BKBosung Kang

Bosung Kang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bosung Kang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Approximate MLE of High-Dimensional STAP Covariance Matrices With Banded and Spiked Structure—A Convex Relaxation Approach

    by Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Sandeep Gogineni, Bosung Kang, Sean M. O'ROurke

    Estimating the clutter-plus-noise covariance matrix in high-dimensional (stap) is challenging in the presence of Internal Clutter Motion (ICM) and a high noise floor. The problem becomes more difficult in low-sample regimes, where the Sample Covariance Matrix (SCM) becomes ill-conditioned. To capture the ICM and high noise floor, we model the covariance matrix using a “Banded+Spiked” structure. Since the Maximum Likelihood Estimation (MLE) for this model is non-convex, we propose a convex relaxation which is formulated as a Frobenius norm minimization with non-smooth convex constraints enforcing banded sparsity. This relaxation serves as a provable upper bound for the non-convex likelihood maximization and extends to cases where the covariance matrix dimension exceeds the number of samples. We derive a variational inequality-based bound to assess its quality. We introduce an algorithm to jointly estimate the banded clutter covariance and noise power. Additionally, we establish conditions ensuring the estimated covariance matrix remains positive definite and the bandsize is accurately recovered. Numerical results using the high-fidelity RFView radar simulation environment demonstrate that our algorithm achieves a higher Signal–to–Clutter–plus–Noise Ratio (SCNR) than state–of–the–art methods, including TABASCO, Spiked Covariance Stein Shrinkage, and Diagonal Loading, particularly when the covariance matrix dimension exceeds the number of samples.


  • Open Access

    Approximate MLE of High-Dimensional STAP Covariance Matrices with Banded & Spiked Structure -- A Convex Relaxation Approach

    by Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Sandeep Gogineni, Bosung Kang, Sean M. O'Rourke

    Estimating the clutter-plus-noise covariance matrix in high-dimensional STAP is challenging in the presence of Internal Clutter Motion (ICM) and a high noise floor. The problem becomes more difficult in low-sample regimes, where the Sample Covariance Matrix (SCM) becomes ill-conditioned. To capture the ICM and high noise floor, we model the covariance matrix using a ``Banded+Spiked'' structure. Since the Maximum Likelihood Estimation (MLE) for this model is non-convex, we propose a convex relaxation which is formulated as a Frobenius norm minimization with non-smooth convex constraints enforcing banded sparsity. This relaxation serves as a provable upper bound for the non-convex likelihood maximization and extends to cases where the covariance matrix dimension exceeds the number of samples. We derive a variational inequality-based bound to assess its quality. We introduce a novel algorithm to jointly estimate the banded clutter covariance and noise power. Additionally, we establish conditions ensuring the estimated covariance matrix remains positive definite and the bandsize is accurately recovered. Numerical results using the high-fidelity RFView radar simulation environment demonstrate that our algorithm achieves a higher Signal-to-Clutter-plus-Noise Ratio (SCNR) than state-of-the-art methods, including TABASCO, Spiked Covariance Stein Shrinkage, and Diagonal Loading, particularly when the covariance matrix dimension exceeds the number of samples.

  • Fisher Information Approach for Masking the Sensing Plan: Applications in Multifunction Radars

    by Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Bosung Kang, Sandeep Gogineni

    How to design a Markov Decision Process (MDP) based radar controller that makes small sacrifices in performance to mask its sensing plan from an adversary? The radar controller purposefully minimizes the Fisher information of its emissions so that an adversary cannot identify the controller's model parameters accurately. Unlike classical open loop statistical inference, where the Fisher information serves as a lower bound for the achievable covariance, this paper employs the Fisher information as a design constraint for a closed loop radar controller to mask its sensing plan. We analytically derive a closed-form expression for the determinant of the Fisher Information Matrix (FIM) pertaining to the parameters of the MDP-based controller. Subsequently, we formulate an MDP which is regularized by the determinant of the adversary's FIM. This results in the perturbations to total cost of operation, stateaction costs, and the transition matrix. Additionally, we propose a Maximum Entropy-based convex lower bound for the FIMconstrained MDP, whose solution can serve as an initialization point for the proposed nonlinear optimization problem. This convex lower bound aligns with existing work that employs the same Maximum Entropy criteria to mask the sensing plan. Numerical results show that the introduction of minor perturbations to the MDP's stateaction costs, transition kernel and the total operation cost can reduce the Fisher Information of the emissions. Consequently, this reduction amplifies the variability in policy and transition kernel estimation errors, thwarting the adversary's accuracy in estimating the controller's sensing plan. We demonstrate this by comparing the error in the estimate of the transition kernel under different criteria: the FIM criteria, the Maximum Entropy criteria, a sensing plan where actions are chosen uniformly, and the unmasked sensing plan.


  • Open Access

    Data‐driven target localization using adaptive radar processing and convolutional neural networks

    by Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang, Ali Pezeshki, Muralidhar Rangaswamy, Vahid Tarokh

    Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data‐driven approach to improve accuracy in radar target localization post adaptive radar detection. To this end, we generate a large number of radar returns by randomly placing targets of variable strengths in a predefined area, using RFView ® , a high‐fidelity, site‐specific, RF modeling & simulation tool. We produce heatmap tensors from the radar returns, in range, azimuth [and Doppler], of the normalized adaptive matched filter (NAMF) test statistic. We then train a regression convolutional neural network (CNN) to estimate target locations from these heatmap tensors, and we compare the target localization accuracy of this approach with that of peak‐finding and local search methods. This empirical study shows that our regression CNN achieves a considerable improvement in target location estimation accuracy. The regression CNN offers significant gains and reasonable accuracy even at signal‐to‐clutter‐plus‐noise ratio (SCNR) regimes that are close to the breakdown threshold SCNR of the NAMF. We also study the robustness of our trained CNN to mismatches in the radar data, where the CNN is tested on heatmap tensors collected from areas that it was not trained on. We show that our CNN can be made robust to mismatches in the radar data through few‐shot learning, using a relatively small number of new training samples.


  • Open Access

    Data-Driven Target Localization: Benchmarking Gradient Descent Using the Cramer-Rao Bound

    by Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang, Muralidhar Rangaswamy

    In modern radar systems, precise target localization using azimuth and velocity estimation is paramount. Traditional unbiased estimation methods have utilized gradient descent algorithms to reach the theoretical limits of the Cramer Rao Bound (CRB) for the error of the parameter estimates. As an extension, we demonstrate on a realistic simulated example scenario that our earlier presented data-driven neural network model outperforms these traditional methods, yielding improved accuracies in target azimuth and velocity estimation. We emphasize, however, that this improvement does not imply that the neural network outperforms the CRB itself. Rather, the enhanced performance is attributed to the biased nature of the neural network approach. Our findings underscore the potential of employing deep learning methods in radar systems to achieve more accurate localization in cluttered and dynamic environments.

  • Open Access

    Data-Driven Target Localization Using Adaptive Radar Processing and Convolutional Neural Networks

    by Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang, Ali Pezeshki, Muralidhar Rangaswamy, Vahid Tarokh

    Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data-driven approach to improve accuracy in radar target localization post adaptive radar detection. To this end, we generate a large number of radar returns by randomly placing targets of variable strengths in a predefined area, using RFView, a high-fidelity, site-specific, RF modeling & simulation tool. We produce heatmap tensors from the radar returns, in range, azimuth [and Doppler], of the normalized adaptive matched filter (NAMF) test statistic. We then train a regression convolutional neural network (CNN) to estimate target locations from these heatmap tensors, and we compare the target localization accuracy of this approach with that of peak-finding and local search methods. This empirical study shows that our regression CNN achieves a considerable improvement in target location estimation accuracy. The regression CNN offers significant gains and reasonable accuracy even at signal-to-clutter-plus-noise ratio (SCNR) regimes that are close to the breakdown threshold SCNR of the NAMF. We also study the robustness of our trained CNN to mismatches in the radar data, where the CNN is tested on heatmap tensors collected from areas that it was not trained on. We show that our CNN can be made robust to mismatches in the radar data through few-shot learning, using a relatively small number of new training samples.

  • Radar Clutter Covariance Estimation: A Nonlinear Spectral Shrinkage Approach

    by Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Bosung Kang, Sandeep Gogineni

    In this paper, we exploit the spiked covariance structure of the clutter plus noise covariance matrix for radar signal processing. Using state-of-the-art techniques high dimensional statistics, we propose a nonlinear shrinkage-based rotation invariant spiked covariance matrix estimator. We state the convergence of the estimated spiked eigenvalues. We use a dataset generated from the high-fidelity, site-specific physics-based radar simulation software RFView to compare the proposed algorithm against the existing Rank Constrained Maximum Likelihood (RCML)-Expected Likelihood (EL) covariance estimation algorithm. We demonstrate that the computation time for the estimation by the proposed algorithm is less than the RCML-EL algorithm with identical Signal to Clutter plus Noise (SCNR) performance. We show that the proposed algorithm and the RCML-EL-based algorithm share the same optimization problem in high dimensions. We use Low-Rank Adaptive Normalized Matched Filter (LR-ANMF) detector to compute the detection probabilities for different false alarm probabilities over a range of target SNR. We present preliminary results which demonstrate the robustness of the detector against contaminating clutter discretes using the Challenge Dataset from RFView. Finally, we empirically show that the minimum variance distortionless beamformer (MVDR) error variance for the proposed algorithm is identical to the error variance resulting from the true covariance matrix


  • Open Access

    Radar Clutter Covariance Estimation: A Nonlinear Spectral Shrinkage Approach

    by Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Bosung Kang, Sandeep Gogineni

    In this paper, we exploit the spiked covariance structure of the clutter plus noise covariance matrix for adaptive radar signal processing. Using state-of-the-art techniques from mathematical finance and high dimensional statistics we propose a non-linear shrinkage-based rotation invariant spiked covariance matrix estimator. We compare the proposed estimator with Rank Constrained Maximum Likelihood (RCML)-Expected Likelihood (EL) covariance estimator using the Challenge dataset generated from RFView. We demonstrate that the computation-time for the proposed estimator is less than the RCML-EL estimator with identical Signal to Clutter plus Noise (SCNR) performance for the Challenge dataset. We derive the lower bound and upper bound for the normalized SCNR and empirically show that RCML-EL and the proposed estimator perform within these derived bounds for the Challenge dataset. We state the convergence for the spiked eigenvalues of the estimator.

  • Open Access

    Subspace Perturbation Analysis for Data-Driven Radar Target Localization

    by Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang, Ali Pezeshki, Muralidhar Rangaswamy, Vahid Tarokh

    Recent works exploring data-driven approaches to classical problems in adaptive radar have demonstrated promising results pertaining to the task of radar target localization. Via the use of space-time adaptive processing (STAP) techniques and convolutional neural networks, these data-driven approaches to target localization have helped benchmark the performance of neural networks for matched scenarios. However, the thorough bridging of these topics across mismatched scenarios still remains an open problem. As such, in this work, we augment our data-driven approach to radar target localization by performing a subspace perturbation analysis, which allows us to benchmark the localization accuracy of our proposed deep learning framework across mismatched scenarios. To evaluate this framework, we generate comprehensive datasets by randomly placing targets of variable strengths in mismatched constrained areas via RFView, a high-fidelity, site-specific modeling and simulation tool. For the radar returns from these constrained areas, we generate heatmap tensors in range, azimuth, and elevation using the normalized adaptive matched filter (NAMF) test statistic. We estimate target locations from these heatmap tensors using a convolutional neural network, and demonstrate that the predictive performance of our framework in the presence of mismatches can be predetermined.

  • Open Access

    Adaptive channel estimation for cognitive fully adaptive radar

    by Bosung Kang, Sandeep Gogineni, Muralidhar Rangaswamy, Joseph R. Guerci, Erik Blasch

    The paper addresses channel state information estimation for a cognitive radar system. The underlying radar signal model considered in this paper is based on a stochastic Green's function approach. In the radar model, the clutter returns can be expressed as a convolution of the stochastic Green's function impulse response with the transmit radar waveform. The paper proposes and solves constrained channel estimation algorithms that exploit the cosine similarity constraint and the inner product constraint to improve conventional least squares solutions. Using the fact that adjacent channel transfer functions have a close relationship in terms of a cosine similarity metric, the cosine similarity constraint can be exploited in the least squares problem. It turns out that the derived optimisation problem under the cosine similarity constraint is non‐convex. However, since strong duality holds for the non‐convex optimisation problem, it can be solved using the semi‐definite relaxation (SDR) approach. The paper also proposes a new optimisation problem with an additional inner product constraint, which results in a convex second‐order cone programming (SOCP) and is robust to the signal‐to‐noise ratio (SNR) in terms of the cosine similarity measurement. Numerical simulations are provided to verify the performance of the proposed methods on a challenge dataset generated using the high‐fidelity modelling and simulation tool, RFView ® .