.
    Raymer, M.L., Punch, W.F., Goodman, E.D., Kuhn, L.A., Jain, A.K.: Dimensionality reduction using genetic algorithms. IEEE Trans. Evolutionary Computation 4, 164–171 (2000)CrossRefGoogle Scholar
  21. 21.
    Rittho, Oliver, Klinkenberg, R., Fischer, S., Mierswa, I., Felske, S., Yale: Yet Another Learning Environment. In: LLWA 2001 - Tagungsband der GI-Workshop-Woche Lernen - Lehren - Wissen - Adaptivität, Dortmund, Germany, vol. (763), pp. 84–92 (2001)Google Scholar
  22. 22.
    XLMiner (extracted on January 29, 2006),

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tung-Kuang Wu
    • 1
  • Shian-Chang Huang
    • 2
  • Ying-Ru Meng
    • 3
  1. 1.Dept. of Information ManagementNational Changhua University of Education 
  2. 2.Dept. of Business AdministrationNational Changhua University of Education 
  3. 3.Dept. of Special EducationNational HsinChu University of Education 

Personalised recommendations