TY - GEN
T1 - Identifying and diagnosing students with learning disabilities using ANN and SVM
AU - Wu, Tung Kuang
AU - Huang, Shian Chang
AU - Meng, Ying Ru
PY - 2006/12/1
Y1 - 2006/12/1
N2 - Due to the implicit characteristics of learning disabilities (LD), the identification or diagnosis of students with learning disabilities has long been a difficult issue. In fact, there is little consensus about what is the best procedure to identify a person with LD. Instead, the procedures are based on empirical findings from scholarly research. This is both true in the United States and Taiwan. However, the situation may be even more difficult in Taiwan. Firstly, the procedure requires a lot of manpower and resources, which is not allowable in Taiwan's current special education system. Secondly, due to the lack of nationally agreed standard, the variations of identifying procedure and the corresponding outcomes among counties are rather significant. In fact, in most counties of Taiwan, the numbers of identified LD students are heavily underestimated. The direct consequence of it is that a lot of potential LD students are not included in special education they are entitled to. To guarantee every potential LD students the right they deserved, the above two issues have to be resolved. In this paper, we try to adopt two well-known artificial intelligence techniques (Artificial Neural Network and Support Vector Machine), which have been applied successfully to solve problems in numerous fields, to the LD identification and diagnosis problem. To the best of our knowledge, this is the first attempt in this field. If proved workable, computer-based artificial intelligence methods will not just relieve the above two problems, but have an additional advantage in eliminating possible human bias. The preliminary results are satisfactory and can be provided as second opinion to the LD evaluation personnel. But it still requires many efforts to make the model more accurate and to make the idea practically feasible, which is what we will be working on.
AB - Due to the implicit characteristics of learning disabilities (LD), the identification or diagnosis of students with learning disabilities has long been a difficult issue. In fact, there is little consensus about what is the best procedure to identify a person with LD. Instead, the procedures are based on empirical findings from scholarly research. This is both true in the United States and Taiwan. However, the situation may be even more difficult in Taiwan. Firstly, the procedure requires a lot of manpower and resources, which is not allowable in Taiwan's current special education system. Secondly, due to the lack of nationally agreed standard, the variations of identifying procedure and the corresponding outcomes among counties are rather significant. In fact, in most counties of Taiwan, the numbers of identified LD students are heavily underestimated. The direct consequence of it is that a lot of potential LD students are not included in special education they are entitled to. To guarantee every potential LD students the right they deserved, the above two issues have to be resolved. In this paper, we try to adopt two well-known artificial intelligence techniques (Artificial Neural Network and Support Vector Machine), which have been applied successfully to solve problems in numerous fields, to the LD identification and diagnosis problem. To the best of our knowledge, this is the first attempt in this field. If proved workable, computer-based artificial intelligence methods will not just relieve the above two problems, but have an additional advantage in eliminating possible human bias. The preliminary results are satisfactory and can be provided as second opinion to the LD evaluation personnel. But it still requires many efforts to make the model more accurate and to make the idea practically feasible, which is what we will be working on.
UR - http://www.scopus.com/inward/record.url?scp=40649127935&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=40649127935&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:40649127935
SN - 0780394909
SN - 9780780394902
T3 - IEEE International Conference on Neural Networks - Conference Proceedings
SP - 4387
EP - 4394
BT - International Joint Conference on Neural Networks 2006, IJCNN '06
T2 - International Joint Conference on Neural Networks 2006, IJCNN '06
Y2 - 16 July 2006 through 21 July 2006
ER -