Laleh Badriasl
Laleh Badriasl has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Anthony Finn
School of Electrical and Mechanical Engineering, Adelaide University, Adelaide, Australia
4 shared publications - Sanjeev Arulampalam
Platforms Division Defence Science and Technology Group Melbourne Vic Australia
4 shared publications Sanjeev Arulampalam
Defence Science and Technology Group
3 shared publicationsAnthony Finn
University of South Australia
2 shared publicationsVahid Majid Nezhad
2 shared publications- Branko Ristic
School of Engineering, RMIT University, Melbourne, VIC, Australia
1 shared publication
Latest Publications
- 9 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 6681-6695
A Closed-Form Estimator for Bearings-Only Fusion of Heterogeneous Passive Sensors
Bearings-only target motion analysis with fusion of heterogeneous passive sensors with and without propagation delay attempts to estimate a target trajectory by fusing bearings from two sensors: a sensor whose measurements have negligible propagation delay and a sensor with measurements that have non negligible propagation delay. This problem is highly nonlinear and challenging, particularly due to the fact that the propagation delay is unknown and is highly coupled with the unknown target states. This paper proposes a novel closed-form instrumental variable based batch estimator for this problem that is computationally fast. The estimator is derived by writing pseudo-linear type equations for the error vector difference between the true target state and a nominal solution. A theoretical bias and mean square error analysis of the proposed estimator is carried out which provides insight into the performance of this estimator. Results indicate that this is a computationally efficient algorithm that is able to produce comparable performance to the maximum likelihood estimator and achieves the Cramer Rao lower bound.
- 9 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 6681-6695
A Closed-Form Estimator for Bearings-Only Fusion of Heterogeneous Passive Sensors
Bearings-only target motion analysis with fusion of heterogeneous passive sensors with and without propagation delay attempts to estimate a target trajectory by fusing bearings from two sensors: a sensor whose measurements have negligible propagation delay and a sensor with measurements that have non negligible propagation delay. This problem is highly nonlinear and challenging, particularly due to the fact that the propagation delay is unknown and is highly coupled with the unknown target states. This paper proposes a novel closed-form instrumental variable based batch estimator for this problem that is computationally fast. The estimator is derived by writing pseudo-linear type equations for the error vector difference between the true target state and a nominal solution. A theoretical bias and mean square error analysis of the proposed estimator is carried out which provides insight into the performance of this estimator. Results indicate that this is a computationally efficient algorithm that is able to produce comparable performance to the maximum likelihood estimator and achieves the Cramer Rao lower bound.
- 27 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 4672-4687
An Algebraic Closed-Form Solution for Bearings-Only Maneuvering Target Motion Analysis From a Nonmaneuvering Platform
In bearings-only target motion analysis (TMA), the observer is often required to outmaneuver the target. However, under specific conditions, an observer moving with constant velocity is sufficient to compute the state of a target that changes its course. A maximum likelihood estimator (MLE) has been developed for this problem in the literature. Unfortunately, the MLE is not only computationally expensive but also prone to divergence problems when poorly initialized. To overcome these shortcomings, this paper proposes a novel quadratically constrained weighted instrumental variable (QC-WIV) estimator. Being a closed-form algorithm, the proposed QC-WIV is inherently more stable than the MLE while at the same time being computationally much more efficient. Moreover, it is shown analytically to be asymptotically unbiased. Numerical simulation studies are presented to corroborate the performance advantage of the proposed QC-WIV, where it is observed to be asymptotically efficient as well. In addition, the QC-WIV performance is on par with the MLE in small noise scenarios for both cases of known and unknown maneuver time. More importantly, the QC-WIV is observed to produce stable estimation performance in large noise levels at which the MLE suffers from divergence.
- 27 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 4672-4687
An Algebraic Closed-Form Solution for Bearings-Only Maneuvering Target Motion Analysis From a Nonmaneuvering Platform
In bearings-only target motion analysis (TMA), the observer is often required to outmaneuver the target. However, under specific conditions, an observer moving with constant velocity is sufficient to compute the state of a target that changes its course. A maximum likelihood estimator (MLE) has been developed for this problem in the literature. Unfortunately, the MLE is not only computationally expensive but also prone to divergence problems when poorly initialized. To overcome these shortcomings, this paper proposes a novel quadratically constrained weighted instrumental variable (QC-WIV) estimator. Being a closed-form algorithm, the proposed QC-WIV is inherently more stable than the MLE while at the same time being computationally much more efficient. Moreover, it is shown analytically to be asymptotically unbiased. Numerical simulation studies are presented to corroborate the performance advantage of the proposed QC-WIV, where it is observed to be asymptotically efficient as well. In addition, the QC-WIV performance is on par with the MLE in small noise scenarios for both cases of known and unknown maneuver time. More importantly, the QC-WIV is observed to produce stable estimation performance in large noise levels at which the MLE suffers from divergence.
- 23 February 2020
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 764-778
Integration of Biologically Inspired Pixel Saliency Estimation and IPDA Filters for Multi-target Tracking
- 23 February 2020
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 764-778
Integration of Biologically Inspired Pixel Saliency Estimation and IPDA Filters for Multi-target Tracking
- 20 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 67 (13) , 3576-3591
Bayesian WIV Estimators for 3-D Bearings-Only TMA With Speed Constraints
This paper develops Bayesian weighted instrumental variable (WIV) estimators under equality and inequality speed constraints for the three-dimensional (3D) bearings-only target motion analysis (TMA) problem, which show improved estimation accuracies compared to their unconstrained counterpart. Incorporating the speed constraint information into our previously proposed Bayesian WIV estimator [36] imposes a quadratic constraint on this problem. Finding an optimal solution for the resulting non-convex problem is by no means straightforward. The main problem with iterative optimisation methods such as the maximum a posteriori (MAP) is that they require initialisation and may converge to a local minimum if poorly initialised. Using advanced linear and nonlinear algebra techniques, non iterative accurate estimators under equality and inequality constraints are developed for this problem. Furthermore, it is proven that the proposed equality constrained estimator is approximately asymptotically unbiased and that the inequality constrained estimator is the optimal solution. An approximate covariance matrix has also been developed for the constrained WIV under equality constraint. Simulation results indicate that the equality and inequality constrained estimators outperform their unconstrained counterpart in the simulated scenarios.
- 20 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 67 (13) , 3576-3591
Bayesian WIV Estimators for 3-D Bearings-Only TMA With Speed Constraints
This paper develops Bayesian weighted instrumental variable (WIV) estimators under equality and inequality speed constraints for the three-dimensional (3D) bearings-only target motion analysis (TMA) problem, which show improved estimation accuracies compared to their unconstrained counterpart. Incorporating the speed constraint information into our previously proposed Bayesian WIV estimator [36] imposes a quadratic constraint on this problem. Finding an optimal solution for the resulting non-convex problem is by no means straightforward. The main problem with iterative optimisation methods such as the maximum a posteriori (MAP) is that they require initialisation and may converge to a local minimum if poorly initialised. Using advanced linear and nonlinear algebra techniques, non iterative accurate estimators under equality and inequality constraints are developed for this problem. Furthermore, it is proven that the proposed equality constrained estimator is approximately asymptotically unbiased and that the inequality constrained estimator is the optimal solution. An approximate covariance matrix has also been developed for the constrained WIV under equality constraint. Simulation results indicate that the equality and inequality constrained estimators outperform their unconstrained counterpart in the simulated scenarios.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 276-280
A Novel Recursive Bayesian Weighted Instrumental Variable Estimator for 3D Bearings-Only TMA
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 276-280
A Novel Recursive Bayesian Weighted Instrumental Variable Estimator for 3D Bearings-Only TMA
- 20 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 66 (4) , 1023-1036
A Novel Batch Bayesian WIV Estimator for Three-Dimensional TMA Using Bearing and Elevation Measurements
In this paper, we derive a novel batch Bayesian weighted instrumental variable estimator for the threedimensional (3D) target motion analysis (TMA) problem using bearing and elevation measurements. Unlike most existing 3D estimators based on instrumental variables, the proposed approach is able to incorporate a priori information into the estimation process and is proven to be approximately asymptotically unbiased. An approximate asymptotic covariance matrix is also presented to evaluate the performance of the estimator. Simulation results show that the proposed estimator outperforms its non-Bayesian counterpart and has an estimation performance on par with the conventional iterative maximum a posteriori (MAP) estimator, while being orders of magnitude faster in a passive sonar TMA problem. Moreover, it was shown that the proposed approach can provide an accurate initialisation for recursive estimators.
- 20 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 66 (4) , 1023-1036
A Novel Batch Bayesian WIV Estimator for Three-Dimensional TMA Using Bearing and Elevation Measurements
In this paper, we derive a novel batch Bayesian weighted instrumental variable estimator for the threedimensional (3D) target motion analysis (TMA) problem using bearing and elevation measurements. Unlike most existing 3D estimators based on instrumental variables, the proposed approach is able to incorporate a priori information into the estimation process and is proven to be approximately asymptotically unbiased. An approximate asymptotic covariance matrix is also presented to evaluate the performance of the estimator. Simulation results show that the proposed estimator outperforms its non-Bayesian counterpart and has an estimation performance on par with the conventional iterative maximum a posteriori (MAP) estimator, while being orders of magnitude faster in a passive sonar TMA problem. Moreover, it was shown that the proposed approach can provide an accurate initialisation for recursive estimators.
- 21 January 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 63 (8) , 1895-1910
A Novel Closed-Form Estimator for 3D TMA Using Heterogeneous Sensors
This paper considers the problem of three-dimensional target motion analysis using a combination of bearing, elevation, and time difference of arrival (TDOA) measurements. We propose a hybrid closed-form solution based on the weighted instrumental variables for this highly nonlinear problem. The proposed solution avoids the high computational complexity and convergence problems associated with iterative estimators. Furthermore, the simulation results suggest that the proposed estimator is nearly efficient, since its performance is very close to the best achievable performance as predicted by the Cramer-Rao lower bound.
- 21 January 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 63 (8) , 1895-1910
A Novel Closed-Form Estimator for 3D TMA Using Heterogeneous Sensors
This paper considers the problem of three-dimensional target motion analysis using a combination of bearing, elevation, and time difference of arrival (TDOA) measurements. We propose a hybrid closed-form solution based on the weighted instrumental variables for this highly nonlinear problem. The proposed solution avoids the high computational complexity and convergence problems associated with iterative estimators. Furthermore, the simulation results suggest that the proposed estimator is nearly efficient, since its performance is very close to the best achievable performance as predicted by the Cramer-Rao lower bound.
- 1 May 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-232
Dual-channel speech enhancement based on stochastic optimization strategies
In this paper, we propose an improved stochastic optimization algorithm called Learning-based Particle Swarm Optimization (LPSO) to design adaptive filter for dual-channel speech enhancement application. The novel algorithm employs a multi-swarm model based on knowledge learning method and dynamic search of global best (gbest) technique, to improve the performance of the Standard Particle Swarm Optimization (SPSO). The knowledge learning method uses the knowledge obtained in the searching process, and the dynamic search of gbest technique simulates the act of human randomized search behavior. The proposed algorithm shows an outstanding performance in dual-channel speech enhancement, and outperforms the SPSO, genetic algorithm (GA), and Normalized Least Mean Squares (NLMS) in a sense of stability and SNR-improvement.
- 1 May 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-232
Dual-channel speech enhancement based on stochastic optimization strategies
In this paper, we propose an improved stochastic optimization algorithm called Learning-based Particle Swarm Optimization (LPSO) to design adaptive filter for dual-channel speech enhancement application. The novel algorithm employs a multi-swarm model based on knowledge learning method and dynamic search of global best (gbest) technique, to improve the performance of the Standard Particle Swarm Optimization (SPSO). The knowledge learning method uses the knowledge obtained in the searching process, and the dynamic search of gbest technique simulates the act of human randomized search behavior. The proposed algorithm shows an outstanding performance in dual-channel speech enhancement, and outperforms the SPSO, genetic algorithm (GA), and Normalized Least Mean Squares (NLMS) in a sense of stability and SNR-improvement.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Asexual Reproduction-based Adaptive Quantum Particle Swarm Optimization algorithm for dual-channel speech enhancement
In this paper, we propose an improved particle swarm optimization algorithm, called Asexual Reproduction-based Adaptive Quantum Particle Swarm Optimization (ARAQPSO), for dual-channel speech enhancement. The foundation of a particle optimization algorithm is to intelligently generate and modify the initial randomized solutions. The proposed algorithm is based on Adaptive Quantum Particle Swarm Optimization (AQPSO) technique. Particles that search the problem space have the ability to reproduce asexually, where the fertility of particles is proportional to their fitness. The proposed algorithm applies an adaptive local search around the fitter particles that result in a comprehensive search in prosperous regions of the problem space. Experimental results indicate that the algorithm outperforms AQPSO, SPSO, and the gradient-based NLMS algorithm in the sense of SNR-improvement.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Asexual Reproduction-based Adaptive Quantum Particle Swarm Optimization algorithm for dual-channel speech enhancement
In this paper, we propose an improved particle swarm optimization algorithm, called Asexual Reproduction-based Adaptive Quantum Particle Swarm Optimization (ARAQPSO), for dual-channel speech enhancement. The foundation of a particle optimization algorithm is to intelligently generate and modify the initial randomized solutions. The proposed algorithm is based on Adaptive Quantum Particle Swarm Optimization (AQPSO) technique. Particles that search the problem space have the ability to reproduce asexually, where the fertility of particles is proportional to their fitness. The proposed algorithm applies an adaptive local search around the fitter particles that result in a comprehensive search in prosperous regions of the problem space. Experimental results indicate that the algorithm outperforms AQPSO, SPSO, and the gradient-based NLMS algorithm in the sense of SNR-improvement.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (21571473) , 441-444
Speech Enhancement Using Particle Swarm Optimization Techniques
This paper introduces the application of particle Swarm optimization techniques in speech enhancement structures. Because of the simple conception, the quick velocity of convergence and easy implementation, Particle swarm optimization (PSO) is used as an effective method in a wide variety of engineering problems. An improved PSO algorithm, called the Modified PSO (MPSO) algorithm, can find optimal or closer-to optimal solution, and has faster search speed. In this paper, we use PSO and MPSO algorithms for speech enhancement and compare the results. Experimental results show that MPSO algorithm outperforms the PSO algorithm in a sense of SNR improvement.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (21571473) , 441-444
Speech Enhancement Using Particle Swarm Optimization Techniques
This paper introduces the application of particle Swarm optimization techniques in speech enhancement structures. Because of the simple conception, the quick velocity of convergence and easy implementation, Particle swarm optimization (PSO) is used as an effective method in a wide variety of engineering problems. An improved PSO algorithm, called the Modified PSO (MPSO) algorithm, can find optimal or closer-to optimal solution, and has faster search speed. In this paper, we use PSO and MPSO algorithms for speech enhancement and compare the results. Experimental results show that MPSO algorithm outperforms the PSO algorithm in a sense of SNR improvement.