search railabs.duhs.duke.edu.

Papers Published

1. Land, W.H., Jr. and Masters, T. and Lo, J.Y., Performance evaluation using the GRNN Oracle and a new evolutionary programming/adaptive boosting hybrid for breast cancer benign/malignant diagnostic aids, Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Data Mining, and Complex Systems. Vol.10. Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE 2000) (2000), pp. 813 - 18 .
   (last updated on 2007/04/15)

   Abstract:
   This paper describes the use of two new neural network technologies for the benign/malignant diagnosis of breast cancer using mammogram findings. These two paradigms use markedly different theories in solving computational intelligence (CI) problems. The General Regression Neural Network (GRNN) Oracle focuses on improving the performance output of a set of learning algorithms that operate and are accurate over the entire (defined) learning space. Adaptive boosting, by contrast, focuses on finding weak learning algorithm(s) that need to be better than “random”, and then, by successive rounds, improves the performance of these algorithm(s)

   Keywords:
   cancer;evolutionary computation;learning (artificial intelligence);mammography;medical diagnostic computing;neural nets;performance evaluation;