Neyman-Pearson Neural Detectors
This paper is devoted to the design of a neural alternative to binary detectors optimized in the Neyman-Pearson sense. These detectors present a configurable low probability of classifying binary symbol 1 when symbol 0 is the correct decision. This kind of error, referred in the scientific literature as salse-positive or false alarm probability has a high cost in many real applications as medical Computer Aided Diagnosis or Radar and Sonar Target Detection, and the possibility of controlling its maximum value is crucial. The novelty and interest of the detector is the application of a Multilayer Perceptron instead of a classical design. Under some conditions, the Neural Detector presents a performance competitive with classical designs adding the typical advantages of Neural Networks. So, the presented Neural Detectors may be considered as an alternative to classical ones.
KeywordsHide Layer Criterion Function Training Pattern False Alarm Probability Posteriori Probability
Unable to display preview. Download preview PDF.
- 1.Velasco, R., Godin, Ch., Cheynet, Ph., Torres-Alegre, S., Andina, D., Gordon, M.B.: Study of two ANN Digital Implementations of a Radar Detector Candidate to an On-Board Satellite Experiment. In: Mira, J., Sánchez-André, V. (eds.).: Engineering Applications of Bio-Inspired Artificial Neural Network. Lecture Notes in Computer Science, Vol. 1607. Springer-Verlag, Berlin Heidelberg New York (1999) 615–624.CrossRefGoogle Scholar
- 3.Decatur, S.E.: Application of Neural Networks to Terrain Classification. Proc. IEEE Int. Conf. Neural Networks. (1989) 283–288.Google Scholar
- 4.Hush, D.R., Horne, B.G.: Progress in Supervised Neural Networks. What’s new since Lippmann?. IEEE Signal Processing Magazine (1993) 8–5Google Scholar
- 5.Sanz-González, J.L., Andina, D.: Performance Analysis of Neural Network Detectors by Importance Sampling Techniques. Neural Processing Letters. Kluwer Academic Publishers, Netherlands ISSN 1370-4621. 9, (1999) 257–269Google Scholar
- 8.El-Jaroudi, A., Makhoul J.: A New Error Criterion For Posterior Probability Estimation With Neural Nets. Proc. of Int. Joint. Conf. Neural Networks, IJCNN, Vol. I 5 (1990) 185–192.Google Scholar