Search results for "uncertainty."

Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR

2021

In medical image segmentation, several studies have used Bayesian neural networks to segment and quantify the uncertainty of the images. These studies show that there might be an increased epistemic uncertainty in areas where there are semantically and visually challenging pixels. The uncertain areas of the image can be of a great interest as they can possibly indicate the regions of incorrect segmentation. To leverage the uncertainty information, we propose a segmentation model that incorporates the uncertainty into its learning process. Firstly, we generate the uncertainty estimate (sample variance) using Monte-Carlo dropout during training. Then we incorporate it into the loss function t…

1997

We have determined by forced Rayleigh scattering the diffusion coefficients of photo-labeled polystyrene micronetwork spheres (radii ≤ 10 nm) in melts of linear polyvinylmethylether (M W ≤ 40000 g/mol) at temperatures of 20-80°C. An expected slippage of the spheres through the meshes of the entanglement network appears possible but is still within the experimental uncertainty of our results.

Statistical Analysis of a Method to Predict Drug–Polymer Miscibility

2015

In this study, a method proposed to predict drug-polymer miscibility from differential scanning calorimetry measurements was subjected to statistical analysis. The method is relatively fast and inexpensive and has gained popularity as a result of the increasing interest in the formulation of drugs as amorphous solid dispersions. However, it does not include a standard statistical assessment of the experimental uncertainty by means of a confidence interval. In addition, it applies a routine mathematical operation known as "transformation to linearity," which previously has been shown to be subject to a substantial bias. The statistical analysis performed in this present study revealed that t…

Approximate Bayesian Computation for Forecasting in Hydrological models

2018

Approximate Bayesian Computation (ABC) is a statistical tool for handling parameter inference in a range of challenging statistical problems, mostly characterized by an intractable likelihood function. In this paper, we focus on the application of ABC to hydrological models, not as a tool for parametric inference, but as a mechanism for generating probabilistic forecasts. This mechanism is referred as Approximate Bayesian Forecasting (ABF). The abcd water balance model is applied to a case study on Aipe river basin in Columbia to demonstrate the applicability of ABF. The predictivity of the ABF is compared with the predictivity of the MCMC algorithm. The results show that the ABF method as …

Latent Class Model to Test the Preferences Heterogeneity in the Perceived Information by Public Transport Users

2012

The aim of analysis is to understand as not reliable information influence the user behaviour and how much disincentive the public transport use. For this purpose, a Stated Preference Survey has been carried out in order to know the preferences of public transport users related to information needs and uncertainty on the information provided by Advanced Traveller Information System (ATIS). The perceived uncertainty is defined as the information accuracy. In our study, it was considered the difference between forecasted or scheduled waiting time at the bus stop and/or metro station provided by ATIS, and experienced one by user, to catch the bus and/or metro respectively. A questionnaire has …

Prenatal diagnosis of cerebral malformation with an uncertain prognosis: a study concerning couple's information and consequences on pregnancy.

2004

Abstract Fetal ultrasound (FU) is used during almost all pregnancies and makes a large contribution to the identification of fetal malformation. It is particularly difficult to announce a malformation, particularly those affecting the brain, because there are often doubts concerning both the diagnosis and the prognosis. Aim. – The aim of this study was to analyze how imaging for prenatal screening is organized and how couples are managed and supported. We concentrated on the procedures used to inform couples: content, method of delivery and consequences. Method. –: Study amongst large multidisciplinary centers in Paris and the Paris region, by semi-directed interviews using a questionnaire.…

Excessive vs. insufficient entry in spatial models: When product design and market size matter

2020

Abstract Under spatial product differentiation and product design, we identify conditions for either excessive or insufficient firm entry. We extend previous settings, based on the Salop circular model, to analyze the combined role of positive demand elasticity and endogenous targeted product design. First, we show that, given the number of firms, the equilibrium level of targeted design is either excessive or insufficient, depending on demand elasticity. Second, with free entry, we show that the degree of targeted product design increases with the relative market size and decreases with demand elasticity. Based on these effects, the interplay between demand elasticity and market size yield…

An evaluation of the environmental factors for supply chain strategy decisions using grey systems and composite indicators

2020

[EN] The purpose of this work is to assess the importance of environmental factors in a supply chain with four partners as a preliminary step to select the competitive strategies and objectives. To achieve this purpose, a real case study was carried out in a footwear supply chain, in which two approaches were used: the grey system theory and uncertainty analysis tools for composite indicators. In order to validate both approaches, a seven-phase research methodology was developed and applied to our case study. In addition, the priorization of environmental factors was calculated individually for each partner. The results allow managers to establish the competitive strategy that best suits th…

Stochastic model predicts evolving preferences in the Iowa gambling task

2014

Learning under uncertainty is a common task that people face in their daily life. This process relies on the cognitive ability to adjust behavior to environmental demands. Although the biological underpinnings of those cognitive processes have been extensively studied, there has been little work in formal models seeking to capture the fundamental dynamic of learning under uncertainty. In the present work, we aimed to understand the basic cognitive mechanisms of outcome processing involved in decisions under uncertainty and to evaluate the relevance of previous experiences in enhancing learning processes within such uncertain context. We propose a formal model that emulates the behavior of p…

Examination of the least-squares method applied to the evaluation of physicochemical parameters with linearized equations

1989

Physicochemical parameters are frequently evaluated by the least-squares method after linearization of the equation which relates the experimental variables to the parameters of interest. When a given set of data is treated to evaluate (n+1) parameters. (n+2) nominally identical linearized equations are possible; each of these leads to different sets of values of the parameters which are also affected by different variances. These differences are also observed when statistical weights are used. Two methods for establishing which one of the (n+2) equations is best for fitting the data, i.e., simulation of experiments and propagation of errors, are discussed, compared and applied to a potenti…