Ontology augmentation:combining semantic web and text resources

This work investigates the process of selecting, extracting and reorganizing content from Semantic Web information sources, to produce an ontology meeting the specifications of a particular domain and/or task. The process is combined with traditional text-based ontology learning methods to achieve tolerance to knowledge incompleteness. The paper describes the approach and presents experiments in which an ontology was built for a diet evaluation task. Although the example presented concerns the specific case of building a nutritional ontology, the methods employed are domain independent and transferrable to other use cases. © 2011 ACM.

Using genetic programming and decision trees for generating structural descriptions of four bar mechanisms

Four bar mechanisms are basic components of many important mechanical devices. The kinematic synthesis of four bar mechanisms is a difficult design problem. A novel method that combines the genetic programming and decision tree learning methods is presented. We give a structural description for the class of mechanisms that produce desired coupler curves. Constructive induction is used to find and characterize feasible regions of the design space. Decision trees constitute the learning engine, and the new features are created by genetic programming.

AllerTOP v.2 - a server for in silico prediction of allergens

Allergy is an overreaction by the immune system to a previously encountered, ordinarily harmless substance - typically proteins - resulting in skin rash, swelling of mucous membranes, sneezing or wheezing, or other abnormal conditions. The use of modified proteins is increasingly widespread: their presence in food, commercial products, such as washing powder, and medical therapeutics and diagnostics, makes predicting and identifying potential allergens a crucial societal issue. The prediction of allergens has been explored widely using bioinformatics, with many tools being developed in the last decade; many of these are freely available online. Here, we report a set of novel models for allergen prediction utilizing amino acid E-descriptors, auto- and cross-covariance transformation, and several machine learning methods for classification, including logistic regression (LR), decision tree (DT), naïve Bayes (NB), random forest (RF), multilayer perceptron (MLP) and k nearest neighbours (kNN). The best performing method was kNN with 85.3% accuracy at 5-fold cross-validation. The resulting model has been implemented in a revised version of the AllerTOP server (http://www.ddg-pharmfac.net/AllerTOP). © Springer-Verlag 2014.

Virtual Environments as an Education Tool for Digital Natives

Report published in the Proceedings of the National Conference on "Education in the Information Society", Plovdiv, May, 2013

AllerTOP - a server for in silico prediction of allergens

Background: Allergy is a form of hypersensitivity to normally innocuous substances, such as dust, pollen, foods or drugs. Allergens are small antigens that commonly provoke an IgE antibody response. There are two types of bioinformatics-based allergen prediction. The first approach follows FAO/WHO Codex alimentarius guidelines and searches for sequence similarity. The second approach is based on identifying conserved allergenicity-related linear motifs. Both approaches assume that allergenicity is a linearly coded property. In the present study, we applied ACC pre-processing to sets of known allergens, developing alignment-independent models for allergen recognition based on the main chemical properties of amino acid sequences.Results: A set of 684 food, 1,156 inhalant and 555 toxin allergens was collected from several databases. A set of non-allergens from the same species were selected to mirror the allergen set. The amino acids in the protein sequences were described by three z-descriptors (z1, z2 and z3) and by auto- and cross-covariance (ACC) transformation were converted into uniform vectors. Each protein was presented as a vector of 45 variables. Five machine learning methods for classification were applied in the study to derive models for allergen prediction. The methods were: discriminant analysis by partial least squares (DA-PLS), logistic regression (LR), decision tree (DT), naïve Bayes (NB) and k nearest neighbours (kNN). The best performing model was derived by kNN at k = 3. It was optimized, cross-validated and implemented in a server named AllerTOP, freely accessible at http://www.pharmfac.net/allertop. AllerTOP also predicts the most probable route of exposure. In comparison to other servers for allergen prediction, AllerTOP outperforms them with 94% sensitivity.Conclusions: AllerTOP is the first alignment-free server for in silico prediction of allergens based on the main physicochemical properties of proteins. Significantly, as well allergenicity AllerTOP is able to predict the route of allergen exposure: food, inhalant or toxin. © 2013 Dimitrov et al.; licensee BioMed Central Ltd.

Algorithm visualization in programming education

This paper introduces the theory of algorithm visualization and its education-related results obtained so far, then an algorithm visualization tool is going to be presented as an example, which we will finally evaluate. This article illustrates furthermore how algorithm visualization tools can be used by teachers and students during the teaching and learning process of programming, and equally evaluates teaching and learning methods. Two tools will be introduced: Jeliot and TRAKLA2.

Mitigating congestion by integrating time forecasting and realtime information aggregation in cellular networks

An iterative travel time forecasting scheme, named the Advanced Multilane Prediction based Real-time Fastest Path (AMPRFP) algorithm, is presented in this dissertation. This scheme is derived from the conventional kernel estimator based prediction model by the association of real-time nonlinear impacts that caused by neighboring arcs’ traffic patterns with the historical traffic behaviors. The AMPRFP algorithm is evaluated by prediction of the travel time of congested arcs in the urban area of Jacksonville City. Experiment results illustrate that the proposed scheme is able to significantly reduce both the relative mean error (RME) and the root-mean-squared error (RMSE) of the predicted travel time. To obtain high quality real-time traffic information, which is essential to the performance of the AMPRFP algorithm, a data clean scheme enhanced empirical learning (DCSEEL) algorithm is also introduced. This novel method investigates the correlation between distance and direction in the geometrical map, which is not considered in existing fingerprint localization methods. Specifically, empirical learning methods are applied to minimize the error that exists in the estimated distance. A direction filter is developed to clean joints that have negative influence to the localization accuracy. Synthetic experiments in urban, suburban and rural environments are designed to evaluate the performance of DCSEEL algorithm in determining the cellular probe’s position. The results show that the cellular probe’s localization accuracy can be notably improved by the DCSEEL algorithm. Additionally, a new fast correlation technique for overcoming the time efficiency problem of the existing correlation algorithm based floating car data (FCD) technique is developed. The matching process is transformed into a 1-dimensional (1-D) curve matching problem and the Fast Normalized Cross-Correlation (FNCC) algorithm is introduced to supersede the Pearson product Moment Correlation Co-efficient (PMCC) algorithm in order to achieve the real-time requirement of the FCD method. The fast correlation technique shows a significant improvement in reducing the computational cost without affecting the accuracy of the matching process.

Statistical dialog management for health interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. ^ Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. ^ The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. ^ In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.^

Escrita colaborativa com google docs: flash fiction, noticing e aprendizagem de inglês como L2

Google Docs (GD) is an online word processor with which multiple authors can work on the same document, in a synchronous or asynchronous manner, which can help develop the ability of writing in English (WEISSHEIMER; SOARES, 2012). As they write collaboratively, learners find more opportunities to notice the gaps in their written production, since they are exposed to more input from the fellow co-authors (WEISSHEIMER; BERGSLEITHNER; LEANDRO, 2012) and prioritize the process of text (re)construction instead of the concern with the final product, i.e., the final version of the text (LEANDRO; WEISSHEIMER; COOPER, 2013). Moreover, when it comes to second language (L2) learning, producing language enables the consolidation of existing knowledge as well as the internalization of new knowledge (SWAIN, 1985; 1993). Taking this into consideration, this mixed-method (DÖRNYEI, 2007) quasi-experimental (NUNAN, 1999) study aims at investigating the impact of collaborative writing through GD on the development of the writing skill in English and on the noticing of syntactic structures (SCHMIDT, 1990). Thirtyfour university students of English integrated the cohort of the study: twenty-five were assigned to the experimental group and nine were assigned to the control group. All learners went through a pre-test and a post-test so that we could measure their noticing of syntactic structures. Learners in the experimental group were exposed to a blended learning experience, in which they took reading and writing classes at the university and collaboratively wrote three pieces of flash fiction (a complete story told in a hundred words), outside the classroom, online through GD, during eleven weeks. Learners in the control group took reading and writing classes at the university but did not practice collaborative writing. The first and last stories produced by the learners in the experimental group were analysed in terms of grammatical accuracy, operationalized as the number of grammar errors per hundred words (SOUSA, 2014), and lexical density, which refers to the relationship between the number of words produced with lexical properties and the number of words produced with grammatical properties (WEISSHEIMER, 2007; MEHNERT, 1998). Additionally, learners in the experimental group answered an online questionnaire on the blended learning experience they were exposed to. The quantitative results showed that the collaborative task led to the production of more lexically dense texts over the 11 weeks. The noticing and grammatical accuracy results were different from what we expected; however, they provide us with insights on measurement issues, in the case of noticing, and on the participants‟ positive attitude towards collaborative writing with flash fiction. The qualitative results also shed light on the usefulness of computer-mediated collaborative writing in L2 learning.

Statistical Dialog Management for Health Interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.

The design studio as liminal space

The context of this research focuses on the efficacy of design studio as a form of teaching and learning. The established model of project-based teaching makes simple parallels between studio and professional practice. However, through comparison of the discourses it is clear that they are of different character. The protocols of the tutorial tradition can act to position the tutor as a defender of the knowledge community rather than a discourse guide for the student. The question arises as to what constitutes the core knowledge that would enable better self-directed study. Rather than focus on key knowledge, there has been an attempt in other fields to agree and share ‘threshold concepts’ within disciplinary knowledge. Meyer and Land describe threshold concepts as representing “a transformed way of understanding, or interpreting or viewing something without which the learner cannot progress [1]. The tutor’s role should be to assist in transforming student’s understanding through the mastery of the ‘troublesome knowledge’ that threshold concepts may embody. Teaching and learning environments under such approaches have been described as ‘liminal’: holding the learner in an ‘in-between’ state new understanding may be difficult and involve identity shifts. Research on the consequence of pressures on facilities and studio space concur, and indicate that studio spaces can be much better used in assisting the path of learning [2]. Through an overview map of threshold concepts, the opportunities for blended learning in supporting student learning in the liminal space of the design studio become much clearer [3] Design studio needs to be recontextualised within the discourse of higher education scholarship, based on a clarified curriculum built from an understanding of what constitutes its threshold concepts. The studio needs to be reconsidered as a space quite unlike that of the practitioner, a liminal space. 1. Meyer, J.H.F. and R. Land, Threshold concepts and troublesome knowledge. Overcoming Barriers to Student Learning: Threshold concepts and troublesome knowledge., 2006: p. 19. 2. Cai, H. and S. Khan, The Common First Year Studio in a Hot-desking Age: An Explorative Study on the Studio Environment and Learning. Journal for Education in the Built Environment 2010. 5(2): p. 39-64. 3. Pektas, S.T., The Blended Design Studio: An Appraisal of New Delivery Modes in Design Education. Procedia - Social and Behavioral Sciences, 2012. 51(0): p. 692-697.

Bayesian nonparametric latent variable models

L’un des problèmes importants en apprentissage automatique est de déterminer la complexité du modèle à apprendre. Une trop grande complexité mène au surapprentissage, ce qui correspond à trouver des structures qui n’existent pas réellement dans les données, tandis qu’une trop faible complexité mène au sous-apprentissage, c’est-à-dire que l’expressivité du modèle est insuffisante pour capturer l’ensemble des structures présentes dans les données. Pour certains modèles probabilistes, la complexité du modèle se traduit par l’introduction d’une ou plusieurs variables cachées dont le rôle est d’expliquer le processus génératif des données. Il existe diverses approches permettant d’identifier le nombre approprié de variables cachées d’un modèle. Cette thèse s’intéresse aux méthodes Bayésiennes nonparamétriques permettant de déterminer le nombre de variables cachées à utiliser ainsi que leur dimensionnalité. La popularisation des statistiques Bayésiennes nonparamétriques au sein de la communauté de l’apprentissage automatique est assez récente. Leur principal attrait vient du fait qu’elles offrent des modèles hautement flexibles et dont la complexité s’ajuste proportionnellement à la quantité de données disponibles. Au cours des dernières années, la recherche sur les méthodes d’apprentissage Bayésiennes nonparamétriques a porté sur trois aspects principaux : la construction de nouveaux modèles, le développement d’algorithmes d’inférence et les applications. Cette thèse présente nos contributions à ces trois sujets de recherches dans le contexte d’apprentissage de modèles à variables cachées. Dans un premier temps, nous introduisons le Pitman-Yor process mixture of Gaussians, un modèle permettant l’apprentissage de mélanges infinis de Gaussiennes. Nous présentons aussi un algorithme d’inférence permettant de découvrir les composantes cachées du modèle que nous évaluons sur deux applications concrètes de robotique. Nos résultats démontrent que l’approche proposée surpasse en performance et en flexibilité les approches classiques d’apprentissage. Dans un deuxième temps, nous proposons l’extended cascading Indian buffet process, un modèle servant de distribution de probabilité a priori sur l’espace des graphes dirigés acycliques. Dans le contexte de réseaux Bayésien, ce prior permet d’identifier à la fois la présence de variables cachées et la structure du réseau parmi celles-ci. Un algorithme d’inférence Monte Carlo par chaîne de Markov est utilisé pour l’évaluation sur des problèmes d’identification de structures et d’estimation de densités. Dans un dernier temps, nous proposons le Indian chefs process, un modèle plus général que l’extended cascading Indian buffet process servant à l’apprentissage de graphes et d’ordres. L’avantage du nouveau modèle est qu’il admet les connections entres les variables observables et qu’il prend en compte l’ordre des variables. Nous présentons un algorithme d’inférence Monte Carlo par chaîne de Markov avec saut réversible permettant l’apprentissage conjoint de graphes et d’ordres. L’évaluation est faite sur des problèmes d’estimations de densité et de test d’indépendance. Ce modèle est le premier modèle Bayésien nonparamétrique permettant d’apprendre des réseaux Bayésiens disposant d’une structure complètement arbitraire.

Network Training Services Ltd case study

Case study on developing a consistent and supportive approach to blended learning

Curriculare Integration elektronischer Lehr-Lernmodule in die traditionelle Präsenzlehre – dargestellt am Beispiel des Projektes IMPULSEC

Im Rahmen universitärer Projekte entwickelte E-Learning-Angebote werden nach ihrer Fertigstellung in der Regel nicht isoliert in der Lehre eingesetzt. Vielmehr sollen sie in bereits bestehende Curricula und traditionelle Präsenzveranstaltungen integriert werden. Der vorliegende Beitrag beschäftigt sich mit der Frage, wie eine solche Integration zu leisten ist und welche Aspekte dabei zu beachten, welche Aufgaben zu übernehmen sind. Am Beispiel des Projektes IMPULSEC wird gezeigt, wie und unter welchen Voraussetzungen am Entwicklungsstandort Osnabrück Lerninhalte und -ziele, Medien und Methoden sowie Sozial- und Organisationsformen von E-Learning-Angeboten mit denen der traditionellen Präsenzlehre zusammengeführt werden.(DIPF/Orig.)