The purpose of this study is to investigate several artificial Neural Network (NN) architectures in order to design a cognitive radar system capable of optimally distinguishing linear Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). The goal is to create a theoretical framework to determine an optimal NN architecture to achieve a Probability of Detection (PD) of 95% or higher and a Probability of False Alarm (PFA) of 1.5% or lower at 5 dB Signal to Noise Ratio (SNR). Literature research reveals that the frequency-domain power spectral densities characterize a signal more efficiently than its time-domain counterparts. Therefore, the input data is preprocessed by calculating the magnitude square of the Discrete Fourier Transform of the digitally sampled bandlimited AWGN and linear FM signals to populate a matrix containing N number of samples and M number of spectra. This matrix is used as input for the NN, and the spectra are divided as follows: 70% for training, 15% for validation, and 15% for testing. The study begins by experimentally deducing the optimal number of hidden neurons (1-40 neurons), then the optimal number of hidden layers (1-5 layers), and lastly, the most efficient learning algorithm. The training algorithms examined are: Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Polak-Ribiére Conjugate Gradient, and Variable Learning Rate Backpropagation. We determine that an architecture with ten hidden neurons (or higher), one hidden layer, and a Scaled Conjugate Gradient for training algorithm encapsulates an optimal architecture for our application.
We propose an approach based on artificial Neural Networks (NN) to classify wideband radar jammer signals for more efficient use of countermeasures. A robust NN is be used to correctly differentiate Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). We compare the performance of the NN using the samples of the power spectrum versus the autocorrelation. Prior experiments showed that frequency-domain moments of the FM signal itself are better descriptors than time-domain moments. Using simulated wideband FM radar signals, we compute a set of N autocorrelation and spectra and feed them to the NN which has ten hidden layers. For training purposes, the autocorrelations or spectra sets are divided into three groups, 75% for training, 15% for validating and 15% for testing. For the power spectra set, we observe that a Signal to Noise Ratio (SNR) of 5dB allows the network to approach an average of 5% percent Probability of Error (PE). Training with the autocorrelation set yields comparable results. For an SNR of 5dB, the average PE reached an average of 0.3%. In both instances, the NN reaches zero percent PE at an SNR of 10dB.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.