ROC analysis as a useful tool for performance evaluation of artificial neural networks

Authors:
Fikret Tokan;Nurhan Türker;Tülay Yıldırım
Affiliations:
Electrical and Electronics Faculty, Department of Electronics and Communication Engineering, Yıldız Technical University, Yıldız, Istanbul, Turkey;Electrical and Electronics Faculty, Department of Electronics and Communication Engineering, Yıldız Technical University, Yıldız, Istanbul, Turkey;Electrical and Electronics Faculty, Department of Electronics and Communication Engineering, Yıldız Technical University, Yıldız, Istanbul, Turkey
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 4
Cited 1

Models of incremental concept formation

Artificial Intelligence
A new distributed data mining model based on similarity

Proceedings of the 2003 ACM symposium on Applied computing
A multiple classifier system for early melanoma diagnosis

Artificial Intelligence in Medicine
Classification capacity of a modular neural network implementing neurally inspired architecture and training rules

IEEE Transactions on Neural Networks

Handling imbalanced data sets with synthetic boundary data generation using bootstrap re-sampling and AdaBoost techniques

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

In many applications of neural networks, the performance of the network is given by the classification accuracy. While obtaining the classification accuracies, the total true classification is computed, but the number of classification rates of the classes and fault classification rates are not given. This would not be enough for a problem having fatal importance. As an implementation example, a dataset having fatal importance is classified by MLP, RBF, GRNN, PNN and LVQ networks and the real performances of these networks are found by applying ROC analysis.