Gestionnaire de vie privée : un cadre pour la protection de la vie privée dans les interactions entre apprenants

L’évolution continue des besoins d’apprentissage vers plus d’efficacité et plus de personnalisation a favorisé l’émergence de nouveaux outils et dimensions dont l’objectif est de rendre l’apprentissage accessible à tout le monde et adapté aux contextes technologiques et sociaux. Cette évolution a donné naissance à ce que l’on appelle l'apprentissage social en ligne mettant l'accent sur l’interaction entre les apprenants. La considération de l’interaction a apporté de nombreux avantages pour l’apprenant, à savoir établir des connexions, échanger des expériences personnelles et bénéficier d’une assistance lui permettant d’améliorer son apprentissage. Cependant, la quantité d'informations personnelles que les apprenants divulguent parfois lors de ces interactions, mène, à des conséquences souvent désastreuses en matière de vie privée comme la cyberintimidation, le vol d’identité, etc. Malgré les préoccupations soulevées, la vie privée en tant que droit individuel représente une situation idéale, difficilement reconnaissable dans le contexte social d’aujourd’hui. En effet, on est passé d'une conceptualisation de la vie privée comme étant un noyau des données sensibles à protéger des pénétrations extérieures à une nouvelle vision centrée sur la négociation de la divulgation de ces données. L’enjeu pour les environnements sociaux d’apprentissage consiste donc à garantir un niveau maximal d’interaction pour les apprenants tout en préservant leurs vies privées. Au meilleur de nos connaissances, la plupart des innovations dans ces environnements ont porté sur l'élaboration des techniques d’interaction, sans aucune considération pour la vie privée, un élément portant nécessaire afin de créer un environnement favorable à l’apprentissage. Dans ce travail, nous proposons un cadre de vie privée que nous avons appelé « gestionnaire de vie privée». Plus précisément, ce gestionnaire se charge de gérer la protection des données personnelles et de la vie privée de l’apprenant durant ses interactions avec ses co-apprenants. En s’appuyant sur l’idée que l’interaction permet d’accéder à l’aide en ligne, nous analysons l’interaction comme une activité cognitive impliquant des facteurs contextuels, d’autres apprenants, et des aspects socio-émotionnels. L'objectif principal de cette thèse est donc de revoir les processus d’entraide entre les apprenants en mettant en oeuvre des outils nécessaires pour trouver un compromis entre l’interaction et la protection de la vie privée. ii Ceci a été effectué selon trois niveaux : le premier étant de considérer des aspects contextuels et sociaux de l’interaction telle que la confiance entre les apprenants et les émotions qui ont initié le besoin d’interagir. Le deuxième niveau de protection consiste à estimer les risques de cette divulgation et faciliter la décision de protection de la vie privée. Le troisième niveau de protection consiste à détecter toute divulgation de données personnelles en utilisant des techniques d’apprentissage machine et d’analyse sémantique.

Sociopathic knowledge bases : correct knowledge can be harmful even given unlimited computation /

"College of Engineering, UILU-ENG-89-1757."

Information extraction from clinical and radiology notes for liver cancer staging

Thesis (Ph.D.)--University of Washington, 2016-06

Approaches and Strategy for Cancer Research and Surveillance Data: Integration, Information Pipeline, Data Models, and Informatics Opportunities

Thesis (Ph.D.)--University of Washington, 2016-04

Understanding human genome regulation through entropic graph-based regularization and submodular optimization

Thesis (Ph.D.)--University of Washington, 2016-06

Essays on the Analysis of Dynamic Games

Thesis (Ph.D.)--University of Washington, 2016-06

Submodular Optimization and Data Processing

Thesis (Ph.D.)--University of Washington, 2016-06

Dynamic Models under Uncertainty for Large-Scale Enterprise Systems

Thesis (Ph.D.)--University of Washington, 2016-06

Microarray expression profiling in melanoma reveals a BRAF mutation signature

We have used microarray gene expression pro. ling and machine learning to predict the presence of BRAF mutations in a panel of 61 melanoma cell lines. The BRAF gene was found to be mutated in 42 samples (69%) and intragenic mutations of the NRAS gene were detected in seven samples (11%). No cell line carried mutations of both genes. Using support vector machines, we have built a classifier that differentiates between melanoma cell lines based on BRAF mutation status. As few as 83 genes are able to discriminate between BRAF mutant and BRAF wild-type samples with clear separation observed using hierarchical clustering. Multidimensional scaling was used to visualize the relationship between a BRAF mutation signature and that of a generalized mitogen-activated protein kinase ( MAPK) activation ( either BRAF or NRAS mutation) in the context of the discriminating gene list. We observed that samples carrying NRAS mutations lie somewhere between those with or without BRAF mutations. These observations suggest that there are gene-specific mutation signals in addition to a common MAPK activation that result from the pleiotropic effects of either BRAF or NRAS on other signaling pathways, leading to measurably different transcriptional changes.

A tutorial on the cross-entropy method

The cross-entropy (CE) method is a new generic approach to combinatorial and multi-extremal optimization and rare event simulation. The purpose of this tutorial is to give a gentle introduction to the CE method. We present the CE methodology, the basic algorithm and its modifications, and discuss applications in combinatorial optimization and machine learning. combinatorial optimization

GANN: Genetic algorithm neural networks for the detection of conserved combinations of features in DNA

Background: The multitude of motif detection algorithms developed to date have largely focused on the detection of patterns in primary sequence. Since sequence-dependent DNA structure and flexibility may also play a role in protein-DNA interactions, the simultaneous exploration of sequence-and structure-based hypotheses about the composition of binding sites and the ordering of features in a regulatory region should be considered as well. The consideration of structural features requires the development of new detection tools that can deal with data types other than primary sequence. Results: GANN ( available at http://bioinformatics.org.au/gann) is a machine learning tool for the detection of conserved features in DNA. The software suite contains programs to extract different regions of genomic DNA from flat files and convert these sequences to indices that reflect sequence and structural composition or the presence of specific protein binding sites. The machine learning component allows the classification of different types of sequences based on subsamples of these indices, and can identify the best combinations of indices and machine learning architecture for sequence discrimination. Another key feature of GANN is the replicated splitting of data into training and test sets, and the implementation of negative controls. In validation experiments, GANN successfully merged important sequence and structural features to yield good predictive models for synthetic and real regulatory regions. Conclusion: GANN is a flexible tool that can search through large sets of sequence and structural feature combinations to identify those that best characterize a set of sequences.

The applicability of recurrent neural networks for biological sequence analysis

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Evaluation of unsupervised semantic mapping of natural language with Leximancer concept mapping

The Leximancer system is a relatively new method for transforming lexical co-occurrence information from natural language into semantic patterns in an unsupervised manner. It employs two stages of co-occurrence information extraction-semantic and relational-using a different algorithm for each stage. The algorithms used are statistical, but they employ nonlinear dynamics and machine learning. This article is an attempt to validate the output of Leximancer, using a set of evaluation criteria taken from content analysis that are appropriate for knowledge discovery tasks.

Fitness assessment of document model

Document classification is a supervised machine learning process, where predefined category labels are assigned to documents based on the hypothesis derived from training set of labelled documents. Documents cannot be directly interpreted by a computer system unless they have been modelled as a collection of computable features. Rogati and Yang [M. Rogati and Y. Yang, Resource selection for domain-specific cross-lingual IR, in SIGIR 2004: Proceedings of the 27th annual international conference on Research and Development in Information Retrieval, ACM Press, Sheffied: United Kingdom, pp. 154-161.] pointed out that the effectiveness of document classification system may vary in different domains. This implies that the quality of document model contributes to the effectiveness of document classification. Conventionally, model evaluation is accomplished by comparing the effectiveness scores of classifiers on model candidates. However, this kind of evaluation methods may encounter either under-fitting or over-fitting problems, because the effectiveness scores are restricted by the learning capacities of classifiers. We propose a model fitness evaluation method to determine whether a model is sufficient to distinguish positive and negative instances while still competent to provide satisfactory effectiveness with a small feature subset. Our experiments demonstrated how the fitness of models are assessed. The results of our work contribute to the researches of feature selection, dimensionality reduction and document classification.

Genes for the majority of group A streptococcal virulence factors and extracellular surface proteins do not confer an increased propensity to cause invasive disease

Background. The factors behind the reemergence of severe, invasive group A streptococcal (GAS) diseases are unclear, but it could be caused by altered genetic endowment in these organisms. However, data from previous studies assessing the association between single genetic factors and invasive disease are often conflicting, suggesting that other, as-yet unidentified factors are necessary for the development of this class of disease. Methods. In this study, we used a targeted GAS virulence microarray containing 226 GAS genes to determine the virulence gene repertoires of 68 GAS isolates (42 associated with invasive disease and 28 associated with noninvasive disease) collected in a defined geographic location during a contiguous time period. We then employed 3 advanced machine learning methods (genetic algorithm neural network, support vector machines, and classification trees) to identify genes with an increased association with invasive disease. Results. Virulence gene profiles of individual GAS isolates varied extensively among these geographically and temporally related strains. Using genetic algorithm neural network analysis, we identified 3 genes with a marginal overrepresentation in invasive disease isolates. Significantly, 2 of these genes, ssa and mf4, encoded superantigens but were only present in a restricted set of GAS M-types. The third gene, spa, was found in variable distributions in all M-types in the study. Conclusions. Our comprehensive analysis of GAS virulence profiles provides strong evidence for the incongruent relationships among any of the 226 genes represented on the array and the overall propensity of GAS to cause invasive disease, underscoring the pathogenic complexity of these diseases, as well as the importance of multiple bacteria and/ or host factors.