Quality Of Prior Information Research Articles

Robust self-adaptive Kalman filter with application in target tracking

Kalman filter has been applied extensively to the target tracking. The estimation performance of Kalman filter is closely resulted by the quality of prior information about the process noise covariance (Q) and the measurement noise covariance (R). Therefore, the development of adaptive Kalman filter is mainly to reduce the estimation errors produced by the uncertainty of Q and R. In this paper, the proposed self-adaptive Kalman filter algorithm has solved the problems of covariance-matching method about the determination of the width of the window and the addition of storage burden and that can update Q and R simultaneously. Simulation results confirm that the proposed method outperforms the traditional Kalman filter and has the better estimation performance than the other two adaptive Kalman filters in the target tracking. The developed filtering algorithm has the following characteristics: high robustness, low computing load, easy operation and tuning Q, R simultaneously.

Limits of special material detectability fundamental to idealized dual-energy radiographic systems

Abstract Analysis of dual-energy radiographic approaches to the detection of “special” material, i.e. contraband, in otherwise innocuous scenes, such as maritime cargo containers encountered at ports of entry, reveals fundamental limitations of data obtained along a single line-of-sight. The basic equations that describe idealized systems are presented and analyzed so as to identify challenges that are only exacerbated by scatter, noise, and measurement uncertainty. In the mono-energetic limit, the instrumentation and measurement techniques reduce to a system of linear equations that are simple to treat: it is shown that there exists a threshold for the minimum amount of high-Z material that can be detected unambiguously (without the risk of false positive or false negative indications), even when the background materials are of finite and of well-known variety. The threshold depends on the quality of prior information about the cargo and the selection of probing energies, and can therefore be minimized by good system design practices and measurement procedures, but persists as a general challenge to security operations. In discussion of this result, it is noted that techniques incorporating other prior information, such as the geometry of cargo and potential contraband, along with data from 2D imaging, have far greater potential. As an example, a simple data analysis method capable of differentiating high-Z spheres from those of more common material is presented. This simple example demonstrates that, although simple line-of-sight transmission radiography may suffer fundamental limitations, there remains good cause to be optimistic about the potential for image analysis in radiographic material identification.

A Bayesian control chart for monitoring the ratio of Weibull percentiles

AbstractThis paper introduces a new Bayesian control chart to compare two processes by monitoring the ratio of percentiles of two quality characteristics that are assumed to be independent Weibull distributed random variables with the same and stable shape parameter larger than one. The chart analyses the sampling data directly, instead of transforming them in order to comply with the usual normality assumption, as many charts do. A real application in the wood industry and a wide simulation illustrate the features of the chart and its performance, depending on the number of training data, the quality of prior information, and the magnitude of the shift.

Integrated Exposure Modeling for Human Biomonitoring Data Assimilation

The integrated exposure assessment framework in HBM4EU aims at introducing a comprehensive methodological approach which will be implemented in a computational platform. The aim is to assess the source-to-dose continuum of a large space of chemical substances, towards the effective assimilation of human biomonitoring (HBM) data. The platform will integrate environmental fate, exposure and internal dose dynamically in time and across different spatial resolutions (from local to global). This description requires the use of multimedia environmental and micro-environmental modelling, exposure analysis incorporating multiple pathways and routes of exposure, and Physiology Based ToxicoKinetic (PBTK) modelling. Exposure analysis up to internal dose, will allow the interpretation of actual dosimetry to target tissues to in vitro assay results. This is of particular importance for the precise estimation of doses that relate to molecular perturbations within adverse outcome pathways (AOPs). Biomonitoring data interpretation is another challenge of the methodology, described as the “reverse modeling” calculations for exposure reconstruction. Following this, and based on the amount and quality of prior information, quantitative predictions, ranging from the overall exposure burden up to pathway/route specific information could be made; this will provide a very comprehensive instrument for policy makers, that will allow them to point out the cost-efficient interventions (which sources contribute mostly to exposure), directly from HBM data. The applicability of the methodology has been demonstrated in the case of bisphenol-A, Exposure reconstruction of available HBM data resulted in very low intake estimates, while the use of in vitro data regarding its estrogenic activity, indicated that there is no reason for concern for individual or aggregate scenarios of BPA exposure in the EU population.

Bayesian Analysis of Parametric Survival Models: A Computer Simulation Study based Informative Priors

In the article, the performance of Bayesian parametric survival models (Weibull, exponential, log-normal and log-logistic) by using Monte Carlo simulation was empirically compared while varying the informative priors and the sample sizes. We simulated the generated data by running for each of Weibull, exponential, log-normal and log-logistic survival models under varying informative priors and sample sizes using our simulation algorithm. For each situation, 1000 simulations were performed. Models with proper informative prior showed a good performance with too little bias. It was found out that bias of models increased while priors were becoming distant from reliability in all sample sizes. According to results obtained from simulation study, researchers should avoid assessment of data by using only one parametric survival model in future studies. We suggest that data should be better explored and processed by high performance modelling methods. Especially, quality of prior information to update knowledge about the parameters was a very important.

Efficiency of risk-based vs . random sampling for the monitoring of tetracycline residues in slaughtered calves in Switzerland

In all European Union countries, chemical residues are required to be routinely monitored in meat. Good farming and veterinary practice can prevent the contamination of meat with pharmaceutical substances, resulting in a low detection of drug residues through random sampling. An alternative approach is to target-monitor farms suspected of treating their animals with antimicrobials. The objective of this project was to assess, using a stochastic model, the efficiency of these two sampling strategies. The model integrated data on Swiss livestock as well as expert opinion and results from studies conducted in Switzerland. Risk-based sampling showed an increase in detection efficiency of up to 100% depending on the prevalence of contaminated herds. Sensitivity analysis of this model showed the importance of the accuracy of prior assumptions for conducting risk-based sampling. The resources gained by changing from random to risk-based sampling should be transferred to improving the quality of prior information.

On the influence of training data quality in k‐t BLAST reconstruction

This work investigated how the quality of prior information (i.e., data acquired during the training stage) influences k-t BLAST reconstruction. The impact of several factors, such as the amount of training data, the presence of spatial misregistration in the training data, and the effects of filtering, was investigated with simulations and in vivo data. It is shown that k-t BLAST outperforms sliding window reconstruction, even with very limited training data. By increasing the amount of training data, reconstruction error continues to decrease, albeit by a diminishing amount. However, an increased amount of training data also increases susceptibility to misregistration of the training data. Filtering of the training data with the goal of reducing truncation artifacts had only minor impact on reconstruction errors. Considering the balance among obtaining the most benefit from the training data, minimizing susceptibility to misregistration, and keeping data acquisition to a minimum, it is concluded that in cardiac imaging the training datasets should be limited to 10-20 profiles in k-space for a typical field of view. The training data may be acquired in a separate breathhold without much penalty, if care is taken to minimize misregistration, such as with a navigator.

Designing a contaminated soil sampling strategy for human health risk assessment

Human health risk assessment is a site-based approach used to identify the potential health hazards which are induced by an old site contamination. For a proper evaluation of the daily doses of contaminants to which people will be exposed given the future occupation of the site, both a characterization and a quantification of soil pollution are needed. Such information can be provided by soil sampling. Thus the choice of the location, the number, depth and type of soil samples is very important and ought to follow a well-defined strategy. A review of contaminated site sampling practices in Europe and North America could not identify any completely formalized sampling strategy for human health risk assessment. On the contrary there are several approaches which can be roughly classified into two categories: a systematic sampling scheme over the whole site, on the one hand, and a sampling design driven by an initial knowledge of the contamination sources and fitted to the suspected pollution pattern, on the other. The first approach provides a complete coverage of the site but it may be rather expensive and entail useless sampling. The performance of the second depends on the quality of prior information. Actually both methods can be combined as explained hereafter. In view of the specificity of each site, the requirements of health risk assessment and the time and cost constraints, it seems difficult to work out a typical soil sampling strategy suitable for all sites. However, some recommendations can be made according to the site dimensions, the nature, degree and heterogeneity of contamination, and the (future) use of the site. The scientist should thus rely on a thorough examination of all available information (site history, geology and hydrogeology, soil properties, contaminants behaviour, etc.) to delimit contaminated areas as homogeneous as possible and then distribute the sampling points (e.g. using a sampling grid). They should also take the potential exposure paths into account in order to define the areas and soil strata to be sampled as a priority. Statistical and geostatistical tools can be helpful for formulating a sampling strategy as well as for interpreting the collected data.