Probabilistic framework for characterizing uncertainty in the performance of networked battlefield sensors

Wilson, D. Keith; Pettit, Chris L.; Lewis, Matthew; Mackay, Sean; Seman, Peter M.

doi:10.1117/12.777760

Cited by 7 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following Dhillon and Chakrabarty, we express each sensor's probability of detection as decreasing exponentially with the radius from the sensor; i.e., P d prq e ¡αr . (1) where α is referred to here as the detection decay factor. Its mean value is changed from one case to the next, but it is constant within a given case.…”

Section: Problem Statement and Assumptionsmentioning

confidence: 99%

“…Nevertheless, many objectives and constraints are common to a wide range of applications, including the goals of minimizing the network's cost and complexity and maximizing the robustness of its performance within the available set of permitted sensor locations. 1 Sensor network optimization is complicated by the fact that the optimization is inherently combinatorial. 2,3 This has motivated the use of heuristic algorithms to avoid the high computational costs of finding global optima by focusing instead on more easily obtained but still satisfactory local optima.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the influence of problem definition in sensor placement optimization

Pettit

Vecherin

Wilson

2009

Defense Transformation and Net-Centric Systems 2009

Self Cite

View full text Add to dashboard Cite

The combinatorial nature of sensor placement optimization has motivated the use of heuristic algorithms to avoid the high computational costs of finding global optima by focusing instead on satisfactory local optima. Transition of an optimization strategy from research to practice should involve a detailed inquiry into the dependence of its results on the representation of realistic scenarios. A sampling method was used to examine how the specification of a sensor placement problem for optimization affects the statistical properties of various ensembles of optimum networks produced by a heuristic algorithm. Features sampled in each ensemble were the resolution of the grid used for computing network coverage, the range of each sensor, and the dimensions of obstacles to line-of-sight sensing. The candidate placement grid also was sampled to examine the consequences of being unable to place sensors at a subset of a regularly spaced grid. The objective function was the number of sensors required to exceed a probability of detection threshold throughout the coverage area. The relative importance of variability in each parameter was found to depend on the widths and baseline values of the assumed variability ranges. Important length scale ratios were identified for ensuring the feasibility and integrity of the optimization process.

show abstract

Section: Problem Statement and Assumptionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On the influence of problem definition in sensor placement optimization

Pettit

Vecherin

Wilson

2009

Defense Transformation and Net-Centric Systems 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…These equations have two and three levels in the hierarchy, respectively. Wilson et al (2008) formulated a hierarchical model for predicting the signal and noise distributions in the presence of uncertainties in the environment and source/receiver characteristics. In their formulation, the joint pdf ( , ) (where n is the noise power) was written…”

Section: Multilevel Modelingmentioning

confidence: 99%

Impact of Parametric Uncertainties on Scattered Signal Distributions and Receiver Operating Characteristics

Wilson¹,

Breton²,

Hart³

et al. 2018

Self Cite

View full text Add to dashboard Cite

Many different distributions are used to model statistics of waves that have been randomly scattered in atmospheric and terrain environments. These distributions have varying analytical advantages and ranges of physical applicability. This report reviews several basic distributions and discusses how they can be extended to include spatial and temporal variability in the scattering process. For this purpose, a compound probability density function (pdf) can be introduced in which a basic pdf describing the underlying scattering process is modulated by a second pdf describing parametric uncertainties in the scattering. We describe some useful new formulations based on the compound pdf, including strong and Rytov (lognormal) scattering processes modulated by the environment. These new formulations lead to relatively simple marginalized signal power distributions (Lomax and lognormal, respectively). Furthermore, we show how the conditional scattered signal pdf may be viewed as a likelihood function in which the modulating pdf is the Bayesian conjugate prior. The parameters of the modulating process can thus be refined by simple sequential Bayesian updating. Finally, the impact of the parametric uncertainties on signal detection and receiver operating characteristic curves is discussed and shown to be a very important consideration in practical applications. DISCLAIMER: The contents of this report are not to be used for advertising, publication, or promotional purposes. Citation of trade names does not constitute an official endorsement or approval of the use of such commercial products. All product names and trademarks cited are the property of their respective owners. The findings of this report are not to be construed as an official Department of the Army position unless so designated by other authorized documents.

show abstract

“…To describe and operate with multimodal sensors systematically, the probability of detection (at a certain probability of false alarm) is chosen as a sensor's performance measure (Wilson et al 2008); it is universal 1 , it directly relates to the receiver operating characteristic (ROC), which is a standard characteristic of a sensor and it provides a natural way to formulate coverage preferences by directly assigning the desired probability of detection for each spatial point. (In this technical report, a standard terminology of signal detection is used: the probability of detection is the probability that a sensor would detect a source when it is really there; the probability of false alarm is the probability that a sensor would detect a source when it is really not there; the probability of misdetection…”

Section: Introductionmentioning

confidence: 99%