DocumentCode
2745346
Title
Quasi-optimum detection results using a neural network
Author
Andina, Diego ; Sanz Gonzalez, J.L.
Author_Institution
ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
Volume
4
fYear
1996
fDate
3-6 Jun 1996
Firstpage
1929
Abstract
We study some particularities for the application of a neural network to binary detection. Using a modeled input (the classical J. Marcum model for pulsed radar detection), we optimize the design of the network, evaluating its performance by Monte Carlo trials. After comparing the detection curves with the theoretical optimum ones, it is found that the number of pulses integrated for each detection is critical for a quasi-optimum performance of the neural network
Keywords
Monte Carlo methods; backpropagation; multilayer perceptrons; pattern classification; radar detection; Monte Carlo trials; binary detection; detection curves; neural network; pulsed radar detection; quasi-optimum detection; Backpropagation algorithms; Concurrent computing; Design optimization; Detectors; Electronic mail; Hardware; Neural networks; Parallel processing; Radar detection; Telecommunication standards;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1996., IEEE International Conference on
Conference_Location
Washington, DC
Print_ISBN
0-7803-3210-5
Type
conf
DOI
10.1109/ICNN.1996.549196
Filename
549196
Link To Document