Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Modular learning strategy for signal detection in a nonstationaryenvironment
IEEE Transactions on Signal Processing
MLP-based radar detectors for Swerling 1 targets
Pattern Recognition and Image Analysis
| Hi-index | 0.00 |
A new pre-processing stage for neural radar detectors is presented order to reduce the detector performance dependence on the Training Signal-to-Noise Ratio (TSNR). The proposed scheme combines Time-frequency Analysis for transforming radar echoes on to a feature space where the detection task is easier, and Principal Component Analysis for dimensionality reduction. The results are compared with those obtained when using a single MLP, demonstrating that the new detection scheme can match the best receiver operatiing characteristic of the single MLP radar detector, for any value of TSNR, avoding the laborious trial-and-error process that is necessary to select the optimum TSNR for a single MLP radar detector.