Multiple Radar Subbands Fusion Algorithm Based on Support Vector Regression in Complex Noise Environment

Zhang, Ying; Wang, Tingjing; Zhao, Huapeng; Zhang, Yanxin; Zhao, Hua

doi:10.1109/tap.2017.2769135

Cited by 22 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, it has also been shown to give excellent performance in the prediction of time series and has been successfully applied to the prediction of nonlinear chaotic time series. In this paper, SVR [30]- [31] is used to analyze and predict the time series X . The training sample is the first 250 data for the time series X , and the test sample is the last 115 data for the time series X .…”

Section: The Prediction Algorithms a The Support Vector Regressionmentioning

confidence: 99%

See 1 more Smart Citation

A New Short-Term Prediction Method for Estimation of the Evaporation Duct Height

et al. 2020

View full text Add to dashboard Cite

Evaporation duct is a kind of chaotic phenomenon over the ocean. In this paper, a new nonlinear prediction algorithm, the Darwinian evolutionary algorithm (DEA), is introduced to obtain the specific nonlinear formula P(•) of the chaotic phenomenon. Based on Darwinian natural selection and survival theory, the method first selects a suitable training set of samples, and then produces an initial population before going through an evolutionary process of selection, reproduction and mutation until the optimal individual is found. Finally, a specific expression for a nonlinear chaotic time series is obtained, which can realize the short-term prediction of evaporation duct height (EDH) quickly and accurately. After that, the DEA, the support vector regression (SVR), and the back propagation (BP) neural network were applied to predict the EDH which were formed over the ocean by using sounding data. After interpolation and smoothing of the original data, we selected the first 250 data as training samples and the last 115 data as test samples to test the effect of the EDA algorithm. The results showed that the root mean squared error (RMSE) for the DEA was about 7% less than that of the SVR and 10% less than that of BP neural network; the mean absolute percent error (MAPE) for the DEA was about 9% less than that of the SVR and 15% less than that of BP neural network. In addition, the DEA obtained, for the first time, a nonlinear expression for EDH, which provides an important reference for future research on the evaporation ducts.

show abstract

Section: The Prediction Algorithms a The Support Vector Regressionmentioning

confidence: 99%

“…For time series {X (t i )}, i = 1, • • • N , the algorithm can be regarded as the output of a deterministic nonlinear autonomous dynamic system [27]; [29]- [30], which satisfies:…”

Section: Darwinian Evolutionary Algorithm 1) Introduction To Darwinia...mentioning

confidence: 99%

A New Short-Term Prediction Method for Estimation of the Evaporation Duct Height

et al. 2020

View full text Add to dashboard Cite

show abstract

“…over a constructed overcomplete dictionary [5] and the support vector regression [6] are also used to compute signal poles of the AR model. In addition, a fusion method that combines the all-phase fast Fourier transform (FT) and the iterative adaptive approach [8] was proposed to fuse the dechirped multiband signals, which is more dedicated to the linear frequency modulated signals.…”

Section: Wavenumber-domain Multiband Signalmentioning

confidence: 99%

Wavenumber-Domain Multiband Signal Fusion With Matrix-Pencil Approach for High-Resolution Imaging

Wang

Aubry

Yarovoy

2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

In this paper, a wavenumber-domain matrix-pencilbased multiband signal fusion approach was proposed for multiband microwave imaging. The approach proposed is based on the Born approximation of the field scattered from a target resulting in the fact that in a given scattering direction, the scattered field can be represented over the whole frequency band as a sum of the same number of contributions. Exploiting the measured multiband data and taking advantage of the parametric modeling for the signals in a radial direction, a unified signal model can be estimated for a large bandwidth in the wavenumber domain. It can be used to fuse the signals at different subbands by extrapolating the missing data in the frequency gaps between them or coherently integrating the overlaps between the adjacent subbands, thus synthesizing an equivalent wideband signal spectrum. Taking an inverse Fourier transform, the synthesized spectrum results in a focused image with improved resolution. Compared with the space-time domain fusion methods, the proposed approach is applicable for radar imaging with the signals collected by either collocated or noncollocated arrays in different frequency bands. Its effectiveness and accuracy are demonstrated through both numerical simulations and experimental imaging results.Index Terms-Matrix-pencil approach (MPA), microwave imaging, multiband signal, signal fusion, wavenumber domain. I. INTRODUCTIONM ICROWAVE imaging has been widely used for nondestructive testing, security check, medical imaging, remote sensing, and so on. In these applications, imaging radar systems generally exploit wideband signals and antenna arrays to achieve high resolution in both downrange and cross-range directions. As downrange resolution is inversely proportional to the operational signal bandwidth of the imaging system, signals with several gigahertz or even larger bandwidth are required to achieve cm/sub-cm level resolutions, especially for short-range applications. To emit and receive such wideband signals, ultrawideband (UWB) antennas and front ends are needed. Vector network analyzers (VNAs)

show abstract

“…High-resolution inverse synthetic aperture radar (ISAR) images can provide information such as the size and geometric structure of targets, which is conducive to target recognition and classification [1][2][3][4]. In a monostatic ISAR imaging system, the range resolution and azimuth resolution are restricted by the limited transmitting bandwidth and observation angle, respectively [5,6]. e multiradar fusion imaging technology is utilized to fuse multiangle and multiband echo data measured by multiple radars with different frequency bands at different observation angles to improve the two-dimensional resolution of images [7].…”

Section: Introductionmentioning

confidence: 99%

Two-Dimensional ISAR Fusion Imaging of Block Structure Targets

Zhu

Liu

Guo

et al. 2021

International Journal of Antennas and Propagation

View full text Add to dashboard Cite

The range resolution and azimuth resolution are restricted by the limited transmitting bandwidth and observation angle in a monostatic radar system. To improve the two-dimensional resolution of inverse synthetic aperture radar (ISAR) imaging, a fast linearized Bregman iteration for unconstrained block sparsity (FLBIUB) algorithm is proposed to achieve multiradar ISAR fusion imaging of block structure targets. First, the ISAR imaging echo data of block structure targets is established based on the geometrical theory of the diffraction model. The multiradar ISAR fusion imaging is transformed into a signal sparse representation problem by vectorization operation. Then, considering the block sparsity of the echo data of block structure targets, the FLBIUB algorithm is utilized to achieve the block sparse signal reconstruction and obtain the fusion image. The algorithm further accelerates the iterative convergence speed and improves the imaging efficiency by combining the weighted back-adding residual and condition number optimization of the basis matrix. Finally, simulation experiments show that the proposed method can effectively achieve block sparse signal reconstruction and two-dimensional multiradar ISAR fusion imaging of block structure targets.

show abstract

Multiple Radar Subbands Fusion Algorithm Based on Support Vector Regression in Complex Noise Environment

Cited by 22 publications

References 23 publications

A New Short-Term Prediction Method for Estimation of the Evaporation Duct Height

A New Short-Term Prediction Method for Estimation of the Evaporation Duct Height

Wavenumber-Domain Multiband Signal Fusion With Matrix-Pencil Approach for High-Resolution Imaging

Two-Dimensional ISAR Fusion Imaging of Block Structure Targets

Contact Info

Product

Resources

About