Ontology-based representation and generation of workflows for micro-task human-machine computation

Doctoral Program in Computer Science

FOSTER: facilitate open science training for european research

FOSTER aims to support different stakeholders, especially young researchers, in adopting open access in the context of the European Research Area (ERA) and in complying with the open access policies and rules of participation set out for Horizon 2020 (H2020). FOSTER establish a European-wide training programme on open access and open data, consolidating training activities at downstream level and reaching diverse disciplinary communities and countries in the ERA. The training programme includes different approaches and delivery options: elearning, blearning, self-learning, dissemination of training materials/contents, helpdesk, face-to-face training, especially training-the-trainers, summer schools, seminars, etc.

Using mouse dynamics to assess stress during online exams

"Lecture notes in computer science series", ISSN 0302-9743, vol. 9121

Vision-based portuguese sign language recognition system

Vision-based hand gesture recognition is an area of active current research in computer vision and machine learning. Being a natural way of human interaction, it is an area where many researchers are working on, with the goal of making human computer interaction (HCI) easier and natural, without the need for any extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them, for example, to convey information. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. Hand gestures are a powerful human communication modality with lots of potential applications and in this context we have sign language recognition, the communication method of deaf people. Sign lan- guages are not standard and universal and the grammars differ from country to coun- try. In this paper, a real-time system able to interpret the Portuguese Sign Language is presented and described. Experiments showed that the system was able to reliably recognize the vowels in real-time, with an accuracy of 99.4% with one dataset of fea- tures and an accuracy of 99.6% with a second dataset of features. Although the im- plemented solution was only trained to recognize the vowels, it is easily extended to recognize the rest of the alphabet, being a solid foundation for the development of any vision-based sign language recognition user interface system.

Cost-effective and lightweight mobile units for MixAR: A comparative trial among different setups

Cultural heritage has arousing the interest of the general public (e.g. tourists), resulting in the increasing number of visitations to archaeological sites. However, many buildings and monuments are severely damaged or completely destroyed, which doesn’t allow to get a full experience of “travelling in time”. Over the years, several Augmented Reality (AR) approaches were proposed to overcome these issues by providing three-dimensional visualization of reconstructed ancient structures in situ. However, most of these systems were made available through heavy and expensive technological bundles. Alternatively, MixAR intends to be a lightweight and cost-effective Mixed Reality system which aims to provide the visualization of virtual ancient buildings reconstructions in situ, properly superimposed and aligned with real-world ruins. This paper proposes and compares different AR mobile units setups to be used in the MixAR system, with low-cost and lightweight requirements in mind, providing different levels of immersion. It was propounded four different mobile units, based on: a laptop computer, a single-board computer (SBC), a tablet and a smartphone, which underwent a set of tests to evaluate their performances. The results show that mobile units based on laptop computer and SBC reached a good overall performance while mobile units based on tablet and smartphone did not meet such a satisfactory result even though they are acceptable for the intended use.

MixAR mobile prototype: visualizing virtually reconstructed ancient structures in situ

Archeology and related areas have a special interest on cultural heritage sites since they provide valuable information about past civilizations. However, the ancient buildings present in these sites are commonly found in an advanced state of degradation which difficult the professional/expert analysis. Virtual reconstructions of such buildings aim to provide a digital insight of how these historical places could have been in ancient times. Moreover, the visualization of such models has been explored by some Augmented Reality (AR) systems capable of providing support to experts. Their compelling and appealing environments have also been applied to promote the social and cultural participation of general public. The existing AR solutions regarding this thematic rarely explore the potential of realism, due to the following lacks: the exploration of mixed environments is usually only supported for indoors or outdoors, not both in the same system; the adaptation of the illumination conditions to the reconstructed structures is rarely addressed causing a decrease of credibility. MixAR [1] is a system concerned with those challenges, aiming to provide the visualization of virtual buildings augmented upon real ruins, allowing soft transitions among its interiors and exteriors and using relighting techniques for a faithful interior illumination, while the user freely moves in a given cultural heritage site, carrying a mobile unit. Regarding the focus of this paper, we intend to report the current state of MixAR mobile unit prototype, which allows visualizing virtual buildings – properly aligned with real-world structures – based on user's location, during outdoor navigation. In order to evaluate the prototype performance, a set of tests were made using virtual models with different complexities.

Gamification e game-based learning: uma abordagem lúdica à aprendizagem

Relatório de estágio de mestrado em Ensino de Informática

Honours students: good marks and what else?

Currently in Portugal academic excellence in higher education is given recognition through merit prizes. Because honours students can be seen as having the potential to achieve imporant levels of professional expertise, especially if they have some personal skills, it is important to know not only the marks of the students but also the personal characteristics that contribute to academic success and which may also be important for career success. Some theoretical models of giftedness and excellence agree with this idea and this work considers the latest contribution of Renzulli (2005) where it is pointed out that excellent achievements result from the combination of motivational, intellectual and creative factors as well as from co-cognitive factors which are most associated with personality functioning in a particular context. The main purpose of this paper is to analyze how honours students differ from their classmates in various psychological dimensions: Cognition-creativity, Motivation and Learning Strategies, Persistence, Social Interaction, Drive for Excellence and Cultural Interest. These dimensions were measured by the Inventory of Psychological Characteristics Associated with Academic Performance (ICPADA), which was constructed taking into consideration the previous study of Scaeger et al. (2012). The sample included 914 Portuguese higher educatoin students from a first cycle degree in the Bologna process. Participants were selected from three different fields of study: Social and Human Sciences; Science and Technology; Arts and Humanities. The data collected through the administration of the ICPADA was presented, and the results revealed a higher self-perception by honours students in all areas analyzed, with the exception of the dimension of social interaction. In addition an interaction effect was revealed for persistence, social interaction, and cultural interest. The field of study and whether the participants were honours students or not were also taken into account. Some implications for future studies are presented here along with possible interventions for honours students.

An interactive web-based tool for breast reduction surgery simulation

In this work, we present a 3D web-based interactive tool for numerical modeling and simulation approach to breast reduction surgery simulation, to assist surgeons in planning all aspects related to breast reduction surgery before the actual procedure takes place, thereby avoiding unnecessary risks. In particular, it allows the modeling of the initial breast geometry, the definition of all aspects related to the surgery and the visualization of the post-surgery breast shape in a realistic environment.

Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

A critical evaluation of methods for the reconstruction of tissue-specific models

Under the framework of constraint based modeling, genome-scale metabolic models (GSMMs) have been used for several tasks, such as metabolic engineering and phenotype prediction. More recently, their application in health related research has spanned drug discovery, biomarker identification and host-pathogen interactions, targeting diseases such as cancer, Alzheimer, obesity or diabetes. In the last years, the development of novel techniques for genome sequencing and other high-throughput methods, together with advances in Bioinformatics, allowed the reconstruction of GSMMs for human cells. Considering the diversity of cell types and tissues present in the human body, it is imperative to develop tissue-specific metabolic models. Methods to automatically generate these models, based on generic human metabolic models and a plethora of omics data, have been proposed. However, their results have not yet been adequately and critically evaluated and compared. This work presents a survey of the most important tissue or cell type specific metabolic model reconstruction methods, which use literature, transcriptomics, proteomics and metabolomics data, together with a global template model. As a case study, we analyzed the consistency between several omics data sources and reconstructed distinct metabolic models of hepatocytes using different methods and data sources as inputs. The results show that omics data sources have a poor overlapping and, in some cases, are even contradictory. Additionally, the hepatocyte metabolic models generated are in many cases not able to perform metabolic functions known to be present in the liver tissue. We conclude that reliable methods for a priori omics data integration are required to support the reconstruction of complex models of human cells.