Interpretation: Printed Document Examination and Evidence

The literature dealing with the interpretation of results of examinations performed on "printed" documents is very limited. The absence of published literature reflects the absence of formal guidelines to help scientists assess the relationship between a questioned document and a particular printing technology. Generally, every printout, independent of the printing technology, may bear traces induced by characteristics of manufacture and/or acquired features of the printing device. A logical approach to help the scientist in the formal interpretation of such findings involves the consideration of a likelihood ratio. Three examples aim to show the application of this approach.

On the Schoenberg transformations in data analysis: theory and illustrations

The class of Schoenberg transformations, embedding Euclidean distances into higher dimensional Euclidean spaces, is presented, and derived from theorems on positive definite and conditionally negative definite matrices. Original results on the arc lengths, angles and curvature of the transformations are proposed, and visualized on artificial data sets by classical multidimensional scaling. A distance-based discriminant algorithm and a robust multidimensional centroid estimate illustrate the theory, closely connected to the Gaussian kernels of Machine Learning.

Do riverine barriers, history or introgression shape the genetic structuring of a common shrew (Sorex araneus) population?

The common shrew (Sorex araneus) is subdivided into numerous chromosome races. The Valais and Cordon chromosome races meet and hybridize at a mountain river in Les Houches (French Alps). Significant genetic structuring was recently reported among populations found on the Valais side of this hybrid zone. In this paper, a phylogenetic analysis and partial Mantel tests are used to investigate the patterns and causes of this structuring. A total of 185 shrews were trapped at 12 localities. All individuals were typed for nine microsatellite loci. Although several mountain rivers are found in the study area, riverine barriers do not have a significant influence on gene flow. Partial Mantel tests show that our result is caused by the influence of the hybrid zone with the Cordon race. The geographical patterns of this structuring are discussed in the context of the contact zone, which appears to extend up to a group of two rivers. The glacier they originate from is known to have cut the Arve valley as recently as 1818. The recent history of this glacier, its moraine and possibly rivers, may therefore be linked to the history of this hybrid zone.

Les méthodes d'ajustement dans les modèles d'évaluation de la mortalité hospitalière. Partie 1, Etude descriptive : document de travail

Suite à la demande du Président de la République de disposer d'indicateurs de mortalité en établissements de santé » (discours du 18 septembre 2008 sur le thème de la politique de la santé et de la réforme du système de soins), la Direction de la recherche, des études, de l'évaluation et des statistiques (DREES) a piloté en 2009, en lien avec la Direction générale de l'offre de soins (DGOS) et la Haute autorité de santé (HAS), l'instruction des aspects méthodologiques relatifs à la construction de ces indicateurs de mortalité. Cette revue de littérature portant sur les différentes méthodes d'ajustement a été réalisée dans ce cadre, à la demande conjointe de la DREES et de la HAS.Ce rapport décrit les méthodes et modèles d'estimation et d'ajustement de la mortalité hospitalière identifiées dans la littérature.Il ressort de cette revue, que d'une manière générale, trois questions méthodologiques majeures préoccupent les épidémiologistes, les chercheurs et les décideurs s'intéressant à l'indicateur de la mortalité hospitalière : i) premièrement, sur l'opportunité d'établir l'indicateur de mortalité hospitalière à partir de groupes de population de patients homogènes définis par des pathologies et/ou des procédures médicales/chirurgicales cibles ; ii) deuxièmement, sur le type d'approche analytique et de l'intérêt de prendre en compte plusieurs niveaux dans l'analyse statistique ; iii) enfin troisièmement, sur le choix des variables d'ajustement permettant de contrôler les différences de case-mix entre plusieurs établissements ou groupes de patients pour réaliser des comparaisons. [Ed.]

Guidance Document for Executive Order Number 17, March 25, 2010

Executive Order 17, signed by Governor Chester J. Culver on September 25, 2009, emphasizes revitalization of historic properties and cultural and entertainment districts and also supports safe and healthy work places, sustainable design and cost effective use of state resources. Specifically, the Executive Order requires that State entities managing or leasing real estate on behalf of the State shall give priority to the needs of public entities and the populations they serve consistent with the cost effective use of state revenues. It also indicates that existing resources and facilities shall be used where adequate, cost competitive and appropriate for efficient and effective current state operations.

Document sobre dones i ciència

El grup ha analitzat l'activitat científica, acadèmica i professional de les dones i com a resultat d'aquestes anàlisis detecta una sèrie de problemes de discriminació que obliguen a adoptar polítiques de gènere en les institucions públiques i privades d'investigació idocència. Aquesta problemàtica requereix un debat social informat que defineixi les actuacions que cal seguir i les modificacions normativesque cal fer per eradicar les situacions de desigualtat.

Document sobre la interrupció voluntària de l'embaràs

El Grup presenta un document d'opinió amb la voluntat d'intervenir en el debat sobre la interrupció voluntària de l'embaràs i proposarmesures normatives que posin fi a l'actual situació d¿inseguretat jurídica derivadade la distorsionada aplicació que s'efectua de la desfasada legislació vigent.L'avortament és un veritable problema de salut pública i tant l'ètica com el drethan de plantejar pautes de conducta assumibles per la majoria dels ciutadans irespectuoses amb les minories, tenint sempre com a marc de referència i principiindeclinable el respecte als Drets Humans.

Document sobre l'objecció de consciència en sanitat

Aquest document parteix del reconeixement del principi d'autonomia de les personesi de la llibertat de consciència, ideològica i religiosa. I precisament per això exposael risc que, en la pràctica sanitària, l'exercici de l'objecció de consciència pugui fercol·lisió amb els drets dels usuaris. Per aquesta raó, l'Administració i les diversesinstitucions involucrades, han de prendre les mesures necessàries per facilitar la compatibilitat de l'exercici dels drets i les decisions de totes les persones implicades.

Machine learning analysis and modeling of interest rate curves

The present research deals with the review of the analysis and modeling of Swiss franc interest rate curves (IRC) by using unsupervised (SOM, Gaussian Mixtures) and supervised machine (MLP) learning algorithms. IRC are considered as objects embedded into different feature spaces: maturities; maturity-date, parameters of Nelson-Siegel model (NSM). Analysis of NSM parameters and their temporal and clustering structures helps to understand the relevance of model and its potential use for the forecasting. Mapping of IRC in a maturity-date feature space is presented and analyzed for the visualization and forecasting purposes.

Advanced geostatistical and machine-learning models for spatial data analysis of radioactively contaminated regions

Radioactive soil-contamination mapping and risk assessment is a vital issue for decision makers. Traditional approaches for mapping the spatial concentration of radionuclides employ various regression-based models, which usually provide a single-value prediction realization accompanied (in some cases) by estimation error. Such approaches do not provide the capability for rigorous uncertainty quantification or probabilistic mapping. Machine learning is a recent and fast-developing approach based on learning patterns and information from data. Artificial neural networks for prediction mapping have been especially powerful in combination with spatial statistics. A data-driven approach provides the opportunity to integrate additional relevant information about spatial phenomena into a prediction model for more accurate spatial estimates and associated uncertainty. Machine-learning algorithms can also be used for a wider spectrum of problems than before: classification, probability density estimation, and so forth. Stochastic simulations are used to model spatial variability and uncertainty. Unlike regression models, they provide multiple realizations of a particular spatial pattern that allow uncertainty and risk quantification. This paper reviews the most recent methods of spatial data analysis, prediction, and risk mapping, based on machine learning and stochastic simulations in comparison with more traditional regression models. The radioactive fallout from the Chernobyl Nuclear Power Plant accident is used to illustrate the application of the models for prediction and classification problems. This fallout is a unique case study that provides the challenging task of analyzing huge amounts of data ('hard' direct measurements, as well as supplementary information and expert estimates) and solving particular decision-oriented problems.

Applying machine learning methods to avalanche forecasting

Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.