Mohammad Reza Jabbari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohammad Reza Jabbari has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Saeed Gazor
Department of Electrical and Computer Engineering, Queens University, Kingston, ON, Canada
3 shared publications - Mohammad Reza Taban
Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran
2 shared publications - Cagatay Edemen
Ozyegin University
1 shared publication - Hossein Nikaein
Research Institute for Information and Communication Technology, Isfahan University of Technology, Isfahan, Iran
1 shared publication - Mehrdad Kaimasi
Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran
1 shared publication Mohadeseh Eslamifard
Department of Electrical and Computer Engineering Isfahan University of Technology (IUT) Isfahan Iran
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (22) , 34582-34597
Moving-Target Localization in Distributed UAV Networks With Sensor-Parameter Uncertainties
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (22) , 34582-34597
Moving-Target Localization in Distributed UAV Networks With Sensor-Parameter Uncertainties
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 4, 586-596
Moving Target Detection Using Passive Bistatic Radars in Presence of Interfering Target and I/Q Imbalances
This paper addresses moving target detection in the presence of an Interfering Target (IT) using Passive Bistatic Radar (PBR) systems affected by hardware mismatches. We focus on In-phase/Quadrature-phase Imbalances (IQIs) common in Direct-Conversion Receivers (DCRs), where IT echoes mask the Main Target (MT). When unmitigated, both effects significantly degrade detection performance. Unlike existing approaches, we assume unknown noise power and unknown target Doppler Shifts (DSs), further increasing the detection challenge. We develop a new signal model for this scenario, formulate a Binary Composite Hypothesis Testing (BCHT) problem, and derive a closed-form asymptotically optimal Generalized Likelihood Ratio Test (GLRT) detector using the Neyman-Pearson criterion. To improve computational efficiency, we exploit Fast Fourier Transform (FFT) symmetry properties and employ batch data processing, substantially reducing computational complexity and execution time. We also analyze the impact of amplitude and phase mismatches on the PBR signal model. Theoretical analysis and simulations demonstrate improved detection probability and enhanced robustness to IQI compared with state-of-the-art methods.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 4, 586-596
Moving Target Detection Using Passive Bistatic Radars in Presence of Interfering Target and I/Q Imbalances
This paper addresses moving target detection in the presence of an Interfering Target (IT) using Passive Bistatic Radar (PBR) systems affected by hardware mismatches. We focus on In-phase/Quadrature-phase Imbalances (IQIs) common in Direct-Conversion Receivers (DCRs), where IT echoes mask the Main Target (MT). When unmitigated, both effects significantly degrade detection performance. Unlike existing approaches, we assume unknown noise power and unknown target Doppler Shifts (DSs), further increasing the detection challenge. We develop a new signal model for this scenario, formulate a Binary Composite Hypothesis Testing (BCHT) problem, and derive a closed-form asymptotically optimal Generalized Likelihood Ratio Test (GLRT) detector using the Neyman-Pearson criterion. To improve computational efficiency, we exploit Fast Fourier Transform (FFT) symmetry properties and employ batch data processing, substantially reducing computational complexity and execution time. We also analyze the impact of amplitude and phase mismatches on the PBR signal model. Theoretical analysis and simulations demonstrate improved detection probability and enhanced robustness to IQI compared with state-of-the-art methods.
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
Heatmap‐Guided Attention Networks for Automatic Segmentation in Lung Computed Tomography Images
In this paper, we propose an automatic image segmentation (AIS) framework for medical imaging that integrates a heatmap attention mechanism (HMAM) into two deep neural network (DNN) architectures: U‐Net and generative adversarial networks (GANs). This HMAM guides the segmentation process by incorporating targeted spatial information that directs the networks toward clinically relevant regions. Heatmaps are generated using a modified VGG16 network, and the learned filters are subsequently transferred to conventional DNNs, whose activations provide complementary spatial guidance during segmentation. Furthermore, we develop two GAN‐based segmentation models that employ a U‐Net architecture and a U‐shaped modified VGG16 architecture as generator networks. In these models, the HMAM is incorporated exclusively into the generator network (GN), rather than the discriminator network (DN), because the GN directly produces the pixel‐wise segmentation mask and is therefore expected to benefit more from spatial guidance. The proposed methods are evaluated using COVID‐19 lung computed tomography (CT) images. Experimental results demonstrate consistent improvements over matched conventional baselines, particularly under limited‐data conditions. For example, the mean dice score of the U‐Net architecture increased from 61.05% to 70.49% on the larger data split and from 73.80% to 84.12% on the smaller split. Similarly, the proposed GAN‐based models achieved substantial performance gains, with the mean dice score increasing from 55.87% to 67.90% for the U‐Net‐based generator and from 58.11% to 78.61% for the VGG16‐based generator.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
Open AccessHeatmap‐Guided Attention Networks for Automatic Segmentation in Lung Computed Tomography Images
In this paper, we propose an automatic image segmentation (AIS) framework for medical imaging that integrates a heatmap attention mechanism (HMAM) into two deep neural network (DNN) architectures: U‐Net and generative adversarial networks (GANs). This HMAM guides the segmentation process by incorporating targeted spatial information that directs the networks toward clinically relevant regions. Heatmaps are generated using a modified VGG16 network, and the learned filters are subsequently transferred to conventional DNNs, whose activations provide complementary spatial guidance during segmentation. Furthermore, we develop two GAN‐based segmentation models that employ a U‐Net architecture and a U‐shaped modified VGG16 architecture as generator networks. In these models, the HMAM is incorporated exclusively into the generator network (GN), rather than the discriminator network (DN), because the GN directly produces the pixel‐wise segmentation mask and is therefore expected to benefit more from spatial guidance. The proposed methods are evaluated using COVID‐19 lung computed tomography (CT) images. Experimental results demonstrate consistent improvements over matched conventional baselines, particularly under limited‐data conditions. For example, the mean dice score of the U‐Net architecture increased from 61.05% to 70.49% on the larger data split and from 73.80% to 84.12% on the smaller split. Similarly, the proposed GAN‐based models achieved substantial performance gains, with the mean dice score increasing from 55.87% to 67.90% for the U‐Net‐based generator and from 58.11% to 78.61% for the VGG16‐based generator.
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 9, 569-580
Asymptotically Efficient Moving Target Localization in Distributed Radar Networks
In this paper, we investigate the joint estimation of the position and velocity of a moving target in distributed networks of moving radars using Time Of Arrival (TOA) and Doppler Shift (DS) measurements. In contrast to most of the existing/recent methods, we avoid the use of Nuisance Variables (NVs) by employing algebraic manipulations. We reformulate a new set of equations that are linear with respect to the target's position and velocity, resulting in a significant performance improvement. Subsequently, we propose a Two-Stage Weighted Least Squares (TSWLS) estimator and recommend two alternative algorithms to reduce computational complexity while preserving the accuracy by selecting either a transmitter or receiver as the reference sensor. We implement the proposed method over fully and partially connected networks. Our theoretical derivations and numerical simulations reveal that the proposed estimators are asymptotically efficient, i.e., they attain the CRLB, at relatively high noise levels. Moreover, the simulation results show that the proposed methods outperform state-of-the-art algorithms.
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 9, 569-580
Asymptotically Efficient Moving Target Localization in Distributed Radar Networks
In this paper, we investigate the joint estimation of the position and velocity of a moving target in distributed networks of moving radars using Time Of Arrival (TOA) and Doppler Shift (DS) measurements. In contrast to most of the existing/recent methods, we avoid the use of Nuisance Variables (NVs) by employing algebraic manipulations. We reformulate a new set of equations that are linear with respect to the target's position and velocity, resulting in a significant performance improvement. Subsequently, we propose a Two-Stage Weighted Least Squares (TSWLS) estimator and recommend two alternative algorithms to reduce computational complexity while preserving the accuracy by selecting either a transmitter or receiver as the reference sensor. We implement the proposed method over fully and partially connected networks. Our theoretical derivations and numerical simulations reveal that the proposed estimators are asymptotically efficient, i.e., they attain the CRLB, at relatively high noise levels. Moreover, the simulation results show that the proposed methods outperform state-of-the-art algorithms.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21640-21651
An Asymptotically Efficient Hyperbolic Localization of a Moving Target by a Distributed Radar Network With Sensors Uncertainties
This paper addresses the moving target localization in a distributed radar network (DRN) with sensor uncertainties. It is assumed that the positions and velocities of the sensors are independent normal random variables with known means and variances. Assuming reference sensors on both sides of transmitters (Txs) and receivers (Rxs), we convert the elliptical localization to a hyperbolic localization problem. We introduce nuisance variables (NVs), remove dependent hyperbolic equations, establish a pseudo-linear system, and solve it by a two-stage weighted least squares (TSWLS) estimator. Subsequently, we propose two alternative estimators to reduce the computational complexity while preserving the accuracy by selecting hyperbolas either at Txs or at Rxs. Moreover, we investigate the impact of the number and type of NVs on localization performance. Numerical simulations confirm our theoretical results and indicate that utilizing all NVs and applying averaging techniques to eliminate dependent hyperbolas produce the most accurate estimate. In addition, our proposed method has several advantages over state-of-the-art competitive methods: i) Its performance is maintained and remains closer to the CRLB in different random configurations of sensors and relative motions of the sensors and the target; ii) It is asymptotically efficient, achieving the CRLB up to relatively high noise levels (around 32 dB) and uncertainty levels (around 20 dB); iii) It has similar order of complexity as other methods and performs satisfactorily under practical real-time scenarios; iv) It involves more independent equations and leads to a significant improvement in accuracy, particularly when the number of Txs or Rxs dominates the other.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21640-21651
An Asymptotically Efficient Hyperbolic Localization of a Moving Target by a Distributed Radar Network With Sensors Uncertainties
This paper addresses the moving target localization in a distributed radar network (DRN) with sensor uncertainties. It is assumed that the positions and velocities of the sensors are independent normal random variables with known means and variances. Assuming reference sensors on both sides of transmitters (Txs) and receivers (Rxs), we convert the elliptical localization to a hyperbolic localization problem. We introduce nuisance variables (NVs), remove dependent hyperbolic equations, establish a pseudo-linear system, and solve it by a two-stage weighted least squares (TSWLS) estimator. Subsequently, we propose two alternative estimators to reduce the computational complexity while preserving the accuracy by selecting hyperbolas either at Txs or at Rxs. Moreover, we investigate the impact of the number and type of NVs on localization performance. Numerical simulations confirm our theoretical results and indicate that utilizing all NVs and applying averaging techniques to eliminate dependent hyperbolas produce the most accurate estimate. In addition, our proposed method has several advantages over state-of-the-art competitive methods: i) Its performance is maintained and remains closer to the CRLB in different random configurations of sensors and relative motions of the sensors and the target; ii) It is asymptotically efficient, achieving the CRLB up to relatively high noise levels (around 32 dB) and uncertainty levels (around 20 dB); iii) It has similar order of complexity as other methods and performs satisfactorily under practical real-time scenarios; iv) It involves more independent equations and leads to a significant improvement in accuracy, particularly when the number of Txs or Rxs dominates the other.