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.

A proactive intelligent decision support system for predicting the popularity of online news

"Lecture notes in computer science series, ISSN 0302-9743, vol. 9273"

Detection of dangerous situations using a smart internet of things system

The Internet of Things (IoT) is a concept that can foster the emergence of innovative applications. In order to minimize parents’s concerns about their children’s safety, this paper presents the design of a smart Internet of Things system for identifying dangerous situations. The system will be based on real time collection and analysis of physiological signals monitored by non-invasive and non-intrusive sensors, Frequency IDentification (RFID) tags and a Global Positioning System (GPS) to determine when a child is in danger. The assumption of a state of danger is made taking into account the validation of a certain number of biometric reactions to some specific situations and according to a self-learning algorithm developed for this architecture. The results of the analysis of data collected and the location of the child will be able in real time to child’s care holders in a web application.

Interaction paradigms versus age-related user profiles: an evaluation on content selection

Novel input modalities such as touch, tangibles or gestures try to exploit human's innate skills rather than imposing new learning processes. However, despite the recent boom of different natural interaction paradigms, it hasn't been systematically evaluated how these interfaces influence a user's performance or whether each interface could be more or less appropriate when it comes to: 1) different age groups; and 2) different basic operations, as data selection, insertion or manipulation. This work presents the first step of an exploratory evaluation about whether or not the users' performance is indeed influenced by the different interfaces. The key point is to understand how different interaction paradigms affect specific target-audiences (children, adults and older adults) when dealing with a selection task. 60 participants took part in this study to assess how different interfaces may influence the interaction of specific groups of users with regard to their age. Four input modalities were used to perform a selection task and the methodology was based on usability testing (speed, accuracy and user preference). The study suggests a statistically significant difference between mean selection times for each group of users, and also raises new issues regarding the “old” mouse input versus the “new” input modalities.

Methanogens, sulphate and heavy metals: a complex system

Anaerobic digestion (AD) is a well-established technology used for the treatment of wastes and wastewaters with high organic content. During AD organic matter is converted stepwise to methane-containing biogasa renewable energy carrier. Methane production occurs in the last AD step and relies on methanogens, which are rather sensitive to some contaminants commonly found in wastewaters (e.g. heavy metals), or easily outcompeted by other groups of microorganisms (e.g. sulphate reducing bacteria, SRB). This review gives an overview of previous research and pilot-scale studies that shed some light on the effects of sulphate and heavy metals on methanogenesis. Despite the numerous studies on this subject, comparison is not always possible due to differences in the experimental conditions used and parameters explained. An overview of the possible benefits of methanogens and SRB co-habitation is also covered. Small amounts of sulphide produced by SRB can precipitate with metals, neutralising the negative effects of sulphide accumulation and free heavy metals on methanogenesis. Knowledge on how to untangle and balance sulphate reduction and methanogenesis is crucial to take advantage of the potential for the utilisation of biogenic sulphide as a metal detoxification agent with minimal loss in methane production in anaerobic digesters.

Um modelo para a gestão do conhecimento organizacional no contexto dos serviços partilhados com recurso à utilização do e-Learning

Tese de Doutoramento em Tecnologias e Sistemas de Informação

Learning joint representations for order and timing of perceptual-motor sequences: a dynamic neural field approach

Many of our everyday tasks require the control of the serial order and the timing of component actions. Using the dynamic neural field (DNF) framework, we address the learning of representations that support the performance of precisely time action sequences. In continuation of previous modeling work and robotics implementations, we ask specifically the question how feedback about executed actions might be used by the learning system to fine tune a joint memory representation of the ordinal and the temporal structure which has been initially acquired by observation. The perceptual memory is represented by a self-stabilized, multi-bump activity pattern of neurons encoding instances of a sensory event (e.g., color, position or pitch) which guides sequence learning. The strength of the population representation of each event is a function of elapsed time since sequence onset. We propose and test in simulations a simple learning rule that detects a mismatch between the expected and realized timing of events and adapts the activation strengths in order to compensate for the movement time needed to achieve the desired effect. The simulation results show that the effector-specific memory representation can be robustly recalled. We discuss the impact of the fast, activation-based learning that the DNF framework provides for robotics applications.

Off-line simulation inspires insight: a neurodynamics approach to efficient robot task learning

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.

Using balanced scorecards to evaluate the data warehouse system utility

Dissertação de mestrado em Systems Engineering

A radiofrequency identification system for the 60 GHz ISM band

Dissertação de mestrado integrado em Engenharia Biomédica (área de especialização em Eletrónica Médica)

Grasses and legumes as cover crop in no-tillage system in northeastern Pará Brazil

Studies to select one or more species of coverage plants adapted to Amazonian soil and climate conditions of the Amazon are a promising strategy for the improvement of environmental quality, establishing no-till agricultural systems, and thereby reducing the impacts of monoculture farming. The aim of this study was to assess the persistence time, half-life time, macronutrient content and accumulation, and C:N ratio of straw coverage in a Ultisol in northeastern Pará. Experimental design was randomized blocks with five treatments and five replicates. Plants were harvested after 105 days, growth and biomass production was quantified. After 84 days, soil coverage was 97, 85, 52, 50, and 15% for signalgrass (Brachiaria brizantha) (syn. Urochloa), dense crowngrass (Panicum purpurascens), jack bean (Canavalia ensiformes), pearl millet (Pennisetum americanum) and sunn hemp (Crotalaria juncea,), respectively. Signalgrass yielded the greatest dry matter production (9,696 kg ha-1). It also had high C:N ratio (38.4), long half-life (86.5 days) and a high persistence in the field. Jack bean also showed high dry matter production (8,950 kg ha-1), but it had low C:N ratio (17.4) and lower half-life time (39 days) than the grasses. These attributes indicate that signalgrass and jack bean have a high potential for use as cover plants in no-till agricultural systems in the State of Pará.

Sistema de apoio à decisão clínica: quality of life system

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Avaliação de desempenho docente: Contributos para as práticas de avaliação na escola

Tese de Doutoramento em Ciências da Educação (Especialidade em Desenvolvimento Curricular)

All over the place localization system

The MAP-i Doctoral Programme in Informatics, of the Universities of Minho, Aveiro and Porto

Development of an intelligent earthwork optimization system

Tese de Doutoramento em Engenharia Civil.