A Novel Classification Method for Diagnosis of Diabetes Mellitus Using Artificial Neural Networks
- 1 February 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 159-163
- https://doi.org/10.1109/dsde.2010.58
Abstract
Many real world problems can be solved with Artificial Neural Networks in the areas of pattern recognition, signal processing and medical diagnosis. Most of the medical data set is seldom complete. Artificial Neural Networks require complete set of data for an accurate classification. This paper dwells on the various missing value techniques to improve the classification accuracy. The proposed system also investigates the impact on preprocessing during the classification. A classifier was applied to Pima Indian Diabetes Dataset and the results were improved tremendously when using certain combination of preprocessing techniques. The experimental system achieves an excellent classification accuracy of 99% which is best than before.Keywords
This publication has 4 references indexed in Scilit:
- Application of Artificial Neural Network (ANN) technique for Diagnosing Diabetes MellitusPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A New Evolutionary Neural Network ClassifierLecture Notes in Computer Science, 2005
- Modelling the glucose metabolism with backpropagation through time trained Elman netsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Dealing with missing values in neural network-based diagnostic systemsNeural Computing & Applications, 1995