Search

This study explored a novel method based on eigenvalue decomposition (EVD) and independent component analysis (ICA) to separate the multi-component radar signal in the single channel. By exploiting the generalized periodicity of the radar signal, the proposed method structures the multi-dimensional matrix from the observed signal in single-channel through EVD, then applies ICA to the matrix to determine the basic waveform of each component, and finally reconstructs the component signals. Simulation results confirmed the effectiveness of the proposed method and compared it with other methods, although the performance of proposed approach is a bit worse than some other method when processing radar signals, the most outstanding advantage of the proposed approach is that it does not require any other known conditions, and it can recover the component signals with a satisfactory level, so it can yet be regarded as an effective method. [ABSTRACT FROM AUTHOR]

This paper proposes an approach of single channel source separation and parameter estimation of multi-component PRBCPM-SFM (pseudo-random binary code phase modulated sinusoidal frequency modulation) signal. By transforming all components to SFM signals through square calculation, we may then apply singular value decomposition to determine the generalized period and the modulation frequency of the SFM signal. The modulation index and carrier frequency are determined by searching for discrete points and optimizing calculations. The initial phase can be determined by calculating the inner product. Finally, given that the pseudo-random binary code is a real signal, the PN (Pseudo-noise) sequence and the amplitude can be estimated. Our proposed method can estimate the SNR by using the method of subspace-based decomposition, and the estimated SNR can be used to adaptively stop separation. Experimental results demonstrate the algorithm's performance. [ABSTRACT FROM AUTHOR]

Signal recognition technology is a currently active area in both civilian and military applications. Recently, deep learning has aroused extensive attempts in radar signal recognition due to its remarkable capability of automatic feature extraction. However, existing radar signal recognition networks overly depend on the probability-based decision model, resulting in poor robustness. This paper develops a novel deep metric learning frame to enhance the robustness of the recognition system. First, a multiscale atrous pyramid network (MAPNet) is proposed to efficiently learn high-resolution and distinct feature representation. Second, a variance loss is designed to constrain the intra-class feature distribution in metric space. Third, according to the distribution of training signals in metric space, recognition results are recalibrated to provide explicit rejection probabilities for unknowns. Extensive experiments and evaluations demonstrate that the proposed model can accurately classify known signals while robustly identifying unknown signals. The signal database and model can be freely accessed at https://github.com/bryantky/MAPNet. [ABSTRACT FROM AUTHOR]

The interference environment faced by Ultra-wideband (UWB) cognitive radar has the characteristics of wide bandwidth and extensive dynamic range. For that, a higher sampling rate is required for spectrum sensing. The current coprime sampling scheme can significantly reduce the sampling rate and show a high degree of freedom. However, the virtual co-array generated by coprime sampling has certain missing elements, leading to errors and the lack of spectral estimation information. This paper proposes a delayed coprime sampling scheme to supplement missing elements in virtual co-arrays to increase degrees of freedom. The regularity of the holes and the selection of suitable delay factors are also presented. The simulation results show that the proposed method can further improve the degree of freedom and theoretically achieve the maximum degree of freedom of a fixed sample. The precision of the spectrum estimation is also improved since the data generated by the proposed method can be used to estimate the existing elements in the virtual co-array. [ABSTRACT FROM AUTHOR]