V. Marivate and T. Marwala (South Africa)
Neural Network, Relational Network, Classification, HIV
The use of computational intelligence techniques to classify people has been used in numerous applications. This paper compares the use of a Multi Layer Perceptron Neural Network and a Relational Network in classifying the HIV status of women at ante-natal clinics. The paper discusses the architecture of the relational network and its merits compare to a neural network and most other computational intelligence classifiers. Results gathered from the study indicate comparable classification accuracies as well as revealed relationships between data features in the classification data. Much higher classification accuracies are recommended for future research in the area of HIV classification as well as missing data estimation.
Important Links:
Go Back
