Branko Ristic - Academia.edu (original) (raw)
Papers by Branko Ristic
Storage and Retrieval for Image and Video Databases, 2000
The tracking performance of the Particle Filter is compared with that of the Range-Parameterised ... more The tracking performance of the Particle Filter is compared with that of the Range-Parameterised EKF (RPEKF) and Modified Polar coordinate EKF (MPEKF) for a single-sensor angle-only tracking problem with ownship maneuver. The Particle Filter is based on representing the required density of the state vector as a set of random samples with associated weights. This filter is implemented for recursive
This work develops a novel estimation approach for nonlinear dynamic stochastic systems by combin... more This work develops a novel estimation approach for nonlinear dynamic stochastic systems by combining the sequential Monte Carlo method with interval analysis. Unlike the common pointwise measurements, the proposed solution is for problems with interval measurements with association uncertainty. The optimal theoretical solution can be formulated in the framework of random set theory as the Bernoulli filter for interval measurements. The straightforward particle filter implementation of the Bernoulli filter typically requires a huge number of particles since the posterior probability density function occupies a significant portion of the state space. In order to reduce the number of particles, without neces-sarily sacrificing estimation accuracy, the paper investigates an implementation based on box particles. A box particle occupies a small and controllable rectangular region of non-zero volume in the target state space. The numerical results demonstrate that the filter performs rema...
The problem is target classification in the circumstances where the likelihood models are impreci... more The problem is target classification in the circumstances where the likelihood models are imprecise. The paper highlights the differences between three suitable solutions: the Transferrable Belief model (TBM), the random set approach and the imprecise probability approach. The random set approach produces identical results to those obtained using the TBM classifier, provided that equivalent measurement models are employed. Similar classification results are also obtained using the imprecise probability theory, although the latter is more general and provides more robust framework for reasoning under uncertainty.
The paper considers the problem of estimating the number of radioactive point sources that potent... more The paper considers the problem of estimating the number of radioactive point sources that potentially exist in a designated area and estimating the parameters of these sources (their locations and strengths) using measurements collected by a low-cost Geiger-Müller counter. In a recent publication the authors proposed candidate algorithms for this task: the maximum likelihood estimator (MLE) and the importance sampling
2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006
A method for performing unscented Kalman filtering with a reduced number of sigma points is propo... more A method for performing unscented Kalman filtering with a reduced number of sigma points is proposed. The procedure is applicable when either the process or measurement equations are partially linear in the sense that only a subset of the elements of the state vector undergo a nonlinear transformation. It is shown that for such models second-order accuracy in the moments required for the unscented Kalman filter recursion can be obtained using a number of sigma points determined by the number of nonlinearly transformed elements rather than the dimension of the state vector. A procedure for computing the sigma points is developed. An application of the proposed method to smoothed target state estimation from bearings measurements is presented
2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, 2013
Abstractó The paper develops an information fusion system that aims at supporting a commander’s d... more Abstractó The paper develops an information fusion system that aims at supporting a commander’s decision making by providing an assessment of threat, that is an estimate of the extent to which an enemy platform poses a threat based on evidence about its intent and capability. Threat is modelled in the framework of the valuation-based system (VBS), by a network of
ISRN Applied Mathematics, 2011
This paper describes and compares two approaches for the problem of determining the number of rad... more This paper describes and compares two approaches for the problem of determining the number of radioactive point sources that potentially exist in a designated area and estimating the parameters of these sources their locations and strengths using a small number of noisy radiological measurements provided by a radiation sensor. Both approaches use the Bayesian inferential methodology but sample the posterior distribution differently: one approach uses importance sampling with progressive correction and the other a reversible-jump Markov chain Monte Carlo sampling. The two approaches also use different measurement models for the radiation data. The first approach assumes a perfect knowledge of the data model and the average background radiation level, whereas the second approach quantifies explicitly the uncertainties in the model specification and in the average background radiation level. The performances of the two approaches are compared using experimental data acquired during a recent radiological field trial.
... Jacobians, dim(4,4) and dim(2,4), respectively » kjk (i), ³ kjk (i), Wi Sigma points and weig... more ... Jacobians, dim(4,4) and dim(2,4), respectively » kjk (i), ³ kjk (i), Wi Sigma points and weights ... The filters are initialized using the same two-point differencing method [8, p. 228], [1, p. 253 ... The EKF only uses the first order terms in the Taylor series expansion of the nonlinear state ...
The paper presents an analysis of a nonlin- ear filtering problem corresponding to tracking of an... more The paper presents an analysis of a nonlin- ear filtering problem corresponding to tracking of an ex- tended target whose shape is modelled by an ellipse. The measurements of target extent are assumed to be available in addition to the usual positional measurements. Using Cramer-Rao bounds we establish the best achievable error performance for this highly nonlinear problem. The theo-
2006 9th International Conference on Information Fusion, 2006
The paper presents an analysis of the phased array radar allocation demands, when tracking highly... more The paper presents an analysis of the phased array radar allocation demands, when tracking highly maneuverable anti-ship missiles (ASM) using a collocated radar/IRST sensor combination. The motion of the ASM is modeled using the quantized acceleration levels. The principal aim of this analysis is to determine an upper bound on the average radar update time. This bound follows from a
Signal Processing, 1998
The paper deals with analysis and time-frequency representation of multicomponent signals charact... more The paper deals with analysis and time-frequency representation of multicomponent signals characterised by non-linear frequency variation in time. A certain type of higher-order time-frequency distribution, referred to as Polynomial Wigner-Ville distribution [2], has been designed to achieve delta function concentration in the timefrequency plane for this class of signals. In the presence of multiplicative noise, the signals are treated as being random and we introduce time-varying higher-order spectra (TV-HOS) as ensemble averaged Polynomial Wigner-Ville distributions. TV-HOS are shown to be natural tools for analysis of non-stationary random signals, and we demonstrate this in the context of FM signals affected by multiplicative noise.
2009 International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2009
ABSTRACT The paper presents an analytical study of the effects of dynamic collaboration in a netw... more ABSTRACT The paper presents an analytical study of the effects of dynamic collaboration in a network of chemical sensors using a simple population and physics based model. The approach is based on the known analogy between the information spread in a sensor network and the epidemics propagation across a population. In this framework we derive analytical expressions which relate the parameters of the network (e.g. number of sensors, their density, sensing time etc), with the network performance parameters (probability of detection, response time of a network) and the parameters of the external challenge (the chemical pollutant and environment). The paper also presents the numerical simulation results in support of analytic expressions.
International Journal of Distributed Sensor Networks, 2012
The problem of environmental monitoring using a wireless network of chemical sensors with a limit... more The problem of environmental monitoring using a wireless network of chemical sensors with a limited energy supply is considered. Since the conventional chemical sensors in active mode consume vast amounts of energy, an optimisation problem arises in the context of a balance between the energy consumption and the detection capabilities of such a network. A protocol based on "dynamic sensor collaboration" is employed: in the absence of any pollutant, majority of sensors are in the sleep (passive) mode; a sensor is invoked (activated) by wake-up messages from its neighbors only when more information is required. The paper proposes a mathematical model of a network of chemical sensors using this protocol. The model provides valuable insights into the network behavior and near optimal capacity design (energy consumption against detection). An analytical model of the environment, using turbulent mixing to capture chaotic fluctuations, intermittency and non-homogeneity of the pollutant distribution, is employed in the study. A binary model of a chemical sensor is assumed (a device with threshold detection). The outcome of the study is a set of simple analytical tools for sensor network design, optimisation, and performance analysis.
2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, 2007
Given a designated polygon-shaped search area with obstacles, the problem is to establish if a ra... more Given a designated polygon-shaped search area with obstacles, the problem is to establish if a radioactive material of unknown intensity of radiation is present in the area, and if present, its whereabouts. The detection/estimation part of the problem is solved in the Bayesian framework using a particle filter. The coordinated search by multiple observers is carried out by maximization of
2007 10th International Conference on Information Fusion, 2007
2011 Seventh International Conference on Intelligent Sensors, Sensor Networks and Information Processing, 2011
ABSTRACT The problem is recursive Bayesian estimation of position and velocity of a moving object... more ABSTRACT The problem is recursive Bayesian estimation of position and velocity of a moving object using asynchronous measurements of Doppler-shift frequencies at several separate locations. By adopting a stochastic dynamic target motion model and assuming that the frequency of the emitting tone is known, the paper develops the theoretical Carme´r-Rao lower bound for the estimation error as a good indicator of target state observability. Furthermore, a particle filter for the recursive target state estimation is developed and its error performance compared to the theoretical CRLB. Initialisation of the particle filter using Doppler-shift measurement presents itself as a serious challenge.
2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009
The problem is statistical prediction of the number of people that will be infected with a contag... more The problem is statistical prediction of the number of people that will be infected with a contagious illness in a closed population over time. The prediction is based on the Susceptible-Infectious-Recovered (SIR) model of epidemic dynamics with inhomogeneous population mixing. The paper presents a theoretical analysis of the predictive accuracy based on the Cramér-Rao lower bound (CRLB). The CRLB provides a tool that enables us to quantify the prediction accuracy of a scale of an epidemic as a function of the prior uncertainty of SIR model parameters, measurement accuracy of the number of infected people and the amount of data available for processing. A verification of the theoretical analysis is carried out by Monte Carlo simulations.
2007 Information, Decision and Control, 2007
The paper investigates the recently proposed ultimate Cramer-Rao lower bound (CRLB) for tracking ... more The paper investigates the recently proposed ultimate Cramer-Rao lower bound (CRLB) for tracking multiple targets (Ristic et al., 2004). There are three main contributions: (1) The effect of interaction between targets is analysed; (2) The multi-target CRLB is verified via Monte Carlo simulations; (3) The broader implication of the CRLB is illustrated in the context of a wireless sensor network.
2007 10th International Conference on Information Fusion, 2007
The paper presents an algorithm for detection and a subsequent information gain driven search for... more The paper presents an algorithm for detection and a subsequent information gain driven search for an unaccounted point source of relatively low-level gamma radiation. Source detection and parameter estimation are carried out jointly in the Bayesian framework using a particle filter. The observer control vector consists of the next sensor location and the exposure time. During the pre-detection search, the
Storage and Retrieval for Image and Video Databases, 2000
The tracking performance of the Particle Filter is compared with that of the Range-Parameterised ... more The tracking performance of the Particle Filter is compared with that of the Range-Parameterised EKF (RPEKF) and Modified Polar coordinate EKF (MPEKF) for a single-sensor angle-only tracking problem with ownship maneuver. The Particle Filter is based on representing the required density of the state vector as a set of random samples with associated weights. This filter is implemented for recursive
This work develops a novel estimation approach for nonlinear dynamic stochastic systems by combin... more This work develops a novel estimation approach for nonlinear dynamic stochastic systems by combining the sequential Monte Carlo method with interval analysis. Unlike the common pointwise measurements, the proposed solution is for problems with interval measurements with association uncertainty. The optimal theoretical solution can be formulated in the framework of random set theory as the Bernoulli filter for interval measurements. The straightforward particle filter implementation of the Bernoulli filter typically requires a huge number of particles since the posterior probability density function occupies a significant portion of the state space. In order to reduce the number of particles, without neces-sarily sacrificing estimation accuracy, the paper investigates an implementation based on box particles. A box particle occupies a small and controllable rectangular region of non-zero volume in the target state space. The numerical results demonstrate that the filter performs rema...
The problem is target classification in the circumstances where the likelihood models are impreci... more The problem is target classification in the circumstances where the likelihood models are imprecise. The paper highlights the differences between three suitable solutions: the Transferrable Belief model (TBM), the random set approach and the imprecise probability approach. The random set approach produces identical results to those obtained using the TBM classifier, provided that equivalent measurement models are employed. Similar classification results are also obtained using the imprecise probability theory, although the latter is more general and provides more robust framework for reasoning under uncertainty.
The paper considers the problem of estimating the number of radioactive point sources that potent... more The paper considers the problem of estimating the number of radioactive point sources that potentially exist in a designated area and estimating the parameters of these sources (their locations and strengths) using measurements collected by a low-cost Geiger-Müller counter. In a recent publication the authors proposed candidate algorithms for this task: the maximum likelihood estimator (MLE) and the importance sampling
2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006
A method for performing unscented Kalman filtering with a reduced number of sigma points is propo... more A method for performing unscented Kalman filtering with a reduced number of sigma points is proposed. The procedure is applicable when either the process or measurement equations are partially linear in the sense that only a subset of the elements of the state vector undergo a nonlinear transformation. It is shown that for such models second-order accuracy in the moments required for the unscented Kalman filter recursion can be obtained using a number of sigma points determined by the number of nonlinearly transformed elements rather than the dimension of the state vector. A procedure for computing the sigma points is developed. An application of the proposed method to smoothed target state estimation from bearings measurements is presented
2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, 2013
Abstractó The paper develops an information fusion system that aims at supporting a commander’s d... more Abstractó The paper develops an information fusion system that aims at supporting a commander’s decision making by providing an assessment of threat, that is an estimate of the extent to which an enemy platform poses a threat based on evidence about its intent and capability. Threat is modelled in the framework of the valuation-based system (VBS), by a network of
ISRN Applied Mathematics, 2011
This paper describes and compares two approaches for the problem of determining the number of rad... more This paper describes and compares two approaches for the problem of determining the number of radioactive point sources that potentially exist in a designated area and estimating the parameters of these sources their locations and strengths using a small number of noisy radiological measurements provided by a radiation sensor. Both approaches use the Bayesian inferential methodology but sample the posterior distribution differently: one approach uses importance sampling with progressive correction and the other a reversible-jump Markov chain Monte Carlo sampling. The two approaches also use different measurement models for the radiation data. The first approach assumes a perfect knowledge of the data model and the average background radiation level, whereas the second approach quantifies explicitly the uncertainties in the model specification and in the average background radiation level. The performances of the two approaches are compared using experimental data acquired during a recent radiological field trial.
... Jacobians, dim(4,4) and dim(2,4), respectively » kjk (i), ³ kjk (i), Wi Sigma points and weig... more ... Jacobians, dim(4,4) and dim(2,4), respectively » kjk (i), ³ kjk (i), Wi Sigma points and weights ... The filters are initialized using the same two-point differencing method [8, p. 228], [1, p. 253 ... The EKF only uses the first order terms in the Taylor series expansion of the nonlinear state ...
The paper presents an analysis of a nonlin- ear filtering problem corresponding to tracking of an... more The paper presents an analysis of a nonlin- ear filtering problem corresponding to tracking of an ex- tended target whose shape is modelled by an ellipse. The measurements of target extent are assumed to be available in addition to the usual positional measurements. Using Cramer-Rao bounds we establish the best achievable error performance for this highly nonlinear problem. The theo-
2006 9th International Conference on Information Fusion, 2006
The paper presents an analysis of the phased array radar allocation demands, when tracking highly... more The paper presents an analysis of the phased array radar allocation demands, when tracking highly maneuverable anti-ship missiles (ASM) using a collocated radar/IRST sensor combination. The motion of the ASM is modeled using the quantized acceleration levels. The principal aim of this analysis is to determine an upper bound on the average radar update time. This bound follows from a
Signal Processing, 1998
The paper deals with analysis and time-frequency representation of multicomponent signals charact... more The paper deals with analysis and time-frequency representation of multicomponent signals characterised by non-linear frequency variation in time. A certain type of higher-order time-frequency distribution, referred to as Polynomial Wigner-Ville distribution [2], has been designed to achieve delta function concentration in the timefrequency plane for this class of signals. In the presence of multiplicative noise, the signals are treated as being random and we introduce time-varying higher-order spectra (TV-HOS) as ensemble averaged Polynomial Wigner-Ville distributions. TV-HOS are shown to be natural tools for analysis of non-stationary random signals, and we demonstrate this in the context of FM signals affected by multiplicative noise.
2009 International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2009
ABSTRACT The paper presents an analytical study of the effects of dynamic collaboration in a netw... more ABSTRACT The paper presents an analytical study of the effects of dynamic collaboration in a network of chemical sensors using a simple population and physics based model. The approach is based on the known analogy between the information spread in a sensor network and the epidemics propagation across a population. In this framework we derive analytical expressions which relate the parameters of the network (e.g. number of sensors, their density, sensing time etc), with the network performance parameters (probability of detection, response time of a network) and the parameters of the external challenge (the chemical pollutant and environment). The paper also presents the numerical simulation results in support of analytic expressions.
International Journal of Distributed Sensor Networks, 2012
The problem of environmental monitoring using a wireless network of chemical sensors with a limit... more The problem of environmental monitoring using a wireless network of chemical sensors with a limited energy supply is considered. Since the conventional chemical sensors in active mode consume vast amounts of energy, an optimisation problem arises in the context of a balance between the energy consumption and the detection capabilities of such a network. A protocol based on "dynamic sensor collaboration" is employed: in the absence of any pollutant, majority of sensors are in the sleep (passive) mode; a sensor is invoked (activated) by wake-up messages from its neighbors only when more information is required. The paper proposes a mathematical model of a network of chemical sensors using this protocol. The model provides valuable insights into the network behavior and near optimal capacity design (energy consumption against detection). An analytical model of the environment, using turbulent mixing to capture chaotic fluctuations, intermittency and non-homogeneity of the pollutant distribution, is employed in the study. A binary model of a chemical sensor is assumed (a device with threshold detection). The outcome of the study is a set of simple analytical tools for sensor network design, optimisation, and performance analysis.
2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, 2007
Given a designated polygon-shaped search area with obstacles, the problem is to establish if a ra... more Given a designated polygon-shaped search area with obstacles, the problem is to establish if a radioactive material of unknown intensity of radiation is present in the area, and if present, its whereabouts. The detection/estimation part of the problem is solved in the Bayesian framework using a particle filter. The coordinated search by multiple observers is carried out by maximization of
2007 10th International Conference on Information Fusion, 2007
2011 Seventh International Conference on Intelligent Sensors, Sensor Networks and Information Processing, 2011
ABSTRACT The problem is recursive Bayesian estimation of position and velocity of a moving object... more ABSTRACT The problem is recursive Bayesian estimation of position and velocity of a moving object using asynchronous measurements of Doppler-shift frequencies at several separate locations. By adopting a stochastic dynamic target motion model and assuming that the frequency of the emitting tone is known, the paper develops the theoretical Carme´r-Rao lower bound for the estimation error as a good indicator of target state observability. Furthermore, a particle filter for the recursive target state estimation is developed and its error performance compared to the theoretical CRLB. Initialisation of the particle filter using Doppler-shift measurement presents itself as a serious challenge.
2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009
The problem is statistical prediction of the number of people that will be infected with a contag... more The problem is statistical prediction of the number of people that will be infected with a contagious illness in a closed population over time. The prediction is based on the Susceptible-Infectious-Recovered (SIR) model of epidemic dynamics with inhomogeneous population mixing. The paper presents a theoretical analysis of the predictive accuracy based on the Cramér-Rao lower bound (CRLB). The CRLB provides a tool that enables us to quantify the prediction accuracy of a scale of an epidemic as a function of the prior uncertainty of SIR model parameters, measurement accuracy of the number of infected people and the amount of data available for processing. A verification of the theoretical analysis is carried out by Monte Carlo simulations.
2007 Information, Decision and Control, 2007
The paper investigates the recently proposed ultimate Cramer-Rao lower bound (CRLB) for tracking ... more The paper investigates the recently proposed ultimate Cramer-Rao lower bound (CRLB) for tracking multiple targets (Ristic et al., 2004). There are three main contributions: (1) The effect of interaction between targets is analysed; (2) The multi-target CRLB is verified via Monte Carlo simulations; (3) The broader implication of the CRLB is illustrated in the context of a wireless sensor network.
2007 10th International Conference on Information Fusion, 2007
The paper presents an algorithm for detection and a subsequent information gain driven search for... more The paper presents an algorithm for detection and a subsequent information gain driven search for an unaccounted point source of relatively low-level gamma radiation. Source detection and parameter estimation are carried out jointly in the Bayesian framework using a particle filter. The observer control vector consists of the next sensor location and the exposure time. During the pre-detection search, the