Neural Networks - 2003 Special issue: Advances in neural networks research IJCNN'03
IEEE Transactions on Signal Processing
Tuning Support Vector Machines for Minimax and Neyman-Pearson Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural network detectors for composite hypothesis tests
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Neural networks for signal detection in non-Gaussian noise
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
SONN and MLP based detection schemes are designed for approximating the Neyman-Pearson, NP, detector for detecting fluctuating targets with unknown Doppler shift in Gaussian interference. The optimum NP detector conveys a complex integral, so sub-optimum approaches based on the Constrained Generalized Likelihood Ratio, CGLR, are proposed as reference solutions. Detectors based on a single MLP, a single SONN, and mixtures of them are studied, and their detection capabilities and computational costs evaluated. Results show that the detector based on a mixture of SONNs is able to approximate the CGLR, outperforming the other proposed solutions, with lower computational cost.