Browsing by Author "Teixeira, Ana"
Now showing 1 - 10 of 39
Results Per Page
Sort Options
- Age and gender effects in european portuguese spontaneous speechPublication . Albuquerque, Luciana; Valente, Ana Rita; Teixeira, Ana; Oliveira, Catarina; Figueiredo, DanielaAging is part of the normal evolution of human beings. However, the knowledge about speech in the older ages is still dispersed and incomplete. Considering conflicting findings reported in prior research, this study aims to contribute to increase our knowledge about age effects on the spontaneous speech of Portuguese adults. In order to analyze the effects of age on rhythmic, intonation and voice quality domains, several parameters were extracted from spontaneous speech produced by 112 adults, aged between 35 and 97. Data were obtained through a picture description task. The results showed that the most consistent age-related effects are an increase in speech pauses, mainly in men, and a Harmonics-to-Noise Ratio (HNR) decrease in women. Speaking fundamental fre-quency (f0) tends to decrease in women and to slightly increase in men with age. These findings for Portuguese are in line with previous research suggesting that suprasegmental characteristics of speech change with age, with some gender differences.
- An exploratory study of brain computer interfacesin computer science educationPublication . Gomes, Anabela; Teixeira, Ana; Eloy, Joana; Mendes, Antonio JoseThis work offers an outline of how brain computer interactions can interconnect with education, specifically with regard to the cognitive and emotional processes occurring during difficult learning. We believe that understanding how to optimize the learner’s attention and workload in learning tasks can improve the efficacy of educational processes, especially in tasks involving highly cognitive activities, such as programming problem solving. The main objective of this study was to examine several brain parameters (attention, concentration and the energy of several brain waves) in a programming orientated task, as well as their variability during tasks of varying complexity. We consider that this work presents very promising future developments, including the possibility of incorporating this technology into a customised automatic system adapted to the student’s cognitive and emotional state.
- Atelier : assistive thechnologies for learning, integration and reabilitationPublication . Gomes, Anabela; Páris, César; Barbosa, Jorge; Santos, Álvaro; Martins, Nuno; Teixeira, AnaA special needs individual is a broad term used to describe a person with a behavioural or emotional disorder, physical disability or learning disability. Many individuals with special needs are limited in verbal communication, or in many cases non-verbal, making communication and learning a challenging task. Additionally, new forms of communication based on technology aren´t designed for them, making them increasingly isolated in social and educational terms. In spite of this, and fortunately, new forms of interaction do exist and they enable these particular users to access knowledge and provide them with the ability to interact with others, undertaking otherwise impossible. In this project the technology used will not be an end in itself but only a way to “drop” the mouse/keyboard paradigm making use of affordable devices available in the market that could be adopted by people with special needs that are unable to apply the traditional forms of interaction, thus assisting people in their education, integration and rehabilitation activities.
- Attention and concentration in normal and deaf gamersPublication . Teixeira, Ana; Tomé, Ana; Roseiro, Luís; Gomes, AnabelaIn this research the performance of individuals with normal hearing and impaired hearing while playing a computer game was evaluated. The aim was to study and understand if impaired hearing gamers are at disadvantage when playing games without being able to hear the music. Three levels (attention, concentration and blinking) were measured to compare and understand how sound can influence players’ attention and concentration performance. The data was recorded using Mindwave equipment during the game Outlast considering two scenarios: game with sound and game without sound. The results show that hearing impaired individuals have the same standard of attention and level of concentration as individuals with normal hearing when there is sound in the game. In the case of the blinking level, this is quite different between the scenarios and the analyzed groups. For this particular study the results suggest that sound is not an important level in the attention and concentration performance of impaired hearing players. Although much work still needs to be done, there is evidence of a relation between the attention and the concentration levels between normal hearing and impaired hearing individuals in the presence and absence of sound.
- Blind source separation using time-delayed signalsPublication . Tomé, A.M.; Teixeira, Ana; Lang, E.W.; Stadlthanner, K.; Rocha, A.P.; Almeida, R.In this work a modified version of AMUSE, called MMUSE, is proposed. The main modification consists in increasing the dimension of the data vectors by joining delayed versions of the observed mixed signals. With the new data a matrix pencil is computed and its generalized eigendecomposition is performed as in AMUSE. We will show that in this case the output (or independent) signals are filtered versions of the source signals. Some numerical simulations using artificially mixed signals as well as biological data (RR and QT intervals of Electrocardiogram) are presented.
- Blueeyes : easing the navigation and orientation of blind peoplePublication . Silva, Marta; Gomes, Anabela; Teixeira, Ana; Orvalho, JoaoAs reported by the World Health Organization (WHO), of the 7 billion people alive today, an estimated 253 million live with visual impairment that cannot be corrected with glasses or contact lenses. From these, 30 million blind or partially sighted persons live in Europe. Over the past years, blindness that is caused by diseases has decreased due to the success of public health actions. However, the number of blind people that are over 60 years old is increasing by 2 million per decade. Unfortunately, all these numbers are estimated to be doubled by 2020. With these facts, is necessary to bring awareness and understanding of the challenges blind people face and help to motivate research into new technology to answer those questions. This document starts to identify the challenges people with visual disabilities face in their life. The problem of navigation and orientation as well the different possibilities to deal with the locomotion situation is also addressed in this paper. It describes the traditional navigational solutions as well other which involves more sophisticated technological devices and their multimodal interfaces. The paper ends with the description of the BlueEyes project (Orvalho, 2016), consisting in a solution to help blind people moving in a city. The first phases of the project are described, and the actual research situations is also slightly explained.
- Caracterização do público num evento de moda, tendo em consideração a definição de personas e as suas motivaçõesPublication . Teixeira, Ana; Borges, AnaNo âmbito do mestrado de Direção Comercial e Marketing, do Instituto Superior de Administração e Gestão (ISAG- European Business School), a presente dissertação aborda sobre as estratégias de comunicação presentes em eventos de moda como o Portugal Fashion, tendo em consideração a construção dos perfis dos seus visitantes (personas) e a sua experiência e motivações com o evento. Após uma abordagem teórica do enquadramento de eventos de moda, estratégias de marketing como a comunicação, experiência do consumidor e o seu público-alvo, recorreu-se à metodologia quantitativa, através da implementação de um inquérito por questionário, com o principal objetivo de estudar as suas personas e a sua experiência com o evento. Após a implementação das técnicas de recolha de dados, os resultados obtidos são analisados e discutidos, concluindo que é possível identificar quatro tipos de personas, entre os quais, Enthusiastic, Fashion Observer, Fashion Outsider, Disconnected, na qual, destacadamente o perfil Enthusiastic revelou maior envolvência, significância e impacto. Conclui-se com estratégias de comunicação assertivas e orientadas confome as caracterÍsticas das personas. É importante destacar que atualmente, encontramo-nos num país mais desenvolvido, onde o contexto cultural tem vindo a ser valorizado e com mercados altamente competitivos. Nesse sentido é muito importante às organizações se adaptarem constantemente às mudanças do mercado tendo sempre por base aquilo que são as necessidades/expectativas dos seus consumidores através de uma comunicação assertiva e orientada.
- Clustering evoked potential signals using subspace methodsPublication . Tomé, A. M.; Teixeira, Ana; Figueiredo, N.; Georgieva, P.; Santos, I.M.; Lang, E.This work proposes a clustering technique to analyze evoked potential signals. The proposed method uses an orthogonal subspace model to enhance the single-trial signals of a session and simultaneously a subspace measure to group the trials into clusters. The ensemble averages of the signals of the different clusters are compared with ensemble averages of visually selected trials which are free of any artifact. Preliminary results consider recordings from an occipital channel where evoked response P100 wave is most pronounced.
- dAMUSE : a new tool for denoising and blind source separationPublication . Tomé, A.M.; Teixeira, Ana; Lang, E.W.; Stadlthanner, K.; Rocha, A.P.; Almeida, R.In this work a generalized version of AMUSE, called dAMUSE is proposed. The main modification consists in embedding the observed mixed signals in a high-dimensional feature space of delayed coordinates. With the embedded signals a matrix pencil is formed and its generalized eigendecomposition is computed similar to the algorithm AMUSE. We show that in this case the uncorrelated output signals are filtered versions of the unknown source signals. Further, denoising the data can be achieved conveniently in parallel with the signal separation. Numerical simulations using artificially mixed signals are presented to show the performance of the method. Further results of a heart rate variability (HRV) study are discussed showing that the output signals are related with LF (low frequency) and HF (high frequency) fluctuations. Finally, an application to separate artifacts from 2D NOESY NMR spectra and to denoise the reconstructed artefact-free spectra is presented also.
- Denoising using local projective subspace methodsPublication . Gruber, P.; Stadlthanner, K.; Böhm, M.; Theis, F.J.; Lang, E.W.; Tomé, A.M.; Teixeira, Ana; Puntonet, C.G.; Gorriz Saéz, J.M.In this paper we present denoising algorithms for enhancing noisy signals based on Local ICA (LICA), Delayed AMUSE (dAMUSE) and Kernel PCA (KPCA). The algorithm LICA relies on applying ICA locally to clusters of signals embedded in a high-dimensional feature space of delayed coordinates. The components resembling the signals can be detected by various criteria like estimators of kurtosis or the variance of autocorrelations depending on the statistical nature of the signal. The algorithm proposed can be applied favorably to the problem of denoising multi-dimensional data. Another projective subspace denoising method using delayed coordinates has been proposed recently with the algorithm dAMUSE. It combines the solution of blind source separation problems with denoising efforts in an elegant way and proofs to be very efficient and fast. Finally, KPCA represents a non-linear projective subspace method that is well suited for denoising also. Besides illustrative applications to toy examples and images, we provide an application of all algorithms considered to the analysis of protein NMR spectra.