TY - GEN
T1 - Computational intelligence and decision trees for missing data estimation
AU - Ssali, George
AU - Marwala, Tshilidzi
PY - 2008
Y1 - 2008
N2 - This paper introduces a novel paradigm to impute missing data that combines a decision tree with an autoassociative neural network (AANN) based model and a principal component analysis-neural network (PCA-NN) based model. For each model, the decision tree is used to predict search bounds for a genetic algorithm that minimise an error function derived from the respective model. The models' ability to impute missing data is tested and compared using HIV sero-prevalance data. Results indicate an average increase in accuracy of 13% with the AANN based model's average accuracy increasing from 75.8% to 86.3% while that of the PCA-NN based model increasing from 66.1 % to 81.6%.
AB - This paper introduces a novel paradigm to impute missing data that combines a decision tree with an autoassociative neural network (AANN) based model and a principal component analysis-neural network (PCA-NN) based model. For each model, the decision tree is used to predict search bounds for a genetic algorithm that minimise an error function derived from the respective model. The models' ability to impute missing data is tested and compared using HIV sero-prevalance data. Results indicate an average increase in accuracy of 13% with the AANN based model's average accuracy increasing from 75.8% to 86.3% while that of the PCA-NN based model increasing from 66.1 % to 81.6%.
UR - http://www.scopus.com/inward/record.url?scp=56349109493&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2008.4633790
DO - 10.1109/IJCNN.2008.4633790
M3 - Conference contribution
AN - SCOPUS:56349109493
SN - 9781424418213
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 201
EP - 207
BT - 2008 International Joint Conference on Neural Networks, IJCNN 2008
T2 - 2008 International Joint Conference on Neural Networks, IJCNN 2008
Y2 - 1 June 2008 through 8 June 2008
ER -
