Face description for perceptual user interfaces

[EN]We investigate mechanisms which can endow the computer with the ability of describing a human face by means of computer vision techniques. This is a necessary requirement in order to develop HCI approaches which make the user feel himself/herself perceived. This paper describes our experiences considering gender, race and the presence of moustache and glasses. This is accomplished comparing, on a set of 6000 facial images, two di erent face representation approaches: Principal Components Analysis (PCA) and Gabor lters. The results achieved using a Support Vector Machine (SVM) based classi er are promising and particularly better for the second representation approach.

Interfaces for Intelligent Environments

Presentaciones de la asignatura Interfaces para Entornos Inteligentes del Máster en Tecnologías de la Informática/Machine Learning and Data Mining.

A take on complexity: bio-molecules and human metabolism interaction modelling for health and nutrition with machine learning

The advent of omic data production has opened many new perspectives in the quest for modelling complexity in biophysical systems. With the capability of characterizing a complex organism through the patterns of its molecular states, observed at different levels through various omics, a new paradigm of investigation is arising. In this thesis, we investigate the links between perturbations of the human organism, described as the ensemble of crosstalk of its molecular states, and health. Machine learning plays a key role within this picture, both in omic data analysis and model building. We propose and discuss different frameworks developed by the author using machine learning for data reduction, integration, projection on latent features, pattern analysis, classification and clustering of omic data, with a focus on 1H NMR metabolomic spectral data. The aim is to link different levels of omic observations of molecular states, from nanoscale to macroscale, to study perturbations such as diseases and diet interpreted as changes in molecular patterns. The first part of this work focuses on the fingerprinting of diseases, linking cellular and systemic metabolomics with genomic to asses and predict the downstream of perturbations all the way down to the enzymatic network. The second part is a set of frameworks and models, developed with 1H NMR metabolomic at its core, to study the exposure of the human organism to diet and food intake in its full complexity, from epidemiological data analysis to molecular characterization of food structure.

Neural Machine Translation in the Field of Law. Analysis and Evaluation against Human Reference of NMT Raw Outputs of an Atto Costitutivo of S.r.l. from Italian into German.

Artificial Intelligence (AI) is gaining ever more ground in every sphere of human life, to the point that it is now even used to pass sentences in courts. The use of AI in the field of Law is however deemed quite controversial, as it could provide more objectivity yet entail an abuse of power as well, given that bias in algorithms behind AI may cause lack of accuracy. As a product of AI, machine translation is being increasingly used in the field of Law too in order to translate laws, judgements, contracts, etc. between different languages and different legal systems. In the legal setting of Company Law, accuracy of the content and suitability of terminology play a crucial role within a translation task, as any addition or omission of content or mistranslation of terms could entail legal consequences for companies. The purpose of the present study is to first assess which neural machine translation system between DeepL and ModernMT produces a more suitable translation from Italian into German of the atto costitutivo of an Italian s.r.l. in terms of accuracy of the content and correctness of terminology, and then to assess which translation proves to be closer to a human reference translation. In order to achieve the above-mentioned aims, two human and automatic evaluations are carried out based on the MQM taxonomy and the BLEU metric. Results of both evaluations show an overall better performance delivered by ModernMT in terms of content accuracy, suitability of terminology, and closeness to a human translation. As emerged from the MQM-based evaluation, its accuracy and terminology errors account for just 8.43% (as opposed to DeepL’s 9.22%), while it obtains an overall BLEU score of 29.14 (against DeepL’s 27.02). The overall performances however show that machines still face barriers in overcoming semantic complexity, tackling polysemy, and choosing domain-specific terminology, which suggests that the discrepancy with human translation may still be remarkable.

As diferentes interfaces da aventura na natureza : reflexões sobre a sociabilidade na vida contemporanea

Universidade Estadual de Campinas . Faculdade de Educação Física

Bond strength of a pit-and-fissure sealant associated to etch-and-rinse and self-etching adhesive systems to saliva-contaminated enamel: individual vs. simultaneous light curing

This study evaluated in vitro the shear bond strength (SBS) of a resin-based pit-and-fissure sealant [Fluroshield (F), Dentsply/Caulk] associated with either an etch-and-rinse [Adper Single Bond 2 (SB), 3M/ESPE] or a self-etching adhesive system [Clearfil S3 Bond (S3), Kuraray Co., Ltd.] to saliva-contaminated enamel, comparing two curing protocols: individual light curing of the adhesive system and the sealant or simultaneous curing of both materials. Mesial and distal enamel surfaces from 45 sound third molars were randomly assigned to 6 groups (n=15), according to the bonding technique: I - F was applied to 37% phosphoric acid etched enamel. The other groups were contaminated with fresh human saliva (0.01 mL; 10 s) after acid etching: II - SB and F were light cured separately; III - SB and F were light cured together; IV - S3 and F were light cured separately; V - S3 and F were light cured simultaneously; VI - F was applied to saliva-contaminated, acid-etched enamel without an intermediate bonding agent layer. SBS was tested to failure in a universal testing machine at 0.5 mm/min. Data were analyzed by one-way ANOVA and Fisher's test (α=0.05).The debonded specimens were examined with a stereomicroscope to assess the failure modes. Three representative specimens from each group were observed under scanning electron microscopy for a qualitative analysis. Mean SBS in MPa were: I-12.28 (±4.29); II-8.57 (±3.19); III-7.97 (±2.16); IV-12.56 (±3.11); V-11.45 (±3.77); and VI-7.47 (±1.99). In conclusion, individual or simultaneous curing of the intermediate bonding agent layer and the resin sealant did not seem to affect bond strength to saliva-contaminated enamel. S3/F presented significantly higher SBS than the that of the groups treated with SB etch-and-rinse adhesive system and similar SBS to that of the control group, in which the sealant was applied under ideal dry, noncontaminated conditions.

Evolutionary conservation of the membrane fusion machine

Recent structural studies of proteins mediating membrane fusion reveal intriguing similarities between diverse viral and mammalian systems. Particularly striking is the close similarity between the transmembrane envelope glycoproteins from the retrovirus HTLV-1 and the filovirus Ebola. These similarities suggest similar mechanisms of membrane fusion. The model that fits most currently available data suggests fusion activation in viral systems is driven by a symmetrical conformational change triggered by an activation event such as receptor binding or a pH change. The mammalian vesicle fusion mediated by the SNARE protein complex most likely occurs by a similar mechanism but without symmetry constraints.

Micromorphology of Resin-Dentin Interfaces Using One-Bottle Etch&Rinse and Self-Etching Adhesive Systems on Laser-Treated Dentin Surfaces: A Confocal Laser Scanning Microscope Analysis

Background and Objectives: This study evaluated the hybrid layer (HL) morphology created by three adhesive systems (AS) on dentin surfaces treated with Er:YAG laser using two irradiation parameters. Study Design: Occlusal flat dentin surfaces of 36 human third molars were assigned into nine groups (n = 4) according to the following ASs: one bottle etch&rinse Single Bond Plus (3M ESPE), two-step Clearfil Protect Bond (Kuraray), and all-in-one S3 Bond (Kuraray) self-etching, which were labeled with rhodamine B or fluorescein isothiocyanate dextran and were applied to dentin surfaces that were irradiated with Er:YAG laser at either 120 (38.7 J/cm(2)) or 200 mJ/pulse (64.5 J/cm(2)), or were applied to untreated dentin surfaces (control group). The ASs were light-activated following MI and the bonded surfaces were restored with resin composite Z250 (3M ESPE). After 24 hours of storage in vegetable oil, the restored teeth were vertically, serially sectioned into 1-mm thick slabs, which had the adhesive interfaces analyzed with confocal laser microscope (CLSM-LSM 510 Meta). CLSM images were recorded in the fluorescent mode from three different regions along each bonded interface. Results: Non-uniform HL was created on laser-irradiated dentin surfaces regardless of laser irradiation protocol for all AS, while regular and uniform HL was observed in the control groups. ""Stretch mark""-like red lines were found within the HL as a result of resin infiltration into dentin microfissures, which were predominantly observed in 200 mJ/pulse groups regardless of AS. Poor resin infiltration into peritubular dentin was observed in most regions of adhesive interfaces created by all ASs on laser-irradiated dentin, resulting in thin resin tags with neither funnel-shaped morphology nor lateral resin projections. Conclusion: Laser irradiation of dentin surfaces at 120 or 200 mJ/pulse resulted in morphological changes in HL and resin tags for all ASs evaluated in the study. Lasers Surg. Med. 42:662-670, 2010. (C) 2010 Wiley-Liss, Inc.

Machine Learning Algorithms at Myocardial Perfusion Imaging - a Preliminary Study

Introduction: A major focus of data mining process - especially machine learning researches - is to automatically learn to recognize complex patterns and help to take the adequate decisions strictly based on the acquired data. Since imaging techniques like MPI – Myocardial Perfusion Imaging on Nuclear Cardiology, can implicate a huge part of the daily workflow and generate gigabytes of data, there could be advantages on Computerized Analysis of data over Human Analysis: shorter time, homogeneity and consistency, automatic recording of analysis results, relatively inexpensive, etc.Objectives: The aim of this study relates with the evaluation of the efficacy of this methodology on the evaluation of MPI Stress studies and the process of decision taking concerning the continuation – or not – of the evaluation of each patient. It has been pursued has an objective to automatically classify a patient test in one of three groups: “Positive”, “Negative” and “Indeterminate”. “Positive” would directly follow to the Rest test part of the exam, the “Negative” would be directly exempted from continuation and only the “Indeterminate” group would deserve the clinician analysis, so allowing economy of clinician’s effort, increasing workflow fluidity at the technologist’s level and probably sparing time to patients. Methods: WEKA v3.6.2 open source software was used to make a comparative analysis of three WEKA algorithms (“OneR”, “J48” and “Naïve Bayes”) - on a retrospective study using the comparison with correspondent clinical results as reference, signed by nuclear cardiologist experts - on “SPECT Heart Dataset”, available on University of California – Irvine, at the Machine Learning Repository. For evaluation purposes, criteria as “Precision”, “Incorrectly Classified Instances” and “Receiver Operating Characteristics (ROC) Areas” were considered. Results: The interpretation of the data suggests that the Naïve Bayes algorithm has the best performance among the three previously selected algorithms. Conclusions: It is believed - and apparently supported by the findings - that machine learning algorithms could significantly assist, at an intermediary level, on the analysis of scintigraphic data obtained on MPI, namely after Stress acquisition, so eventually increasing efficiency of the entire system and potentially easing both roles of Technologists and Nuclear Cardiologists. In the actual continuation of this study, it is planned to use more patient information and significantly increase the population under study, in order to allow improving system accuracy.

Supervisão, comando e controlo para sistemas robóticos

Mestrado em Engenharia Electrotécnica e de Computadores. Área de Especialização em Sistemas Autónomos

Modelos e interfaces gráficos para objectos de aprendizagem na área da saúde

A educação é uma área bastante importante no desenvolvimento humano e tem vindo a adaptar-se às novas tecnologias. Tentam-se encontrar novas maneiras de ensinar de modo a obter um rendimento cada vez maior na aprendizagem das pessoas. Com o aparecimento de novas tecnologias como os computadores e a Internet, a concepção de aplicações digitais educativas cresceu e a necessidade de instruir cada vez melhor os alunos leva a que estas aplicações precisem de um interface que consiga leccionar de uma maneira rápida e eficiente. A combinação entre o ensino com o auxílio dessas novas tecnologias e a educação à distância deu origem ao e-Learning (ensino à distância). Através do ensino à distância, as possibilidades de aumento de conhecimento dos alunos aumentaram e a informação necessária tornou-se disponível a qualquer hora em qualquer lugar com acesso à Internet. Mas os cursos criados online tinham custos altos e levavam muito tempo a preparar o que gerou um problema para quem os criava. Para recuperar o investimento realizado decidiu-se dividir os conteúdos em módulos capazes de serem reaproveitados em diferentes contextos e diferentes tipos de utilizadores. Estes conteúdos modulares foram denominados Objectos de Aprendizagem. Nesta tese, é abordado o estudo dos Objectos de Aprendizagem e a sua evolução ao longo dos tempos em termos de interface com o utilizador. A concepção de um interface que seja natural e simples de utilizar nem sempre é fácil e independentemente do contexto em que se insere, requer algum conhecimento de regras que façam com que o utilizador que use determinada aplicação consiga trabalhar com um mínimo de desempenho. Na concepção de Objectos de Aprendizagem, áreas de complexidade elevada como a Medicina levam a que professores ou doutores sintam alguma dificuldade em criar um interface com conteúdos educativos capaz de ensinar com eficiência os alunos, devido ao facto de grande parte deles desconhecerem as técnicas e regras que levam ao desenvolvimento de um interface de uma aplicação. Através do estudo dessas regras e estilos de interacção torna-se mais fácil a criação de um bom interface e ao longo desta tese será estudado e proposto uma ferramenta que ajude tanto na criação de Objectos de Aprendizagem como na concepção do respectivo interface.

Projecto de avaliação de interfaces – PAI

Para obtenção do grau de Doutor pela Universidade de Vigo com menção internacional Departamento de Informática

Learning with tangible interfaces

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

SketchyDynamics apoio à produção de sistemas baseados em interfaces caligráficas para a simulação da dinâmica de corpos rígidos

Mestrado em Engenharia Informática - Área de Especialização em Sistemas Gráficos e Multimédia