RRRaghu G. Raj

Raghu G. Raj

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Raghu G. Raj has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Robust and tractable multidimensional exponential analysis

    by H. N. Mhaskar, S. Kitimoon, Raghu G. Raj

    Motivated by a number of applications in signal processing, we study the following question. Given samples of a multidimensional signal of the form $$f(\varvec{\ell })=\sum _{k=1}^K a_k\exp (-i\langle \varvec{\ell }, \textbf{w}_k\rangle ), \quad \textbf{w}_1,\cdots ,\textbf{w}_k\in \mathbb {R}^q, \ \varvec{\ell }\in \mathbb {Z}^q, \ |\varvec{\ell }| <n,$$ determine the values of the number K of components, and the parameters $$a_k$$ and $$\textbf{w}_k$$ ’s. We note that the the number of samples of f in the above equation is $$(2n-1)^q$$ . We develop an algorithm to recuperate these quantities accurately using only a subsample of size $$\mathcal {O}(qn)$$ of this data. For this purpose, we use a novel localized kernel method to identify the parameters, including the number K of signals. Our method is easy to implement, and is shown to be stable under a very low SNR range. We demonstrate the effectiveness of our resulting algorithm using 2 and 3 dimensional examples from the literature, and show substantial improvements over state-of-the-art techniques including Prony based, MUSIC and ESPRIT approaches.


  • Open Access

    An LFM-Based Semiblind Synchronization Method for Bistatic Radar Imaging

    by James Park, Raghu G. Raj

    Bistatic radar provides an additional degree of freedom in the observing geometry for imaging by using a spatially separated transmitter and receiver. This capability allows the capture of scattering phenomena at various bistatic sensing angles, which helps to interpret physical characteristics of a target or scene for remote sensing and radar applications. A crucial problem associated with bistatic radar is synchronization of time and frequency between the transmitter and receiver for coherent image formation. In this paper, a model-based method to synchronization, called semi-blind synchronization, is introduced for maintaining the phase coherence of a bistatic radar system for range-Doppler processing. Specifically, semi-blind synchronization refers to bistatic synchronization where the direct path is not available or where the Global Positioning System (GPS) signal is not accurate enough, and where prior knowledge of the transmit waveform and target location are exploited during a coherent processing interval (CPI). The method focuses on error estimation and compensation based on understanding the impact of synchronization errors on the received signals. After detailing our system model and semi-blind synchronization method, we conduct a simulation study for assessing the effectiveness of our method by first introducing a variety of synchronization errors including chirp rate mismatch, time and frequency offsets. Scattering responses from a point target are simulated, and high range resolution profiles (HRRP) and range-Doppler images are formed to validate the proposed method. The simulation results demonstrate that a Linear Frequency Modulation (LFM) waveform enables us to estimate and compensate the synchronization errors considered in this paper and improve the overall quality of the bistatic range-Doppler image. Our synchronization technique has potentially broad applicability in emerging remote sensing applications using bistatic radar systems.


  • Open Access

    Deep Regularized Compound Gaussian Network for Solving Linear Inverse Problems

    by Carter Lyons, Raghu G. Raj, Margaret Cheney

    Incorporating prior information into inverse problems, e.g. via maximum-a-posteriori estimation, is an important technique for facilitating robust inverse problem solutions. In this paper, we devise two novel approaches for linear inverse problems that permit problem-specific statistical prior selections within the compound Gaussian (CG) class of distributions. The CG class subsumes many commonly used priors in signal and image reconstruction methods including those of sparsity-based approaches. The first method developed is an iterative algorithm, called generalized compound Gaussian least squares (G-CG-LS), that minimizes a regularized least squares objective function where the regularization enforces a CG prior. G-CG-LS is then unrolled, or unfolded, to furnish our second method, which is a novel deep regularized (DR) neural network, called DR-CG-Net, that learns the prior information. A detailed computational theory on convergence properties of G-CG-LS and thorough numerical experiments for DR-CG-Net are provided. Due to the comprehensive nature of the CG prior, these experiments show that DR-CG-Net outperforms competitive prior art methods in tomographic imaging and compressive sensing, especially in challenging low-training scenarios.


  • Open Access

    On Generalization Bounds for Deep Compound Gaussian Neural Networks

    by Carter Lyons, Raghu G. Raj, Margaret Cheney

    Algorithm unfolding or unrolling is the technique of constructing a deep neural network (DNN) from an iterative algorithm. Unrolled DNNs often provide better interpretability and superior empirical performance over standard DNNs in signal estimation tasks. An important theoretical question, which has only recently received attention, is the development of generalization error bounds for unrolled DNNs. These bounds deliver theoretical and practical insights into the performance of a DNN on empirical datasets that are distinct from, but sampled from, the probability density generating the DNN training data. In this paper, we develop novel generalization error bounds for a class of unrolled DNNs that are informed by a compound Gaussian prior. These compound Gaussian networks have been shown to outperform comparative standard and unfolded deep neural networks in compressive sensing and tomographic imaging problems. The generalization error bound is formulated by bounding the Rademacher complexity of the class of compound Gaussian network estimates with Dudley's integral. Under realistic conditions, we show that, at worst, the generalization error scales $\mathcal{O}(n\sqrt{\ln(n)})$ in the signal dimension and $\mathcal{O}(($Network Size$)^{3/2})$ in network size.

  • Open Access

    A Compound Gaussian Least Squares Algorithm and Unrolled Network for Linear Inverse Problems

    by Carter Lyons, Raghu G. Raj, Margaret Cheney

    For solving linear inverse problems, particularly of the type that appears in tomographic imaging and compressive sensing, this paper develops two new approaches. The first approach is an iterative algorithm that minimizes a regularized least squares objective function where the regularization is based on a compound Gaussian prior distribution. The compound Gaussian prior subsumes many of the commonly used priors in image reconstruction, including those of sparsity-based approaches. The developed iterative algorithm gives rise to the paper's second new approach, which is a deep neural network that corresponds to an "unrolling" or "unfolding" of the iterative algorithm. Unrolled deep neural networks have interpretable layers and outperform standard deep learning methods. This paper includes a detailed computational theory that provides insight into the construction and performance of both algorithms. The conclusion is that both algorithms outperform other state-of-the-art approaches to tomographic image formation and compressive sensing, especially in the difficult regime of low training.

  • A Compound Gaussian Least Squares Algorithm and Unrolled Network for Linear Inverse Problems

    by Carter Lyons, Raghu G. Raj, Margaret Cheney

    For solving linear inverse problems, particularly of the type that appears in tomographic imaging and compressive sensing, this paper develops two new approaches. The first approach is an iterative algorithm that minimizes a regularized least squares objective function where the regularization is based on a compound Gaussian prior distribution. The compound Gaussian prior subsumes many of the commonly used priors in image reconstruction, including those of sparsity-based approaches. The developed iterative algorithm gives rise to the paper’s second new approach, which is a deep neural network that corresponds to an “unrolling” or “unfolding” of the iterative algorithm. Unrolled deep neural networks have interpretable layers and outperform standard deep learning methods. This paper includes a detailed computational theory that provides insight into the construction and performance of both algorithms. The conclusion is that both algorithms outperform other state-of-the-art approaches to tomographic image formation and compressive sensing, especially in the difficult regime of low training.


  • A Computational Electromagnetics and Sparsity-Based Feature Extraction Approach to Ground-Penetrating Radar Imaging

    by Zacharie Idriss, Raghu G. Raj, Ram M. Narayanan

    In this paper, a feature extraction technique based on the electromagnetic (EM) representation of radar signals is presented. In particular, we focus on ground-penetrating radar (GPR) imaging, where we model the backscatter from varying 2-D geometric shapes with arbitrary local coordinate rotations. Due to the electrically small nature of buried targets and the bending of the radar signal at the air–soil interface, we focus on exact methods to model the surface current density induced on scattering surfaces. Overcomplete basis sets are derived from the EM descriptions to represent the scene sparsely. From this proposed modeling framework, we devise a novel methodology to exploit the prediction of scattering behavior to extract features for classification from radar scenes when multiple buried scattering surfaces are present. We see that our method can identify and reconstruct buried scattering geometries in the presence of false targets that are brought about by the nonlinear nature of the exact EM modeling methods. A noniterative algorithm based on the conjugate of Green’s function is developed to solve for the surface current in an unknown domain using multifrequency, multiaperture data. Our modeling and feature extraction algorithms are numerically validated for different target shapes buried in lossy soil profiles.


  • Nonparametric Decentralized Detection and Sparse Sensor Selection via Multi-Sensor Online Kernel Scalar Quantization

    by Jing Guo, Raghu G. Raj, David J. Love, Christopher G. Brinton

    Signal classification problems arise in a wide variety of applications, and their demand is only expected to grow. In this paper, we focus on the wireless sensor network signal classification setting, where each sensor forwards quantized signals to a fusion center to be classified. Our primary goal is to train a decision function and quantizers across the sensors to maximize the classification performance in an online manner. Moreover, we are interested in sparse sensor selection using a marginalized weighted kernel approach to improve network resource efficiency by disabling less reliable sensors with minimal effect on classification performance. To achieve our goals, we develop a multi-sensor online kernel scalar quantization (MSOKSQ) learning strategy that operates on the sensor outputs at the fusion center. Our theoretical analysis reveals how the proposed algorithm affects the quantizers across the sensors. Additionally, we provide a convergence analysis of our online learning approach by studying its relationship to batch learning. We conduct numerical studies under different classification and sensor network settings which demonstrate the accuracy gains from optimizing different components of MSOKSQ and robustness to reduction in the number of sensors selected.


  • Multilook Polarimetric 3-D Interferometric ISAR Imaging

    by James Park, Raghu G. Raj, Marco Martorella, Elisa Giusti

    This paper introduces polarimetric 3-D interferometric inverse synthetic aperture radar (ISAR) imaging process using multiple phase centers via a spatio-sensor multilook algorithm. This approach enables one to take effective advantage of polarimetric scattering mechanisms in 3-D target representations, which may improve target classification and identification. In addition, the multilook algorithm enhances the accuracy of height estimation in noisy conditions. The 3-D interferometric ISAR (InISAR) imaging process is validated using the backhoe synthetic data released by the Air Force Research Laboratory (AFRL).


  • MSAR-Net: A Deep Learning Based Classification Approach for Learning the Maritime Environment

    by Robert W. Jansen, Raghu G. Raj

    We develop an end-to-end deep learning-based approach for the classification of complex maritime environments via multichannel synthetic aperture radar (MSAR) sensors. In particular, we introduce a novel convolutional neural network (CNN)-based multichannel structure that incorporates a divisive normalization technique that is critical for achieving consistent classification performance across maritime scenes. We evaluate the performance of our technique, called MSAR-Net, using datasets collected by the U.S. Naval Research Laboratory’s experimental airborne MSAR system. Our results demonstrate that MSAR-Net achieves consistently and substantially superior performance compared to conventional amplitude-based scene classification. Finally, though we focus on the specific (yet difficult) problem of maritime surveillance, MSAR-Net, introduced in this article, is a fundamental technique that can potentially result in significant performance improvements in a variety of multichannel surveillance and remote sensing applications.