Search results for "uncertainty"

Bridging Sensing and Decision Making in Ambient Intelligence Environments

2009

Context-aware and Ambient Intelligence environments represent one of the emerging issues in the last decade. In such intelligent environments, information is gathered to provide, on one hand, autonomic and easy to manage applications, and, on the other, secured access controlled environments. Several approaches have been defined in the literature to describe context-aware application with techniques to capture and represent information related to a specified domain. However and to the best of our knowledge, none has questioned the reliability of the techniques used to extract meaningful knowledge needed for decision making especially if the information captured is of multimedia types (image…

Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR

2021

International audience; 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 …

Using Polynomial Loss and Uncertainty Information for Robust Left Atrial and Scar Quantification and Segmentation

2022

Automatic and accurate segmentation of the left atrial (LA) cavity and scar can be helpful for the diagnosis and prognosis of patients with atrial fibrillation. However, automating the segmentation can be difficult due to the poor image quality, variable LA shapes, and small discrete regions of LA scars. In this paper, we proposed a fully-automatic method to segment LA cavity and scar from Late Gadolinium Enhancement (LGE) MRIs. For the loss functions, we propose two different losses for each task. To enhance the segmentation of LA cavity from the multicenter dataset, we present a hybrid loss that leverages Dice loss with a polynomial version of cross-entropy loss (PolyCE). We also utilize …

How to Enrich Description Logics with Fuzziness

2017

International audience; The paper describes the relation between fuzzy and non-fuzzy description logics. It gives an overview about current research in these areas and describes the difference between tasks for description logics and fuzzy logics. The paper also deals with the transformation properties of description logics to fuzzy logics and backwards. While the process of transformation from a description logic to a fuzzy logic is a trivial inclusion, the other way of reducing information from fuzzy logic to description logic is a difficult task, that will be topic of future work.

Automated uncertainty quantification analysis using a system model and data

2015

International audience; Understanding the sources of, and quantifying the magnitude of, uncertainty can improve decision-making and, thereby, make manufacturing systems more efficient. Achieving this goal requires knowledge in two separate domains: data science and manufacturing. In this paper, we focus on quantifying uncertainty, usually called uncertainty quantification (UQ). More specifically, we propose a methodology to perform UQ automatically using Bayesian networks (BN) constructed from three types of sources: a descriptive system model, physics-based mathematical models, and data. The system model is a high-level model describing the system and its parameters; we develop this model …

Calcul des contributions des incertitudes dans un modèle complexe de qualité de l'eau

2010

The quantification of uncertainty in integrated urban drainage water quality models is of paramount interest. Indeed, the assessment of the reliability of the model results for complex water quality models is useful for understanding the significance of the results. However, the state of knowledge regarding uncertainties in urban drainage models is poor. In the case of integrated urban drainage water quality models, due to the fact that integrated approaches are basically a cascade of sub-models (simulating sewer system, wastewater treatment plant and receiving water body), the uncertainty produced in one sub-model propagates to the following ones depending on the model structure, the estim…

Human capital and RD Driven Growth: analyse for France at regional level on the long run

2012

At the root of the Lisbon goal, for Europe, is placed the awareness for advocating a close link between growth and dissemination of advanced knowledge and innovation, on the one hand, and raising in general endowments in human capital, on the other hand, as to have power over the development of non-specific skills and boost efficiency. Much work in literature also stressed the interest of the position concerning traditional activities in the geography of innovation and links, in the long term, between the spatial distribution of longestablished skills and knowledge creation. Following Jones, in this approach, for which contribution to R&D and innovation explains half of the increase in weal…

Analysis of errors caused by incomplete knowledge of material data in mathematical models of elastic media

2011

A Combined Fuzzy-SEM Evaluation Approach to Identify the Key Drivers of the Academic Library Service Quality in the Digital Technology Era: An Empiri…

2017

A conceptual model of the Academic Library (AL) service quality is hypothesized in the present article, and then validated and analyzed by a novel evaluation approach. Specifically, the conceptual model integrates the fundamental attributes of the canonical AL service together with those more relevant of the new and widely considered AL Electronic Service (e-services). As concerns the evaluation approach, it incorporates the Fuzzy Sets Theory (FST) so as to deal with the students’ uncertainty over their own judgments on the AL service quality and a Structural Equation Model (SEM) to validate the conceptual model and to determine the key drivers of the AL service quality. The effectiveness o…

Statistical methods for adaptive river basin management and monitoring

2018

Decision-making at different phases of adaptive river basin management planning rely largely on the information that is gained through environmental monitoring. The aim of this thesis was to develop and test statistical assessment tools presumed to be particularly useful for evaluating existing monitoring designs, converting monitoring data into management information and quantifying uncertainties. River basin scale monitoring was performed using a wireless sensor network and a data quality control system and maintenance effort was assessed. National-scale, traditional monitoring data and linear mixed effect modelling were used to estimate the uncertainty in two status class metrics (total …