Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

E-learning initiatives in forensic interpretation: report on experiences from current projects and outlook

This paper reports on the purpose, design, methodology and target audience of E-learning courses in forensic interpretation offered by the authors since 2010, including practical experiences made throughout the implementation period of this project. This initiative was motivated by the fact that reporting results of forensic examinations in a logically correct and scientifically rigorous way is a daily challenge for any forensic practitioner. Indeed, interpretation of raw data and communication of findings in both written and oral statements are topics where knowledge and applied skills are needed. Although most forensic scientists hold educational records in traditional sciences, only few actually followed full courses that focussed on interpretation issues. Such courses should include foundational principles and methodology - including elements of forensic statistics - for the evaluation of forensic data in a way that is tailored to meet the needs of the criminal justice system. In order to help bridge this gap, the authors' initiative seeks to offer educational opportunities that allow practitioners to acquire knowledge and competence in the current approaches to the evaluation and interpretation of forensic findings. These cover, among other aspects, probabilistic reasoning (including Bayesian networks and other methods of forensic statistics, tools and software), case pre-assessment, skills in the oral and written communication of uncertainty, and the development of independence and self-confidence to solve practical inference problems. E-learning was chosen as a general format because it helps to form a trans-institutional online-community of practitioners from varying forensic disciplines and workfield experience such as reporting officers, (chief) scientists, forensic coordinators, but also lawyers who all can interact directly from their personal workplaces without consideration of distances, travel expenses or time schedules. In the authors' experience, the proposed learning initiative supports participants in developing their expertise and skills in forensic interpretation, but also offers an opportunity for the associated institutions and the forensic community to reinforce the development of a harmonized view with regard to interpretation across forensic disciplines, laboratories and judicial systems.

How can we teach EBM in clinical practice? : an analysis of barriers to implementation of on-the-job EBM teaching and learning.

Introduction: Evidence-based medicine (EBM) improves the quality of health care. Courses on how to teach EBM in practice are available, but knowledge does not automatically imply its application in teaching. We aimed to identify and compare barriers and facilitators for teaching EBM in clinical practice in various European countries. Methods: A questionnaire was constructed listing potential barriers and facilitators for EBM teaching in clinical practice. Answers were reported on a 7-point Likert scale ranging from not at all being a barrier to being an insurmountable barrier. Results: The questionnaire was completed by 120 clinical EBM teachers from 11 countries. Lack of time was the strongest barrier for teaching EBM in practice (median 5). Moderate barriers were the lack of requirements for EBM skills and a pyramid hierarchy in health care management structure (median 4). In Germany, Hungary and Poland, reading and understanding articles in English was a higher barrier than in the other countries. Conclusion: Incorporation of teaching EBM in practice faces several barriers to implementation. Teaching EBM in clinical settings is most successful where EBM principles are culturally embedded and form part and parcel of everyday clinical decisions and medical practice.

Multitask learning of environmental spatial data

The present research deals with an application of artificial neural networks for multitask learning from spatial environmental data. The real case study (sediments contamination of Geneva Lake) consists of 8 pollutants. There are different relationships between these variables, from linear correlations to strong nonlinear dependencies. The main idea is to construct a subsets of pollutants which can be efficiently modeled together within the multitask framework. The proposed two-step approach is based on: 1) the criterion of nonlinear predictability of each variable ?k? by analyzing all possible models composed from the rest of the variables by using a General Regression Neural Network (GRNN) as a model; 2) a multitask learning of the best model using multilayer perceptron and spatial predictions. The results of the study are analyzed using both machine learning and geostatistical tools.

Reversal of activity-mediated spine dynamics and learning impairment in a mouse model of Fragile X syndrome.

Fragile X syndrome (FXS) is characterized by intellectual disability and autistic traits, and results from the silencing of the FMR1 gene coding for a protein implicated in the regulation of protein synthesis at synapses. The lack of functional Fragile X mental retardation protein has been proposed to result in an excessive signaling of synaptic metabotropic glutamate receptors, leading to alterations of synapse maturation and plasticity. It remains, however, unclear how mechanisms of activity-dependent spine dynamics are affected in Fmr knockout (Fmr1-KO) mice and whether they can be reversed. Here we used a repetitive imaging approach in hippocampal slice cultures to investigate properties of structural plasticity and their modulation by signaling pathways. We found that basal spine turnover was significantly reduced in Fmr1-KO mice, but markedly enhanced by activity. Additionally, activity-mediated spine stabilization was lost in Fmr1-KO mice. Application of the metabotropic glutamate receptor antagonist α-Methyl-4-carboxyphenylglycine (MCPG) enhanced basal turnover, improved spine stability, but failed to reinstate activity-mediated spine stabilization. In contrast, enhancing phosphoinositide-3 kinase (PI3K) signaling, a pathway implicated in various aspects of synaptic plasticity, reversed both basal turnover and activity-mediated spine stabilization. It also restored defective long-term potentiation mechanisms in slices and improved reversal learning in Fmr1-KO mice. These results suggest that modulation of PI3K signaling could contribute to improve the cognitive deficits associated with FXS.

Penser la médecine communautaire s'apprend avec les pairs. [The spirit of community medicine: students learning from students].

At the University of Lausanne third-year medical students are given the task of spending a month investigating a question of community medicine. In 2009, four students evaluated the legitimacy of health insurers intervening in the management of depression. They found that health insurers put pressure on public authorities during the development of legislation governing the health system and reimbursement for treatment. This fact emerged during the scientific investigation led jointly by the team in the course of the "module of immersion in community medicine." This paper presents each step of their study. The example chosen illustrates the learning objectives covered by the module.

The development and pilot-testing of a training curriculum in adolescent medicine and health.

PURPOSE: To select and propose a set of knowledge, attitudes, and skills essential for the care of adolescents; to encourage the development of adolescent health multidisciplinary networks; and to set up training programs in as many European countries as possible. METHODS: The curriculum was developed by 16 physicians from 11 European countries with various professional specializations. In line with modern guidelines in medical education, it is a modular, flexible instrument which covers the main teaching areas in the field, such as basic skills (i.e. setting, rights and confidentiality, gender and cultural issues) as well as specific themes (i.e. sexual and reproductive health, eating disorders, chronic conditions). It consists of 17 thematic modules, each containing detailed objectives, learning approaches, examples, and evaluation methods. RESULT: Two international one-week summer schools were used to assess the feasibility and appropriateness of the curriculum. The overall evaluation was good, with most of the items surpassing three on a four-point Likert scale. However, it pointed to several aspects (process and content) which will need to be refined in the future, such as an increase in interactive sessions (role playing), and a better mix of clinical and public health issues.

Learning wind fields with multiple kernels

This paper presents multiple kernel learning (MKL) regression as an exploratory spatial data analysis and modelling tool. The MKL approach is introduced as an extension of support vector regression, where MKL uses dedicated kernels to divide a given task into sub-problems and to treat them separately in an effective way. It provides better interpretability to non-linear robust kernel regression at the cost of a more complex numerical optimization. In particular, we investigate the use of MKL as a tool that allows us to avoid using ad-hoc topographic indices as covariables in statistical models in complex terrains. Instead, MKL learns these relationships from the data in a non-parametric fashion. A study on data simulated from real terrain features confirms the ability of MKL to enhance the interpretability of data-driven models and to aid feature selection without degrading predictive performances. Here we examine the stability of the MKL algorithm with respect to the number of training data samples and to the presence of noise. The results of a real case study are also presented, where MKL is able to exploit a large set of terrain features computed at multiple spatial scales, when predicting mean wind speed in an Alpine region.

Se former à l'entretien motivationnel pour aider ses patients à changer: Les étudiants en médecine le confirment [Learning motivational interviewing to help patients change their health-related behaviors: medical students confirm it].

At the Lausanne University, 5th year medical students were trained in Motivational interviewing (MI). Eight hours of training improved their competence in the use of this approach. This experience supports the implementation of MI training in medical schools. Motivational interviewing allows the health professional to actively involve the patient in this behavior change process (drinking, smoking, diet, exercise, medication adherence, etc.), by encouraging reflection and reinforcing personal motivation and resources.

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.