An official website of the United States government
Abstract In this work, we describe a new approach that uses variational encoder-decoder (VED) networks for efficient uncertainty quantification forgoal-orientedinverse problems. Contrary to standard inverse problems, these approaches are goal-oriented in that the goal is to estimate some quantities of interest (QoI) that are functions of the solution of an inverse problem, rather than the solution itself. Moreover, we are interested in computing uncertainty metrics associated with the QoI, thus utilizing a Bayesian approach for inverse problems that incorporates the prediction operator and techniques for exploring the posterior. This may be particularly challenging, especially for nonlinear, possibly unknown, operators and nonstandard prior assumptions. We harness recent advances in machine learning, i.e. VED networks, to describe a data-driven approach to large-scale inverse problems. This enables a real-time uncertainty quantification for the QoI. One of the advantages of our approach is that we avoid the need to solve challenging inversion problems by training a network to approximate the mapping from observations to QoI. Another main benefit is that we enable uncertainty quantification for the QoI by leveraging probability distributions in the latent and target spaces. This allows us to efficiently generate QoI samples and circumvent complicated or even unknown forward models and prediction operators. Numerical results from medical tomography reconstruction and nonlinear hydraulic tomography demonstrate the potential and broad applicability of the approach.
more »
« less
QOI: Assessing Participation in Threat Information Sharing
We introduce the notion of Quality of Indicator (QoI) to assess the level of contribution by participants in threat intelligence sharing. We exemplify QoI by metrics of the correctness, relevance, utility, and uniqueness of indicators. We build a system that extrapolates the metrics using a machine learning process over a reference set of indicators. We compared these results against a model that only considers the volume of information as a metric for contribution, and unveiled various observations, including the ability to spot low-quality contributions that are synonymous to free-riding.
more »
« less
- PAR ID:
- 10084228
- Date Published:
- Journal Name:
- 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018
- Page Range / eLocation ID:
- 6951 to 6955
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A major challenge in mobile crowdsensing applications is the generation of false (or spam) contributions resulting from selfish and malicious behaviors of users, or wrong perception of an event. Such false contributions induce loss of revenue owing to undue incentivization, and also affect the operational reliability of the applications. To counter these problems, we propose an event-trust and user-reputation model, called QnQ, to segregate different user classes such as honest, selfish, or malicious. The resultant user reputation scores, are based on both `quality' (accuracy of contribution) and `quantity' (degree of participation) of their contributions. Specifically, QnQ exploits a rating feedback mechanism for evaluating an event-specific expected truthfulness, which is then transformed into a robust quality of information (QoI) metric to weaken various effects of selfish and malicious user behaviors. Eventually, the QoIs of various events in which a user has participated are aggregated to compute his reputation score, which in turn is used to judiciously disburse user incentives with a goal to reduce the incentive losses of the CS application provider. Subsequently, inspired by cumulative prospect theory (CPT), we propose a risk tolerance and reputation aware trustworthy decision making scheme to determine whether an event should be published or not, thus improving the operational reliability of the application. To evaluate QnQ experimentally, we consider a vehicular crowdsensing application as a proof-of-concept. We compare QoI performance achieved by our model with Jøsang's belief model, reputation scoring with Dempster-Shafer based reputation model, and operational (decision) accuracy with expected utility theory. Experimental results demonstrate that QnQ is able to better capture subtle differences in user behaviors based on both quality and quantity, reduces incentive losses, and significantly improves operational accuracy in presence of rogue contributionsmore » « less
-
We introduce a flexible framework that produces high-quality almost-exact matches for causal inference. Most prior work in matching uses ad-hoc distance metrics, often leading to poor quality matches, particularly when there are irrelevant covariates. In this work, we learn an interpretable distance metric for matching, which leads to substantially higher quality matches. The learned distance metric stretches the covariate space according to each covariate's contribution to outcome prediction: this stretching means that mismatches on important covariates carry a larger penalty than mismatches on irrelevant covariates. Our ability to learn flexible distance metrics leads to matches that are interpretable and useful for the estimation of conditional average treatment effects.more » « less
-
Fecal indicator bacteria currently used for water quality monitoring inadequately represent viral fate in water systems, motivating the development of viral fecal pollution indicators. Molecular viral fecal pollution indicators such as crAssphage and pepper mild mottle virus (PMMoV) have emerged as leading viral fecal pollution indicator candidates due to ease and speed of measurement and target specificity. Elucidating the fate of molecular viral fecal indicators in water systems is necessary to facilitate their development, broader adoption, and ultimately their association with infectious risk. A significant mechanism controlling the behavior of viral indicators in environmental waters is association with particles, as this would dictate removal via settling and transport characteristics. In this study, we investigated the particle associations of six molecular fecal pollution targets (crAssphage, PMMoV, adenovirus, human polyomavirus, norovirus, HF183/BacR287) in wastewater using a cascade filtration approach. Four different filters were employed representing large settleable particles (180 μm), larger (20 μm) and smaller suspended particles (0.45 μm), and non-settleable particles (0.03 μm). All molecular targets were detected on all particle size fractions; however, all targets had their highest concentrations on the 0.45 μm (percent contribution ranging from 40% to 80.5%) and 20 μm (percent contribution ranging from 3.9% to 39.4%) filters. The association of viral fecal pollution targets with suspended particles suggests that particle association will dictate transport in environmental waters and that sample concentration approaches based upon particle collection will be effective for these targets.more » « less
-
Since the emergence of middle schools as distinct educational settings in the 1960s, proponents of the model have advocated for structures and approaches that best meet the particular developmental needs of young adolescents. Middle school researchers have developed frameworks of best practices for schools that have been widely, if not uniformly, adopted. However, there is a paucity of large-scale quantitative research on the efficacy of such best practices. In this study we used state-level administrative data from Texas to estimate the school-level contribution to standardized test scores in math and language arts, along with absenteeism. We then regressed these value-added quantities on indicators of middle school structures, along with research-supported predictors of school efficacy. Results showed that schools with fewer classes in the school day and higher quality teachers performed better, among other indicators. Findings from models using the campus contribution to absenteeism were similar. These results indicate that while elements of the middle school model may help transform individual schools, the equitable distribution of resources and the undoing of de facto segregation are vital to the success of all young adolescents.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICASSP.2018.8462036
