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.

Designing and implementing a performance measurement system in Auto Ribeiro, Lda.

In any business it is very important to measure the performance and it helps to select key information to make better decisions on time. This research focuses on the design and implementation of a performance measurement system in a Portuguese medium size firm operating in the specialized health care transformation vehicles industry. From the evidence that outputs from Auto Ribeiro’s current information system is misaligned with the company’s objectives and strategy, this research tries to solve this business problem through the development of a Balanced Scorecard analysis, although there are some issues, which deserve further development.

Control system for actuation and sensing in digital microfluidics devices

Digital Microfluidics (DMF) is a second generation technique, derived from the conventional microfluidics that instead of using continuous liquid fluxes, it uses only individual droplets driven by external electric signals. In this thesis a new DMF control/sensing system for visualization, droplet control (movement, dispensing, merging and splitting) and real time impedance measurement have been developed. The software for the proposed system was implemented in MATLAB with a graphical user interface. An Arduino was used as control board and dedicated circuits for voltage switching and contacts were designed and implemented in printed circuit boards. A high resolution camera was integrated for visualization. In our new approach, the DMF chips are driven by a dual-tone signal where the sum of two independent ac signals (one for droplet operations and the other for impedance sensing) is applied to the electrodes, and afterwards independently evaluated by a lock-in amplifier. With this new approach we were able to choose the appropriated amplitudes and frequencies for the different proposes (actuation and sensing). The measurements made were used to evaluate the real time droplet impedance enabling the knowledge of its position and velocity. This new approach opens new possibilities for impedance sensing and feedback control in DMF devices.

Avaliação da contaminação em metais pesados no pescado: análise da situação do pescado comercializado em Portugal e dos alertas emitidos pelo sistema RASFF (Rapid Alert System for Food and Feed)

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

Carbon prices. Dynamic analysis of European and Californian markets

Dissertação para obtenção do Grau de Doutor em Alterações Climáticas e Políticas de Desenvolvimento Sustentável