Shared-memory parallelization of the data association problem inmultitarget tracking

The focus of this paper is to present the results of our investigation and evaluation of various shared-memory parallelizations of the data association problem in multitarget tracking. The multitarget tracking algorithm developed was for a sparse air traffic surveillance problem, and is based on an Interacting Multiple Model (IMM) state estimator embedded into the (2D) assignment framework. The IMM estimator imposes a computational burden in terms of both space and time complexity, since more than one filter model is used to calculate state estimates, covariances, and likelihood functions. In fact, contrary to conventional wisdom, for sparse multitarget tracking problems, we show that the assignment (or data association) problem is not the major computational bottleneck. Instead, the interface to the assignment problem, namely, computing the rather numerous gating tests and IMM state estimates, covariance calculations, and likelihood function evaluations (used as cost coefficients in the assignment problem), is the major source of the workload. Using a measurement database based on two FAA air traffic control radars, we show that a “coarse-grained” (dynamic) parallelization across the numerous tracks found in a multitarget tracking problem is robust, scalable, and demonstrates superior computational performance to previously proposed “fine-grained” (static) parallelizations within the IMM     

Redundancy and data compression in recursive estimation

The problem of the existence of redundancy in the data in a recursive estimation problem is investigated. Given a certain data rate, should the estimator be run at the same rate? It is shown that under certain conditions there is redundancy in the data and the estimator can be run at a lower rate using compressed data with practically the same performance as when no data compression is utilized. It is also pointed out that, although at the higher rate there is redundancy in the data, the performance deteriorates noticeably when the data rate is lowered. Conditions for the existence of redundancy in the data and the procedure to remove it are presented. The procedure to compress the data is obtained such as to preserve the information in the sense of Fisher. The effect of data compression is a reduction in the computation requirements by a factor equal to the compression ratio. Such a reduction might be important in real-time applications in which the computing power is limited or too expensive. The application of this technique to the tracking of a reentry vehicle with a linearized filter is discussed in more detail and simulation results are presented.     

Alginate drug delivery systems: application in context of pharmaceutical and biomedical research

Alginates are natural polymers widely used in the food industry because of their biocompatible, biodegradable character, nontoxicity and easy availability. The bioadhesive character of alginates makes them useful in the pharmaceutical industry as well. The application areas of sodium alginate-based drug delivery systems are many and these systems can be formulated as gels, matrices, membranes, nanospheres, microspheres, etc. Worldwide researchers are exploring possible applications of alginates as coating material, preparation of controlled-release drug delivery systems such as microspheres, beads, pellets, gels, fibers, membranes, etc. In the present review, such applications of alginates are discussed.     

IMM estimation for multitarget-multisensor air traffic surveillance

This paper deals with the design and implementation of an algorithm for track formation and maintenance in a multisensor Air Traffic Surveillance scenario. The major contribution of the present work is the development of the combined likelihood function that enables the replacement of the Kalman filter (KF) with the much more versatile interacting multiple model (IMM) estimator which, as a self adjusting variable-bandwidth state estimator accounts for the various motion modes of the aircraft. This likelihood function defines the objective function used in the measurement to track assignment algorithm. Also, this algorithm incorporates both skill and beacon returns i.e., it fuses the primary and secondary radar data. Data from two FAA radars are used to evaluate the performance of this algorithm. The use of the IMM estimator yields considerable noise reduction during uniform motion, while maintaining the accuracy of the state estimates during maneuver. Overall, the mean square prediction error (to the next observation time) is reduced by 30% and the rms errors in the altitude rate estimates are reduced by a factor of three over the KF. The usefulness of the tracker presented here is also demonstrated on a noncooperative target     

Joint probabilistic data association for multitarget tracking with possibly unresolved measurements and maneuvers

In a multitarget environment, when tracking crossing targets, a model is needed for the situation where the measurements from two targets are merged into one due to an inherent resolution threshold. A multidimensional model for the merged measurements is proposed and the resulting pdf is presented. This model is applied to augment the Joint Probabilistic Data Association (JPDA) algorithm used for tracking multiple targets in a cluttered environment, so that it can handle, in a more realistic manner, the situation of crossing targets. An extension to maneuvering targets is also presented.     

Decision and estimation procedures for air contaminants

This paper deals with the problem of enforcing average exposure standards for atmospheric contaminants in an industrial environment based upon short-period samples. Due to inherent uncertainties, a decision is to be made only if the probability of incorrect decision is below a prescribed level. It is shown how such a decision can be obtained in a very simple manner with the help of a decision chart with families of curves corresponding to the number of observations.     

An actively adaptive control for linear systems with random parameters via the dual control approach

A new method is presented for controlling a discrete-time linear system with possibly time-varying random parameters in the presence of input and output noise. The cost is assumed to be quadratic in the state and control. Previous algorithms for the above problem when the system had both zeros and poles unknown were of the open-loop feedback type, i.e., they did not take into account that future observations will be made. Therefore, even though these schemes were adaptive, their learning was "accidental." In contrast to this, the new approach uses an expression of the optimal cost-to-go that exhibits the dual purpose of the control, i.e., learning and control. The effect of the present control on the future estimation ("learning") appears explicitly in the cost used in the stochastic dynamic programming equation. The resulting sequence of controls, which is of the closed-loop type, is shown via simulations to appropriately divide its energy between the learning and the control purposes. Therefore, this control is called actively adaptive because it regulates the speed and amount of learning as required by the performance index. The simulations on a third-order system with six unknown parameters also demonstrate the computational feasibility of the proposed algorithm.     

Consistency and robustness of PDAF for target tracking in cluttered environments

This paper presents a simulation-based investigation of the consistency of the PDAF via statistical tests of its actual errors versus the filter calculated covariances. These tests confirm the goodness of the approximation done at every stage in the PDAF, where a Gaussian mixture is replaced by an ‘umbrella’ Gaussian using moment matching. Two versions of the PDAF are examined: a parametric one that uses a Poisson model for the number of clutter originated measurements and a nonparametric one that uses a diffuse prior. While no new theoretical results are presented, the methodology of testing filter consistency can prove to be useful in the general evaluation of filters that contain approximations.