Loading...
11 results
Search Results
Now showing 1 - 10 of 11
- Aplicação de redes neuronais artificiais ao apoio no diagnóstico de AVCs isquémicos por tomografia computorizadaPublication . Ribeiro, Luís; Ruano, M. GracaActualmente com os avanços tecnológicos das ciências informáticas, novas oportunidades surgem para melhorar a qualidade de vida, e em particular, as condições de avaliação diagnóstica. A tomografia computorizada é um dos equipamentos de diagnóstico por imagem que mais actualizações têm vindo a sofrer com os avanços tecnológicos, e que, por esse motivo e pela qualidade do diagnóstico que proporciona, tem vindo a ser dos mais utilizados. Uma das patologias que confirma a frequência de utilização dos tomografos computacionais é o acidente vascular cerebral isquémico (AVCI). O interesse por esta patologia, e em geral pela análise imagiológica do encéfalo, como forma de rastreio prende-se com a ocorrência de AVCI nos países desenvolvidos e o impacto sócio-económico que o mesmo produz. Nesse sentido, este estudo pretende avaliar a capacidade das redes neuronais artificiais (RNA) na identificação automática de AVCI mediante recurso a imagens da densidade dos tecidos obtidas por tomografia computorizada. No desenvolvimento deste trabalho utilizaram-se exames de tomografia computorizada crânio-encefálicas e respectivos relatórios médicos, e, RNAs comprovadamente eficientes noutras áreas do saber mas com idêntica problemática de identificação, das imagens e dos relatórios foram extraídos parâmetros os quais constituíram objecto de treino das RNAs. Uma vez treinadas as redes os modelos neuronais foram testados com dados nunca submetidos à rede. Nesta fase de avaliação conclui-se que as RNAs podem vir a contribuir significativamente no apoio ao diagnóstico de AVCIs por tomografia computorizada, uma vez que nos casos testados se verifica a identificação automática de lesões isquémicas, sem falsos negativos e apresentando poucos falsos positivos.
- A new method for groundwater plume detection under uncertaintyPublication . Nunes, Luís; Cunha, Maria da Conceição; Ribeiro, Luís; Azevedo, JoãoGroundwater contamination plumes characterization is a very hard task to perform, requiring usually a large number of sampling sites. In this article a method to optimize a monitoring network for plume detection and delimitation is proposed. It is assumed that a prior extensive sampling campaign was made, and only a few sampling sites must be included in the optimal monitoring network. The objective function incorporates the prior knowledge about concentration variability, in the form of its density function, and also a measure of spatial coverage (space-filling method), in order to best distribute the stations over the field. The method was applied to a synthetic case-study with 160 sampling locations, and a final optimal monitoring network with 40 stations was obtained. Simulated annealing optimization algorithm was used to solve this very difficult combinatorial problem, which has more than 8,6x1037 possible solutions).
- Recursos hídricosPublication . Cunha, Luís V.; Ribeiro, Luís; Oliveira, Ricardo P.; Nascimento, João; Monteiro, José Paulo; Dill, Amélia Maria Mello de Carvalho; Nunes, L.O Projecto "Climate Change in Portugal. Scenarios, Impacts and Adaptation Measures" (SIAM) iniciou-se em meados de 1999, com o financiamento da Fundação Calouste Gulbenkian e da Fundação para a Ciência e a Tecnologia. O Projecto SIAM teve como objectivo a realização da primeira avaliação integrada dos impactos e medidas de adaptação às alterações climáticas em Portugal Continental no século XXI. Os estudos realizados basearam-se em cenários do clima futuro obtidos a partir de modelos de circulação geral da atmosfera e incidiram sobre um conjunto de sectores sócio-económicos e sistemas biofísicos designadamente: recursos hídricos, zonas costeiras, agricultura, saúde humana, energia, florestas e biodiversidade e pescas. Foi também realizada uma análise sociológica sobre a problemática das alterações climáticas em Portugal. As principais conclusões obtidas no Projecto SIAM foram publicadas num Sumário Executivo e Conclusões, lançado em Outubro de 2001, editado em português e em inglês.A segunda fase do Projecto SIAM (SIAM II) iniciou-se em Janeiro de 2002. Esta segunda fase focou-se no estudo de caso do Estuário do Sado, tendo os estudos sido alargados às Regiões Autónomas da Madeira e dos Açores. O SIAM II incluiu ainda uma componente de Outreach que teve como objectivo a divulgação dos resultados obtidos no SIAM I aos diversos agentes interessados, obtendo ainda inputs para o SIAM II, através da organização de reuniões nas quais participaram as equipas dos sectores considerados relevantes para a região escolhida e os respectivos agentes interessados. O SIAM II foi financiado pelo Instituto do Ambiente, do Ministério das Cidades, do Ordenamento do Território e Ambiente.
- Neural networks assisted diagnosis of ischemic CVA's through CT scanPublication . Ribeiro, Luís; Ruano, Antonio; Ruano, M. Graça; Ferreira, P. M.Technological and computing evolution promoted new opportunities to improve the quality of life through new medical achievements, in particular, the quality of diagnostic evaluations. Computerised tomography (CT) is one of the imaging equipments for diagnosis which has most benefited from technological improvements. Because of that, and due to the quality of the diagnosis produced, it is one of the most employed equipments in clinical applications. As an example, the ischaemic cerebral vascular accident (ICVA) is a pathology confirming the frequent use of CT. The interest in this pathology, and in general for the encephalon image analysis as a preventive diagnosis, is mainly due to its frequent occurrence in development countries and its social-economic impact. In this paper we propose to evaluate the ability of of artificial neural networks (ANNs) for automatic identification of ICVAs by means of tissue density images obtained by CT. Cranioencephalon CT exams and their respective medical reports were used to train ANN classifiers by means of features extracted from the images. Once the ANNs were trained, the classifiers were tested with data never seen by the network. At this stage we may conclude that the ANNs may significantly contribute as an ICVAs and CT diagnostic aid, since among the test cases the automatic identification of ischaemic lesions has been performed with no false negatives and very few false positives.
- The water crisis in southern Portugal: how did we get there and how should we solve itPublication . Nunes, Luís; Monteiro, José Paulo; Cunha, Maria da Conceição; Vieira, João; Lucas, Helena; Ribeiro, LuísUntil very recently, public water supply in the Algarve region was almost entirely supported by groundwater wells. However, in the last years of the XX Century, the Portuguese central administration defined a scheme for the public water supply sector entirely based in surface water from large dams, in order to guarantee the public water supply. The efforts to abandon groundwater as a source for public supply started in 1998, after a large investment in new infrastructures and rehabilitation of other ones. However, the practical implementation of this water supply scheme showed that an integrated resource management is needed in order to implement a more economical and reliable solution. The present paper describes the historical background and the evolution of water use in the last decades until the present time in the Algarve, and a proposal for restructuring the management of the water supplies based in the development of a decision support system in the scope of an integrated water resources management.
- Section 2: Monitoring programmes: the fundamental component of estuaries management. How to design one?Publication . Nunes, L.; Caeiro, S.; Ramos, Tomás Barros; Cunha, Maria da Conceição; Ribeiro, Luís; Costa, Maria H.This article focuses on the design of a conceptual framework to design and assess environmental estuarine monitoring programmes, including the networks, to detect quality status changes in coastal areas within environmental management programmes. Monitoring is a fundamental component in any management system, and in particular in sensitive areas under strong human pressures, like estuaries. These pressures will be reflected in impacts in the ecosystem and also in responses from it. A monitoring program including the network and the indicators measured, should be designed to be able to identify the i) pressures, ii) the state and effects, and iii) the responses of human action in the estuary according to casualty chains, also the monitoring performance should be measured to assess the effectiveness of the monitoring program itself. Answers to these needs are studied in this article, namely in what concerns the selection and location of the monitoring stations. To evaluate the “best” monitoring design one should first clearly identify the objectives of the network and which indicators (in the sense of important variables that reflect environmental attributes) are most appropriate for the particular situation. In this work two methods for monitoring network design will be evaluated, namely i) variance-reduction based, and ii) space-filling. These two are examples of a statistically-based method, and of a random-allocation-based method. The most appropriate objective functions are used to reflect the objectives of the monitoring. In all cases the objective function models are solved with the simulated annealing meta-heuristic algorithm, implemented by the team to solve monitoring optimisation problems. Due to the amount and quality of the information available, the Sado estuary is used as a case-study to demonstrate the results of the methods and helping in the comparative analysis.
- Optimization of an estuarine monitoring program: selecting the best spatial distributionPublication . Caeiro, S.; Nunes, L.; Goovaerts, Pierre; Ribeiro, Luís; Painho, M.; Costa, Maria H.Monitoring estuarine programs are fundamental to evaluate the status and trends of pollution abatement actions, fulfillment of environmental quality standards and compliance with permit conditions. Their sampling designs should provide statistically unbiased estimates of the status and trends with quantitative confidence limits on both spatial and temporal scales. Variance reduction techniques have proved to be good methodologies for choosing better spatial and temporal designs. The aim of this work is to select a subset of monitoring sampling stations based on locations from an extensive estuarine sediment campaign. In this campaign 153 sites were sampled in the Sado estuary (southern Portugal). In each location three sediment parameters were determined with the objective of defining spatially homogenous environmental areas. The new monitoring program is based on fewer and on the most representative monitoring stations inside each homogeneous environmental area for their future contaminant assessment. Simulated annealing was used to iteratively improve on the mean square error of estimation, by removing one station at a time and estimating it by indicator kriging using the remaining stations in the sub-set, within a controlled non-exhaustive looping scheme. Different sub-set cardinalities were tested in order to determine the optimal cost-benefit relationship between the number of stations and monitoring costs. The model results indicate 60 station design to be optimal, but 17 additional stations with expertise criteria of proximity to point sources and characterization of all homogenous areas were added.
- Mixed analytical and numerical modelling of an oceanic peninsulaPublication . Nunes, Luís; Dill, Amélia Maria Mello de Carvalho; Ribeiro, Luís; Vieira, JoãoAnalytical and numerical models were applied to an oceanic peninsula to estimate the volume of freshwater available, and the amount of water that could be pumped without depleting the resource. The analytical models were used at regional scale, whereas the numerical models were applied in a small domain to obtain the hydrogeologic parameters of the aquifer. The results showed that even small pumping rates of 10% of the annual net recharge would have important impacts in the thickness of the water lens, which can be even higher during dry years, when the annual recharge may be half of the multiple-year long-term average value.
- Screening of sustainable groundwater sources for integration into a regional drought-prone water supply systemPublication . Stigter, T. Y.; Monteiro, José Paulo; Nunes, L.; Vieira, João; Cunha, Maria da Conceição; Ribeiro, Luís; Nascimento, João; Lucas, HelenaThis paper reports on the qualitative and quantitative screening of groundwater sources for integration into the public water supply system of the Algarve, Portugal. The results are employed in a decision support system currently under development for an integrated water resources management scheme in the region. Such a scheme is crucial for several reasons, including the extreme seasonal and annual variations in rainfall, the effect of climate change on more frequent and long-lasting droughts, the continuously increasing water demand and the high risk of a single-source water supply policy. The latter was revealed during the severe drought of 2004 and 2005, when surface reservoirs were depleted and the regional water demand could not be met, despite the drilling of emergency wells. For screening and selection, quantitative criteria are based on aquifer properties and well yields, whereas qualitative criteria are defined by water quality indices. These reflect the well’s degree of violation of drinking water standards for different sets of variables, including toxicity parameters, nitrate and chloride, iron and manganese and microbiological parameters. Results indicate the current availability of at least 1100 l s−1 of high quality groundwater (55% of the regional demand), requiring only disinfection (900 l s−1) or basic treatment, prior to human consumption. These groundwater withdrawals are sustainable when compared to mean annual recharge, considering that at least 40% is preserved for ecological demands. A more accurate and comprehensive analysis of sustainability is performed with the help of steady-state and transient groundwater flow simulations, which account for aquifer geometry, boundary conditions, recharge and discharge rates, pumping activity and season. (tibor.stigter@ist.utl.pt) ality. They permit an advanced analysis of present and future scenarios and show that increasing water demands and decreasing rainfall will make the water supply system extremely vulnerable, with a high risk of groundwater salinization and ecosystem degradation.
- Diagnóstico de CVA isquémicos asistido por redes neuronales mediante la exploración por CTPublication . Ribeiro, Luís; Ruano, Antonio; Ruano, M. Graça; Ferreira, P. M.La evolución tecnologica y computacional ha generado más oportunidades de mejorar la calidad de vida mediante nuevos logos médicos; en particular, con la calidad de las evaluaciones de diagnóstico. La tomografía computarizada (CT) es uno de los equipos de proyección de imagen para diagnóstico que más se han beneficiado de las mejoras tecnológicas.