Analysis and recognition of similar environmental sounds

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Informática

Automated image tagging through tag propagation

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

Human activity recognition with accelerometry: novel time and frequency features

Human Activity Recognition systems require objective and reliable methods that can be used in the daily routine and must offer consistent results according with the performed activities. These systems are under development and offer objective and personalized support for several applications such as the healthcare area. This thesis aims to create a framework for human activities recognition based on accelerometry signals. Some new features and techniques inspired in the audio recognition methodology are introduced in this work, namely Log Scale Power Bandwidth and the Markov Models application. The Forward Feature Selection was adopted as the feature selection algorithm in order to improve the clustering performances and limit the computational demands. This method selects the most suitable set of features for activities recognition in accelerometry from a 423th dimensional feature vector. Several Machine Learning algorithms were applied to the used accelerometry databases – FCHA and PAMAP databases - and these showed promising results in activities recognition. The developed algorithm set constitutes a mighty contribution for the development of reliable evaluation methods of movement disorders for diagnosis and treatment applications.

Human activity data discovery based on accelerometry

Dissertation to Obtain Master Degree in Biomedical Engineering

O Figural no Cinema Contemporâneo: Articulações e Disjunções do Visível e do Dizível

O que significa hoje um pensamento do figural? Qual a sua importância no quadro hegemónico do Arquivo Audiovisual e Multimédia Contemporâneo? Qual a relação que o cinema, enquanto assimilável ao pensamento do figural, tem com o Arquivo, tendo em conta a recente apropriação, interpretação, reconfiguração e interrogação das estruturas arquivísticas e materiais de arquivo, por parte de cineastas que usam o cinema, ele próprio, uma forma de arquivagem e material de arquivo, como ferramenta privilegiada de interpelação do Arquivo? Qual a potencial relevância do cinema, encarado nesta perspectiva, face à necessidade política de conceber um exterior do Arquivo? Estas são algumas das perguntas que estão na origem desta tese e a que ela procura responder, através da proposta de (re)corte de um arquivo de filmes e enunciados teóricos e da sua interpelação mútua. Com efeito, a imagem ou ideia de figural supõe uma reconfiguração das relações entre visível e dizível que não só nos serve de topos inspirador da metodologia da tese, num esforço de procurar inscrever a espacialização exigida pelo pensamento do figural na sua própria estrutura, como, sobretudo, nos fornece o quadro teórico de partida para pensar hoje, na senda de autores como Jean- François Lyotard, Michel Foucault e Gilles Deleuze, a relevância simultaneamente epistemológica e política da assimilação de certos gestos cinematográficos contemporâneos a uma imagem do pensamento com estes contornos. Assim, o cinema, sobretudo na sua forma ensaística, é identificado com a possibilidade de pôr em prática, um pensamento do interstício figural, que contraria a identidade dominante do ver e do falar, que rege o paradigma contemporâneo da comunicação, assente na respectiva conversão mútua - as imagens reduzem-se à sua significação ou conteúdo e as palavras convertem-se em imagens legíveis. Através das possibilidades oferecidas pela montagem cinematográfica, trata-se, então, de reenviar as imagens a uma leitura que só elas podem dar, e as palavras a um novo tipo de escuta e entendimento, o que se traduz, em termos da relação do cinema ao Arquivo contemporâneo, na sugestão de que o cinema é uma ferramenta de requalificação do saber que aquele supõe. A nossa hipótese é, pois, a de que o cinema em geral, e certos filmes em particular, ao permitirem a perscrutação arqueológica do Arquivo, introduzem delay na nossa relação aos “documentos”, sendo que é aí, nesse intervalo entre o registo e a sua retoma, que se joga a possibilidade de resistência face ao poder difuso do Arquivo, tal como se manifesta na internet, na televisão, nas redes que hoje geram a regulação, tratamento e transmissão da informação; porque possui uma dimensão audiovisual que lhe permite articular e desarticular arquivos e corpos, e dado que as relações entre dizível e visível não estão estabilizadas, o cinema torna possível a reescrita das figuras, ou seja, um pensamento que não dispõe de uma forma já feita de verdade para o encontro das frases e das experiências, mas que extrai relações essenciais e verdadeiras dos acontecimentos do nosso presente e da nossa história, precisamente a partir da exploração do intervalo instável entre discurso e figura, e da experimentação ao nível da recolagem entre enunciados e visibilidades.

Predicting market direction with hidden Markov models

This paper develops the model of Bicego, Grosso, and Otranto (2008) and applies Hidden Markov Models to predict market direction. The paper draws an analogy between financial markets and speech recognition, seeking inspiration from the latter to solve common issues in quantitative investing. Whereas previous works focus mostly on very complex modifications of the original hidden markov model algorithm, the current paper provides an innovative methodology by drawing inspiration from thoroughly tested, yet simple, speech recognition methodologies. By grouping returns into sequences, Hidden Markov Models can then predict market direction the same way they are used to identify phonemes in speech recognition. The model proves highly successful in identifying market direction but fails to consistently identify whether a trend is in place. All in all, the current paper seeks to bridge the gap between speech recognition and quantitative finance and, even though the model is not fully successful, several refinements are suggested and the room for improvement is significant.

Introducing mapping standards in the quality assessment of buildings extracted from very high resolution satellite imagery

Many municipal activities require updated large-scale maps that include both topographic and thematic information. For this purpose, the efficient use of very high spatial resolution (VHR) satellite imagery suggests the development of approaches that enable a timely discrimination, counting and delineation of urban elements according to legal technical specifications and quality standards. Therefore, the nature of this data source and expanding range of applications calls for objective methods and quantitative metrics to assess the quality of the extracted information which go beyond traditional thematic accuracy alone. The present work concerns the development and testing of a new approach for using technical mapping standards in the quality assessment of buildings automatically extracted from VHR satellite imagery. Feature extraction software was employed to map buildings present in a pansharpened QuickBird image of Lisbon. Quality assessment was exhaustive and involved comparisons of extracted features against a reference data set, introducing cartographic constraints from scales 1:1000, 1:5000, and 1:10,000. The spatial data quality elements subject to evaluation were: thematic (attribute) accuracy, completeness, and geometric quality assessed based on planimetric deviation from the reference map. Tests were developed and metrics analyzed considering thresholds and standards for the large mapping scales most frequently used by municipalities. Results show that values for completeness varied with mapping scales and were only slightly superior for scale 1:10,000. Concerning the geometric quality, a large percentage of extracted features met the strict topographic standards of planimetric deviation for scale 1:10,000, while no buildings were compliant with the specification for scale 1:1000.

Perylene Diimide acceptors: Fabrication and characterization of electron-only, hole-only devices and solar cells

The thrust towards energy conservation and reduced environmental footprint has fueled intensive research for alternative low cost sources of renewable energy. Organic photovoltaic cells (OPVs), with their low fabrication costs, easy processing and flexibility, represent a possible viable alternative. Perylene diimides (PDIs) are promising electron-acceptor candidates for bulk heterojunction (BHJ) OPVs, as they combine higher absorption and stability with tunable material properties, such as solubility and position of the lowest unoccupied molecular orbital (LUMO) level. A prerequisite for trap free electron transport is for the LUMO to be located at a level deeper than 3.7 eV since electron trapping in organic semiconductors is universal and dominated by a trap level located at 3.6 eV. Although the mostly used fullerene acceptors in polymer:fullerene solar cells feature trap-free electron transport, low optical absorption of fullerene derivatives limits maximum attainable efficiency. In this thesis, we try to get a better understanding of the electronic properties of PDIs, with a focus on charge carrier transport characteristics and the effect of different processing conditions such as annealing temperature and top contact (cathode) material. We report on a commercially available PDI and three PDI derivatives as acceptor materials, and its blends with MEH-PPV (Poly[2-methoxy 5-(2-ethylhexyloxy)-1,4-phenylenevinylene]) and P3HT (Poly(3-hexylthiophene-2,5-diyl)) donor materials in single carrier devices (electron-only and hole-only) and in solar cells. Space-charge limited current measurements and modelling of temperature dependent J-V characteristics confirmed that the electron transport is essentially trap-free in such materials. Different blend ratios of P3HT:PDI-1 (1:1) and (1:3) show increase in the device performance with increasing PDI-1 ratio. Furthermore, thermal annealing of the devices have a significant effect in the solar cells that decreases open-circuit voltage (Voc) and fill factor FF, but increases short-circuit current (Jsc) and overall device performance. Morphological studies show that over-aggregation in traditional donor:PDI blend systems is still a big problem, which hinders charge carrier transport and performance in solar cells.

Algorithms for information extraction and signal annotation on long-term biosignals using clustering techniques

Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica

Minimal computation structures for visual information applications based on printed electronics

In the early nineties, Mark Weiser wrote a series of seminal papers that introduced the concept of Ubiquitous Computing. According to Weiser, computers require too much attention from the user, drawing his focus from the tasks at hand. Instead of being the centre of attention, computers should be so natural that they would vanish into the human environment. Computers become not only truly pervasive but also effectively invisible and unobtrusive to the user. This requires not only for smaller, cheaper and low power consumption computers, but also for equally convenient display solutions that can be harmoniously integrated into our surroundings. With the advent of Printed Electronics, new ways to link the physical and the digital worlds became available. By combining common printing techniques such as inkjet printing with electro-optical functional inks, it is starting to be possible not only to mass-produce extremely thin, flexible and cost effective electronic circuits but also to introduce electronic functionalities into products where it was previously unavailable. Indeed, Printed Electronics is enabling the creation of novel sensing and display elements for interactive devices, free of form factor. At the same time, the rise in the availability and affordability of digital fabrication technologies, namely of 3D printers, to the average consumer is fostering a new industrial (digital) revolution and the democratisation of innovation. Nowadays, end-users are already able to custom design and manufacture on demand their own physical products, according to their own needs. In the future, they will be able to fabricate interactive digital devices with user-specific form and functionality from the comfort of their homes. This thesis explores how task-specific, low computation, interactive devices capable of presenting dynamic visual information can be created using Printed Electronics technologies, whilst following an approach based on the ideals behind Personal Fabrication. Focus is given on the use of printed electrochromic displays as a medium for delivering dynamic digital information. According to the architecture of the displays, several approaches are highlighted and categorised. Furthermore, a pictorial computation model based on extended cellular automata principles is used to programme dynamic simulation models into matrix-based electrochromic displays. Envisaged applications include the modelling of physical, chemical, biological, and environmental phenomena.