User friendly knowledge acquisition system for medical devices actuation

Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica

A knowledge-based framework to facilitate E-training implementation

Dissertação para obtenção do Grau de Mestre em Engenharia Eletrotécnica e de Computadores

Enhancing information retrieval in folksonomies using ontology of place constructed from Gazetteer information

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies

Image processing for displacement measurements

Since the invention of photography humans have been using images to capture, store and analyse the act that they are interested in. With the developments in this field, assisted by better computers, it is possible to use image processing technology as an accurate method of analysis and measurement. Image processing's principal qualities are flexibility, adaptability and the ability to easily and quickly process a large amount of information. Successful examples of applications can be seen in several areas of human life, such as biomedical, industry, surveillance, military and mapping. This is so true that there are several Nobel prizes related to imaging. The accurate measurement of deformations, displacements, strain fields and surface defects are challenging in many material tests in Civil Engineering because traditionally these measurements require complex and expensive equipment, plus time consuming calibration. Image processing can be an inexpensive and effective tool for load displacement measurements. Using an adequate image acquisition system and taking advantage of the computation power of modern computers it is possible to accurately measure very small displacements with high precision. On the market there are already several commercial software packages. However they are commercialized at high cost. In this work block-matching algorithms will be used in order to compare the results from image processing with the data obtained with physical transducers during laboratory load tests. In order to test the proposed solutions several load tests were carried out in partnership with researchers from the Civil Engineering Department at Universidade Nova de Lisboa (UNL).

The implementation of an Enterprise Geographical Information System to support Cadastre and Expropriation activities.

The processes of mobilization of land for infrastructures of public and private domain are developed according to proper legal frameworks and systematically confronted with the impoverished national situation as regards the cadastral identification and regularization, which leads to big inefficiencies, sometimes with very negative impact to the overall effectiveness. This project report describes Ferbritas Cadastre Information System (FBSIC) project and tools, which in conjunction with other applications, allow managing the entire life-cycle of Land Acquisition and Cadastre, including support to field activities with the integration of information collected in the field, the development of multi-criteria analysis information, monitoring all information in the exploration stage, and the automated generation of outputs. The benefits are evident at the level of operational efficiency, including tools that enable process integration and standardization of procedures, facilitate analysis and quality control and maximize performance in the acquisition, maintenance and management of registration information and expropriation (expropriation projects). Therefore, the implemented system achieves levels of robustness, comprehensiveness, openness, scalability and reliability suitable for a structural platform. The resultant solution, FBSIC, is a fit-for-purpose cadastre information system rooted in the field of railway infrastructures. FBSIC integrating nature of allows: to accomplish present needs and scale to meet future services; to collect, maintain, manage and share all information in one common platform, and transform it into knowledge; to relate with other platforms; to increase accuracy and productivity of business processes related with land property management.

Creation of a web application for smart park system and parking prediction study for system integration

In the last few years, we have observed an exponential increasing of the information systems, and parking information is one more example of them. The needs of obtaining reliable and updated information of parking slots availability are very important in the goal of traffic reduction. Also parking slot prediction is a new topic that has already started to be applied. San Francisco in America and Santander in Spain are examples of such projects carried out to obtain this kind of information. The aim of this thesis is the study and evaluation of methodologies for parking slot prediction and the integration in a web application, where all kind of users will be able to know the current parking status and also future status according to parking model predictions. The source of the data is ancillary in this work but it needs to be understood anyway to understand the parking behaviour. Actually, there are many modelling techniques used for this purpose such as time series analysis, decision trees, neural networks and clustering. In this work, the author explains the best techniques at this work, analyzes the result and points out the advantages and disadvantages of each one. The model will learn the periodic and seasonal patterns of the parking status behaviour, and with this knowledge it can predict future status values given a date. The data used comes from the Smart Park Ontinyent and it is about parking occupancy status together with timestamps and it is stored in a database. After data acquisition, data analysis and pre-processing was needed for model implementations. The first test done was with the boosting ensemble classifier, employed over a set of decision trees, created with C5.0 algorithm from a set of training samples, to assign a prediction value to each object. In addition to the predictions, this work has got measurements error that indicates the reliability of the outcome predictions being correct. The second test was done using the function fitting seasonal exponential smoothing tbats model. Finally as the last test, it has been tried a model that is actually a combination of the previous two models, just to see the result of this combination. The results were quite good for all of them, having error averages of 6.2, 6.6 and 5.4 in vacancies predictions for the three models respectively. This means from a parking of 47 places a 10% average error in parking slot predictions. This result could be even better with longer data available. In order to make this kind of information visible and reachable from everyone having a device with internet connection, a web application was made for this purpose. Beside the data displaying, this application also offers different functions to improve the task of searching for parking. The new functions, apart from parking prediction, were: - Park distances from user location. It provides all the distances to user current location to the different parks in the city. - Geocoding. The service for matching a literal description or an address to a concrete location. - Geolocation. The service for positioning the user. - Parking list panel. This is not a service neither a function, is just a better visualization and better handling of the information.

Fouling of a drinking water system in relation to hydraulic circumstances and customer complaints

In a “perfect” drinking water system, the water quality for the consumers should be the same as the quality of the water leaving the treatment plant. However, some variability along the system can lead to a decrease in water quality (such as discolouration) which is usually reflected in the number of the customer complaints. This change may be related to the amount of sediment in the distribution network, leading to an increase in turbidity at the water supply. Since there is no such thing as a perfect drinking water system, the behaviour of particles in a drinking water network needs a suitable approach in order to understand how it works. Moreover, the combination of measurements, such as turbidity patterns and the Resuspension Potential Method (RPM) aid in the prevention of discoloured water complaints and intervention in the treatment upgrade or the network cleaning. Besides sediments there is also bacterial regrowth in the network, which is related to the water quality and distribution network characteristics. In a theoretical drinking water system higher velocities, temperature and shorter residences times lead to wider bacterial growth. In this study we observe velocity and residence steady-states and bacterial does not seem to be related to either. It can be concluded that adequate measurements of RPM, customer complaints and bacterial concentrations allow a wider knowledge on particle behaviour in drinking water systems.

Human-robot teamwork: a knowledge-based solution

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

Social network analysis applied to knowledge creation and transfer in the portuguese agricultural R&D field: an exploratory study

Paper presented at the 9th European Conference on Knowledge Management, Southampton Solent University, Southampton, UK, 4-5 Sep. 2008. URL: http://academic-conferences.org/eckm/eckm2008/eckm08-home.htm

Innovation through virtual communities of practice: motivations and constraints in the knowledge-creation process

This paper appears in International Journal of Projectics. Vol 4(1), pp. 39-49

LADAR based mapping and obstacle detection system for service robots

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

Adesão ao regime terapêutico na pessoa com enfarte agudo do miócardio: contributo dos enfermeiros no internamento hospita

RESUMO: O Enfarte Agudo do Miocárdio (EAM) representa um dos principais problemas de saúde pública em Portugal. A rápida intervenção nos factores de risco determinantes da saúde cardíaca pode ter um impacto positivo em vários indicadores de saúde. O objectivo final dessa intervenção passa por capacitar a pessoa, para que, autonomamente, adopte um conjunto de comportamentos de saúde, baseados em estilos de vida protectores da saúde cardíaca, que favorecem positivamente o processo de reabilitação. Esta procura e aquisição do comportamento de saúde, adesão ao regime terapêutico, deve ser desenvolvido em parceria com os profissionais de saúde. O hospital representa a porta de entrada da pessoa com EAM no sistema de saúde. É neste contacto que se inicia uma intervenção de sensibilização e promoção da adesão ao regime terapêutico. Sendo os enfermeiros um grupo profissional que estabelece uma relação continua com a pessoa, importa conhecer um conjunto de dimensões do desempenho dos enfermeiros na promoção da adesão ao regime terapêutico. Breve referência ao desenho de estudo. Foram incluídas no estudo 143 enfermeiros de 9 serviços hospitalares da Região de Saúde de Lisboa e Vale do Tejo. Os dados foram obtidos através de um questionário auto-preenchido. Os dados mostraram que a população de enfermeiros é jovem (M= 30,5: dp= 8,0), 49% têm uma idade £ 26 anos e apresenta pouca experiência profissional (M=7,7; dp= 7,6), 48,2% exerce a profissão há menos de 3 anos. A antiguidade no serviço actual é reduzida (M= 4,7; dp= 4,6), 48,9% estão no serviço há menos de 2 anos. Os enfermeiros acreditam que deviam intervir com mais frequência nos factores de risco fisiológicos e comportamentais que nos factores psicossociais e ambientais; a confiança que têm nas capacidades para intervir nos factores de risco fisiológicos e comportamentais é maior que nos factores psicossociais e ambientais e no último ano, intervieram mais frequentemente nos factores de risco fisiológicos e comportamentais que nos psicossociais e ambientais. O “ensaio” da validação da escala de Will scale de Anderson et al (2004), sobre a capacidade de intervenção na saúde cardíaca, mostrou que o teste de Esfericidade de Bartlett e Medida de adequação da amostragem de Kaiser-Meyer- Olkin (KMO) permitiram a realização da análise factorial em componentes principais (AFCP). Da AFCP emergiram 16 factores, os mesmos que no estudo original de Anderson et al (2004), que revelaram boa consistência interna, com valores de alpha de Cronbach que variaram entre 0,71 a 0,98. Os resultados revelam a necessidade de sensibilizar os enfermeiros para valorizar a intervenção no âmbito dos factores de risco psicossociais e ambientais para promover a adesão ao regime terapêutico. Sugerem ainda que a intervenção baseada na evidência pode ser potenciada de forma a melhorar as práticas de cuidados dos enfermeiros. ABSTRACT: Myocardial infarction (MI) is one of the most important problems in public health in Portugal. A prompt intervention in cardiac health determinants means a positive impact in health outcomes, individually and collectively. The main purpose of this intervention lays on patient’s empowerment so he or she becomes able to choose healthy behaviours, based on heart health protective life styles, and therefore to manage his/hers therapeutic regime. This search and acquisition of health behaviours leading to therapeutic regime adherence may positively have an influence on the whole rehabilitation process and it must be developed in partnership with health workers. MI patients’ first contact with the Health System usually happens at the Hospital. Here the first steps are taken to start an intervention in order to promote therapeutic regime adherence. Nurses are a group of health workers who establish a unique and continuous relation with patients, so it matters to have knowledge of their performance skills that can actually promote a healthy behaviours and increase therapeutic regime adherence. Short Study design The study sample includes 143 nurses working on 9 different hospital wards, belonging to the Lisboa and Tejo’s Valley Health Region, in the district of Lisbon. Data were collected trough a self-administered questionnaire. It revealed that the nurses sample is a young population (M=30,5; dp=8,0), 49% of whom are aged less than 26 years old and has little professional experience (M=7,7; dp= 7,6); 48,2% work has nurses for less than 3 years. There’s a low percentage of seniority (M=4,7; dp=4,6), 48,9% of nurses work in these wards for less than 2 years. Nurses believe they should have intervene more frequently in physiological and behaviour risk factors than in psychological, social and environmental factors; they have greater confidence in their ability to intervene in physiological and behaviour risk factors than to intervene in psychological, social and environmental factors. In last year they took interventions more frequently in physiological and behaviour risk factors than in the other health determinants. The Scale Validation “essay” on Will Scale (Anderson et al, 2004), about heart health intervention capacity, revealed that the Bartlett’s test sphericity and the Kaiser-Meyer- Olkin’s (KMO) appropriate sample measure allowed the factorial analysis on main components (FAMC). From FAMC emerged 16 factors, the same number found on Anderson’s et al (2004) study, revealing good internal consistence, with Cronbach’s alpha values that varied between 0,71 and 0,98. The results point a need for nurses to attribute bigger value to other health determinants intervention - such as psychological, social and environmental determinants - so they’ll take part in promoting therapeutic regime adherence. The results also suggest t

Georeferencing Road Accidents with Google Earth: Transforming Information into Knowledge for Decision Support

Over the last fifty years mobility practices have changed dramatically, improving the way travel takes place, the time it takes but also on matters like road safety and prevention. High mortality caused by high accident levels has reached untenable levels. But the research into road mortality stayed limited to comparative statistical exercises which go no further than defining accident types. In terms of sharing information and mapping accidents, little progress has been mad, aside from the normal publication of figures, either through simplistic tables or web pages. With considerable technological advances on geographical information technologies, research and development stayed rather static with only a few good examples on dynamic mapping. The use of Global Positioning System (GPS) devices as normal equipments on automobile industry resulted in a more dynamic mobility patterns but also with higher degrees of uncertainty on road traffic. This paper describes a road accident georeferencing project for the Lisbon District involving fatalities and serious injuries during 2007. In the initial phase, individual information summaries were compiled giving information on accidents and its majour characteristics, collected by the security forces: the Public Safety Police Force (Polícia de Segurança Pública - PSP) and the National Guard (Guarda Nacional Republicana - GNR). The Google Earth platform was used to georeference the information in order to inform the public and the authorities of the accident locations, the nature of the location, and the causes and consequences of the accidents. This paper also gives future insights about augmented reality technologies, considered crucial to advances to road safety and prevention studies. At the end, this exercise could be considered a success because of numerous consequences, as for stakeholders who decide what to do but also for the public awareness to the problem of road mortality.

Low cost inertial-based localization system for a service robot

Dissertation presented at Faculty of Sciences and Technology of the New University of Lisbon to attain the Master degree in Electrical and Computer Science Engineering

Declarative approach to data extraction of web pages

Thesis submitted to Faculdade de Ciências e Tecnologia of the Universidade Nova de Lisboa, in partial fulfilment of the requirements for the degree of Master in Computer Science