Uncertainty Quantification with Support Vector Regression Prediction Models

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. The paper considers a data driven approach in modelling uncertainty in spatial predictions. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic features and describe stochastic variability and non-uniqueness of spatial properties. It is able to capture and preserve key spatial dependencies such as connectivity, which is often difficult to achieve with two-point geostatistical models. Semi-supervised SVR is designed to integrate various kinds of conditioning data and learn dependences from them. A stochastic semi-supervised SVR model is integrated into a Bayesian framework to quantify uncertainty with multiple models fitted to dynamic observations. The developed approach is illustrated with a reservoir case study. The resulting probabilistic production forecasts are described by uncertainty envelopes.

Expression of E-Selectin and Vascular Cell Adhesion Molecule-1 in So-Called 'Negative' Appendices: First Results to Support the Pathological Diagnosis in Borderline Cases.

Background: Since the rate of histologically 'negative' appendices still ranges between 15 and 20%, appendicitis in 'borderline' cases remains a challenging disease. As previously described, cell adhesion molecule expression correlates with different stages of appendicitis. Therefore, it was of interest to determine whether the 'negative' appendix correlated with the absence of E-selectin or vascular cell adhesion molecule-1 (VCAM-1). Methods: Nineteen grossly normal appendices from a series of 120 appendectomy specimens from patients with suspected appendicitis were analysed in frozen sections for the expression of E-selectin and VCAM-1. As control, 5 normal appendices were stained. Results: This study showed a coexpression of E-selectin and VCAM-1 in endothelial cells in early and recurrent appendicitis. In patients with symptoms for less than 6 h, only E-selectin was detected. Cases with fibrosis and luminal obliteration were only positive for VCAM-1. In cases of early appendicitis with symptoms of less than 6 h duration, a discordance between histological and immunohistochemical results was found. Conclusions: This report indicates that E-selectin and VCAM-1 expression could be useful parameters in the diagnosis of appendicitis in borderline cases.

Support services for vulnerable patients by a multidisciplinary team in an emergency department

Introduction: Individuals with poor social determinants of health aremore likely to receive improper healthcare. Frequent Users (FUs) ofEmergency Departments (ED) (defined as >4 visits in the previous12 months) represent a subgroup of vulnerable patients presentingwith specific medical and social needs. They usually account for highhealthcare costs by overusing the healthcare system. In 2008-2009,FUs accounted for 4% of our ED patients but 17% of all our ED visits.Methods: We conducted a prospective cohort of patients admitted toour ED with vulnerabilities in ≥3 specific domains (somatic or mentaldiseases, risk behaviors, social determinants of health, and healthcareuse). Patients were either directly identified by a multidisciplinary team(two nurses, one social worker, one physician) or referred to that teamby the ED staff during opening hours from July 1st 2010 to April 30th2011.Results: 127 patients were included (67% males), aged 43 years (SD15); 65% were migrants. They had a median of 6 ED visits (interquartilerange (IQR) 8-1) in the previous 12 months, representing a total of 697visits. The most frequently affected domains during the index visit were:71% somatic, 61% psychiatric, 75% risk behaviors, 97% social and84% healthcare use issues. Each case required a median of 234minutes (IQR 300-90) dedicated to assess their outpatient network(99% of the patients), to set up an ambulatory medical follow-up (43%)or a meeting with social services (40%).Conclusions: Vulnerability affected ED patients in more than onedomain. Vulnerable patients have complex needs that were difficult toaddress in the time-pressured ED setting. Although ED consultationoffers immediate access to medical care, EDs are dedicated more foracute short-term somatic care. Caring for a growing number ofvulnerable patients requires a different type of management. Limitedevidence shows that multidisciplinary case-management interventionshave demonstrated positive outcomes in terms of reducing ED useand costs, and improvement of patient's medical and social outcomes.A randomized trial of case-management is underway to confirm theresults of observational studies.

TACI, unlike BAFF-R, is solely activated by oligomeric BAFF and APRIL to support survival of activated B cells and plasmablasts.

The cytokine BAFF binds to the receptors TACI, BCMA, and BAFF-R on B cells, whereas APRIL binds to TACI and BCMA only. The signaling properties of soluble trimeric BAFF (BAFF 3-mer) were compared with those of higher-order BAFF oligomers. All forms of BAFF bound BAFF-R and TACI, and elicited BAFF-R-dependent signals in primary B cells. In contrast, signaling through TACI in mature B cells or plasmablasts was only achieved by higher-order BAFF and APRIL oligomers, all of which were also po-tent activators of a multimerization-dependent reporter signaling pathway. These results indicate that, although BAFF-R and TACI can provide B cells with similar signals, only BAFF-R, but not TACI, can respond to soluble BAFF 3-mer, which is the main form of BAFF found in circulation. BAFF 60-mer, an efficient TACI agonist, was also detected in plasma of BAFF transgenic and nontransgenic mice and was more than 100-fold more active than BAFF 3-mer for the activation of multimerization-dependent signals. TACI supported survival of activated B cells and plasmablasts in vitro, providing a rational basis to explain the immunoglobulin deficiency reported in TACI-deficient persons.

Geomodelling of a fluvial system with semi-supervised support vector regression

Fluvial deposits are a challenge for modelling flow in sub-surface reservoirs. Connectivity and continuity of permeable bodies have a major impact on fluid flow in porous media. Contemporary object-based and multipoint statistics methods face a problem of robust representation of connected structures. An alternative approach to model petrophysical properties is based on machine learning algorithm ? Support Vector Regression (SVR). Semi-supervised SVR is able to establish spatial connectivity taking into account the prior knowledge on natural similarities. SVR as a learning algorithm is robust to noise and captures dependencies from all available data. Semi-supervised SVR applied to a synthetic fluvial reservoir demonstrated robust results, which are well matched to the flow performance

Example-based support vector machine for drug concentration analysis

Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (S VM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM-based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.

Le Soutien psychiatrique Intensif dans le Milieu (SIM) à Lausanne: un projet pilote [Intensive Psychiatric Support at the Setting in Lausanne: a pilot project]

While the hospital remains an important element of the psychiatric health-care system, the fact that it is always the best place to treat acute psychotic episodes is still debated. After a brief review of the literature relative to the main existing community care models, the authors describe the development in the Department Universitaire de Psychiatrie Adulte (DUPA), of an alternative to hospitalisation for patient going through a severe acute psychiatric episode. They present three clinical situations and the aims of the research project, which will follow this pilot phase.

System-level Support for Mobile Ad hoc Communications: an Algorithmic & Practical Approach

A mobile ad hoc network (MANET) is a decentralized and infrastructure-less network. This thesis aims to provide support at the system-level for developers of applications or protocols in such networks. To do this, we propose contributions in both the algorithmic realm and in the practical realm. In the algorithmic realm, we contribute to the field by proposing different context-aware broadcast and multicast algorithms in MANETs, namely six-shot broadcast, six-shot multicast, PLAN-B and ageneric algorithmic approach to optimize the power consumption of existing algorithms. For each algorithm we propose, we compare it to existing algorithms that are either probabilistic or context-aware, and then we evaluate their performance based on simulations. We demonstrate that in some cases, context-aware information, such as location or signal-strength, can improve the effciency. In the practical realm, we propose a testbed framework, namely ManetLab, to implement and to deploy MANET-specific protocols, and to evaluate their performance. This testbed framework aims to increase the accuracy of performance evaluation compared to simulations, while keeping the ease of use offered by the simulators to reproduce a performance evaluation. By evaluating the performance of different probabilistic algorithms with ManetLab, we observe that both simulations and testbeds should be used in a complementary way. In addition to the above original contributions, we also provide two surveys about system-level support for ad hoc communications in order to establish a state of the art. The first is about existing broadcast algorithms and the second is about existing middleware solutions and the way they deal with privacy and especially with location privacy. - Un réseau mobile ad hoc (MANET) est un réseau avec une architecture décentralisée et sans infrastructure. Cette thèse vise à fournir un support adéquat, au niveau système, aux développeurs d'applications ou de protocoles dans de tels réseaux. Dans ce but, nous proposons des contributions à la fois dans le domaine de l'algorithmique et dans celui de la pratique. Nous contribuons au domaine algorithmique en proposant différents algorithmes de diffusion dans les MANETs, algorithmes qui sont sensibles au contexte, à savoir six-shot broadcast,six-shot multicast, PLAN-B ainsi qu'une approche générique permettant d'optimiser la consommation d'énergie de ces algorithmes. Pour chaque algorithme que nous proposons, nous le comparons à des algorithmes existants qui sont soit probabilistes, soit sensibles au contexte, puis nous évaluons leurs performances sur la base de simulations. Nous montrons que, dans certains cas, des informations liées au contexte, telles que la localisation ou l'intensité du signal, peuvent améliorer l'efficience de ces algorithmes. Sur le plan pratique, nous proposons une plateforme logicielle pour la création de bancs d'essai, intitulé ManetLab, permettant d'implémenter, et de déployer des protocoles spécifiques aux MANETs, de sorte à évaluer leur performance. Cet outil logiciel vise à accroître la précision desévaluations de performance comparativement à celles fournies par des simulations, tout en conservant la facilité d'utilisation offerte par les simulateurs pour reproduire uneévaluation de performance. En évaluant les performances de différents algorithmes probabilistes avec ManetLab, nous observons que simulateurs et bancs d'essai doivent être utilisés de manière complémentaire. En plus de ces contributions principales, nous fournissons également deux états de l'art au sujet du support nécessaire pour les communications ad hoc. Le premier porte sur les algorithmes de diffusion existants et le second sur les solutions de type middleware existantes et la façon dont elles traitent de la confidentialité, en particulier celle de la localisation.

Cost-effective experimental design to support modeling of concentration-response functions

Modeling concentration-response function became extremely popular in ecotoxicology during the last decade. Indeed, modeling allows determining the total response pattern of a given substance. However, reliable modeling is consuming in term of data, which is in contradiction with the current trend in ecotoxicology, which aims to reduce, for cost and ethical reasons, the number of data produced during an experiment. It is therefore crucial to determine experimental design in a cost-effective manner. In this paper, we propose to use the theory of locally D-optimal designs to determine the set of concentrations to be tested so that the parameters of the concentration-response function can be estimated with high precision. We illustrated this approach by determining the locally D-optimal designs to estimate the toxicity of the herbicide dinoseb on daphnids and algae. The results show that the number of concentrations to be tested is often equal to the number of parameters and often related to the their meaning, i.e. they are located close to the parameters. Furthermore, the results show that the locally D-optimal design often has the minimal number of support points and is not much sensitive to small changes in nominal values of the parameters. In order to reduce the experimental cost and the use of test organisms, especially in case of long-term studies, reliable nominal values may therefore be fixed based on prior knowledge and literature research instead of on preliminary experiments