Lpi Radar Waveform Classification Using Binary Svm and Multi-Class Svm Based on Principal Components of Tfi

Abstract

Since cognition has become an important topic in Electronic Warfare(EW) systems, Electronic Support Measures (ESM) are used to monitor, interceptand analyze radar signals. Low Probability of Intercept (LPI) radars are preferredto be able to detect targets without being detected by ESM systems. Because of theirproperties as low power, variable frequency, wide bandwidth, LPI Radarwaveforms are difficult to intercept with ESM systems. In addition to intercepting,the determination of the waveform types used by the LPI Radars is also veryimportant for applying counter-measures against these radars. In this study, asolution for the LPI Radar waveform recognition is proposed. The solution is basedon the training of Support Vector Machine (SVM) after applying PrincipalComponent Analysis (PCA) to the data obtained by Time-Frequency Images (TFI).TFIs are generated using Choi-Williams Distribution. High energy regions on theseimages are cropped automatically and then resized to obtain uniform data set. Toobtain the best result in SVM, the SVM Hyper-Parameters are also optimized.Results are obtained by using one-against-all and one-against-one methods. Betterclassification performance than those given in the literature has been obtainedespecially for lower Signal to Noise Ratio (SNR) values. The cross-validated resultsobtained are compared with the best results in the literature.