18 results on '"Pires, João Moura"'
Search Results
2. Road Traffic Flow Prediction with Visual Analytics
- Author
-
Datia, Nuno, primary, Pato, Matilde P. M., additional, Vaz, João, additional, and Pires, João Moura, additional
- Published
- 2024
- Full Text
- View/download PDF
3. ML Approach to Predict Air Quality Using Sensor and Road Traffic Data
- Author
-
Datia, Nuno, Pato, M. P. M., Taborda, Ruben, Pires, João Moura, Kacprzyk, Janusz, Series Editor, Kovalerchuk, Boris, editor, Nazemi, Kawa, editor, Andonie, Răzvan, editor, Datia, Nuno, editor, and Banissi, Ebad, editor
- Published
- 2022
- Full Text
- View/download PDF
4. Creating a forest disturbance dataset for continental Portugal
- Author
-
Fernandes, Eduardo, primary, Damásio, Carlos Viegas, additional, and Pires, João Moura, additional
- Published
- 2022
- Full Text
- View/download PDF
5. Visual analytics for spatiotemporal events
- Author
-
Silva, Ricardo Almeida, Pires, João Moura, Datia, Nuno, Santos, Maribel Yasmina, Martins, Bruno, and Birra, Fernando
- Published
- 2019
- Full Text
- View/download PDF
6. When Granules Are not Enough in a Theory of Granularities
- Author
-
Silva, Ricardo Almeida, Pires, João Moura, Santos, Maribel Yasmina, Cartwright, William, Series editor, Gartner, Georg, Series editor, Meng, Liqiu, Series editor, Peterson, Michael P., Series editor, Bregt, Arnold, editor, Sarjakoski, Tapani, editor, van Lammeren, Ron, editor, and Rip, Frans, editor
- Published
- 2017
- Full Text
- View/download PDF
7. Severity Estimation of Stator Winding Short-Circuit Faults Using Cubist
- Author
-
dos Santos, Tiago, Ferreira, Fernando J. T. E., Pires, João Moura, Damásio, Carlos Viegas, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Oliveira, Eugénio, editor, Gama, João, editor, Vale, Zita, editor, and Lopes Cardoso, Henrique, editor
- Published
- 2017
- Full Text
- View/download PDF
8. Enhancing Exploratory Analysis by Summarizing Spatiotemporal Events Across Multiple Levels of Detail
- Author
-
Silva, Ricardo Almeida, Pires, João Moura, Santos, Maribel Yasmina, Datia, Nuno, Cartwright, William, Series editor, Gartner, Georg, Series editor, Meng, Liqiu, Series editor, Peterson, Michael P., Series editor, Sarjakoski, Tapani, editor, Santos, Maribel Yasmina, editor, and Sarjakoski, L. Tiina, editor
- Published
- 2016
- Full Text
- View/download PDF
9. Aggregating Spatio-temporal Phenomena at Multiple Levels of Detail
- Author
-
Silva, Ricardo Almeida, Pires, João Moura, Santos, Maribel Yasmina, Leal, Rui, Cartwright, William, Series editor, Gartner, Georg, Series editor, Meng, Liqiu, Series editor, Peterson, Michael P, Series editor, Bacao, Fernando, editor, Santos, Maribel Yasmina, editor, and Painho, Marco, editor
- Published
- 2015
- Full Text
- View/download PDF
10. Severity Estimation of Stator Winding Short-Circuit Faults Using Cubist
- Author
-
dos Santos, Tiago, primary, Ferreira, Fernando J. T. E., additional, Pires, João Moura, additional, and Damásio, Carlos Viegas, additional
- Published
- 2017
- Full Text
- View/download PDF
11. Enhancing Exploratory Analysis by Summarizing Spatiotemporal Events Across Multiple Levels of Detail
- Author
-
Silva, Ricardo Almeida, primary, Pires, João Moura, additional, Santos, Maribel Yasmina, additional, and Datia, Nuno, additional
- Published
- 2016
- Full Text
- View/download PDF
12. Spatial Disaggregation of Historical Census DataLeveraging Multiple Sources of Ancillary Information
- Author
-
Monteiro, João, Martins, Bruno, Murrieta-Flores, Patricia, Pires, João Moura, Monteiro, João, Martins, Bruno, Murrieta-Flores, Patricia, and Pires, João Moura
- Abstract
High-resolution population grids built from historical census data can ease the analyses of geographical population changes, at the same time also facilitating the combination of population data with other GIS layers to perform analyses on a wide range of topics. This article reports on experiments with a hybrid spatial disaggregation technique that combines the ideas of dasymetric mapping and pycnophylactic interpolation, using modern machine learning methods to combine different types of ancillary variables, in order to disaggregate historical census data into a 200 m resolution grid. We specifically report on experiments related to the disaggregation of historical population counts from three different national censuses which took place around 1900, respectively in Great Britain, Belgium, and the Netherlands. The obtained results indicate that the proposed method is indeed highly accurate, outperforming simpler disaggregation schemes based on mass-preserving areal weighting or pycnophylactic interpolation. The best results were obtained using modern regression methods (i.e., gradient tree boosting or convolutional neural networks, depending on the case study), which previously have only seldom been used for spatial disaggregation.
- Published
- 2019
13. Understanding the SNN Input Parameters and How They Affect the Clustering Results
- Author
-
Moreira, Guilherme, primary, Santos, Maribel Yasmina, additional, Pires, João Moura, additional, and Galvão, João, additional
- Published
- 2015
- Full Text
- View/download PDF
14. Detection of Road Accident Accumulation Zones with a Visual Analytics Approach
- Author
-
Ramos, Luís, primary, Silva, Luís, additional, Santos, Maribel Yasmina, additional, and Pires, João Moura, additional
- Published
- 2015
- Full Text
- View/download PDF
15. Dealing with Repeated Objects in SNNagg.
- Author
-
Galvão, João, Santos, Maribel Yasmina, Pires, João Moura, and Costa, Carlos
- Subjects
NEAREST neighbor analysis (Statistics) ,DATA mining ,FUZZY clustering technique ,SUPERVISED learning ,SPATIAL data structures - Abstract
Due to the constant technological advances and massive use of electronic devices, the amount of data generated has increased at a very high rate, leading to the urgent need to process larger amounts of data in less time. In order to be able to handle these large amounts of data, several techniques and algorithms have been developed in the area of knowledge discovery in databases, which process consists of several stages, including data mining that analyze vast amounts of data, identifying patterns, models or trends. Among the several data mining techniques, this work is focused in clustering spatial data with a density-based approach that uses the Shared Nearest Neighbor algorithm (SNN). SNN has shown several advantages when analyzing this type of data, identifying clusters of different sizes, shapes, and densities, and also dealing with noise. This paper presents and evaluates a new extension of SNN that is able to deal with repeated objects, creating aggregates that reduce the processing time required to cluster a given dataset, as repeated objects are excluded from the most time demanding step, which is associated with the identification of the k-nearest neighbors of a point. The proposed approach, SNNagg, was evaluated and the obtained results show that the processing time is reduced without compromising the quality of the obtained clusters. [ABSTRACT FROM AUTHOR]
- Published
- 2016
16. A granularity theory for modelling spatio-temporal phenomena at multiple levels of detail
- Author
-
Silva, Ricardo Almeida, Pires, João Moura, and Santos, Maribel Yasmina
- Abstract
Reasoning about spatio-temporal phenomena requires the adoption of common granularities that facilitate and enhance the comprehension of a particular phenomenon. In our day-to-day activities, spatial granules like state, province or country, and temporal granules like day, month or year, are used to index facts and to allow reasoning adopting the level of detail considered appropriate in a particular analytical context. In an era where huge amounts of spatio-temporal data are collected every day, it is crucial to model the spatio-temporal phenomena expressed in such data sets having in mind that different levels of detail can be useful in the analysis of such phenomena and that different levels of detail are related, for instance, through a spatial or temporal hierarchy. As the size and level of details of the data sets increase, the need to use multiple levels of detail that enhance our capability to achieve useful insights from data also increases. This paper presents a granularity theory devised to model spatio-temporal phenomena at different levels of detail. This granularity theory is more general than the existing granularities proposals. In fact, we relate those proposals with the presented granularity theory.
- Published
- 2015
- Full Text
- View/download PDF
17. A Data-driven Methodology Towards Mobility- and Traffic-related Big Spatiotemporal Data Frameworks
- Author
-
Figueiras, Paulo Alves, Jardim-Gonçalves, Ricardo, and Pires, João Moura
- Subjects
data- driven methodology ,geo-referenced time series ,Mobility- and Traffic-related data framework ,Big Spatiotemporal Data ,Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática [Domínio/Área Científica] ,spatiotemporal events - Abstract
Human population is increasing at unprecedented rates, particularly in urban areas. This increase, along with the rise of a more economically empowered middle class, brings new and complex challenges to the mobility of people within urban areas. To tackle such challenges, transportation and mobility authorities and operators are trying to adopt innovative Big Data-driven Mobility- and Traffic-related solutions. Such solutions will help decision-making processes that aim to ease the load on an already overloaded transport infrastructure. The information collected from day-to-day mobility and traffic can help to mitigate some of such mobility challenges in urban areas. Road infrastructure and traffic management operators (RITMOs) face several limitations to effectively extract value from the exponentially growing volumes of mobility- and traffic-related Big Spatiotemporal Data (MobiTrafficBD) that are being acquired and gathered. Research about the topics of Big Data, Spatiotemporal Data and specially MobiTrafficBD is scattered, and existing literature does not offer a concrete, common methodological approach to setup, configure, deploy and use a complete Big Data-based framework to manage the lifecycle of mobility-related spatiotemporal data, mainly focused on geo-referenced time series (GRTS) and spatiotemporal events (ST Events), extract value from it and support decision-making processes of RITMOs. This doctoral thesis proposes a data-driven, prescriptive methodological approach towards the design, development and deployment of MobiTrafficBD Frameworks focused on GRTS and ST Events. Besides a thorough literature review on Spatiotemporal Data, Big Data and the merging of these two fields through MobiTraffiBD, the methodological approach comprises a set of general characteristics, technical requirements, logical components, data flows and technological infrastructure models, as well as guidelines and best practices that aim to guide researchers, practitioners and stakeholders, such as RITMOs, throughout the design, development and deployment phases of any MobiTrafficBD Framework. This work is intended to be a supporting methodological guide, based on widely used Reference Architectures and guidelines for Big Data, but enriched with inherent characteristics and concerns brought about by Big Spatiotemporal Data, such as in the case of GRTS and ST Events. The proposed methodology was evaluated and demonstrated in various real-world use cases that deployed MobiTrafficBD-based Data Management, Processing, Analytics and Visualisation methods, tools and technologies, under the umbrella of several research projects funded by the European Commission and the Portuguese Government. A população humana cresce a um ritmo sem precedentes, particularmente nas áreas urbanas. Este aumento, aliado ao robustecimento de uma classe média com maior poder económico, introduzem novos e complexos desafios na mobilidade de pessoas em áreas urbanas. Para abordar estes desafios, autoridades e operadores de transportes e mobilidade estão a adotar soluções inovadoras no domínio dos sistemas de Dados em Larga Escala nos domínios da Mobilidade e Tráfego. Estas soluções irão apoiar os processos de decisão com o intuito de libertar uma infraestrutura de estradas e transportes já sobrecarregada. A informação colecionada da mobilidade diária e da utilização da infraestrutura de estradas pode ajudar na mitigação de alguns dos desafios da mobilidade urbana. Os operadores de gestão de trânsito e de infraestruturas de estradas (em inglês, road infrastructure and traffic management operators — RITMOs) estão limitados no que toca a extrair valor de um sempre crescente volume de Dados Espaciotemporais em Larga Escala no domínio da Mobilidade e Tráfego (em inglês, Mobility- and Traffic-related Big Spatiotemporal Data —MobiTrafficBD) que estão a ser colecionados e recolhidos. Os trabalhos de investigação sobre os tópicos de Big Data, Dados Espaciotemporais e, especialmente, de MobiTrafficBD, estão dispersos, e a literatura existente não oferece uma metodologia comum e concreta para preparar, configurar, implementar e usar uma plataforma (framework) baseada em tecnologias Big Data para gerir o ciclo de vida de dados espaciotemporais em larga escala, com ênfase nas série temporais georreferenciadas (em inglês, geo-referenced time series — GRTS) e eventos espacio- temporais (em inglês, spatiotemporal events — ST Events), extrair valor destes dados e apoiar os RITMOs nos seus processos de decisão. Esta dissertação doutoral propõe uma metodologia prescritiva orientada a dados, para o design, desenvolvimento e implementação de plataformas de MobiTrafficBD, focadas em GRTS e ST Events. Além de uma revisão de literatura completa nas áreas de Dados Espaciotemporais, Big Data e na junção destas áreas através do conceito de MobiTrafficBD, a metodologia proposta contem um conjunto de características gerais, requisitos técnicos, componentes lógicos, fluxos de dados e modelos de infraestrutura tecnológica, bem como diretrizes e boas práticas para investigadores, profissionais e outras partes interessadas, como RITMOs, com o objetivo de guiá-los pelas fases de design, desenvolvimento e implementação de qualquer pla- taforma MobiTrafficBD. Este trabalho deve ser visto como um guia metodológico de suporte, baseado em Arqui- teturas de Referência e diretrizes amplamente utilizadas, mas enriquecido com as característi- cas e assuntos implícitos relacionados com Dados Espaciotemporais em Larga Escala, como no caso de GRTS e ST Events. A metodologia proposta foi avaliada e demonstrada em vários cenários reais no âmbito de projetos de investigação financiados pela Comissão Europeia e pelo Governo português, nos quais foram implementados métodos, ferramentas e tecnologias nas áreas de Gestão de Dados, Processamento de Dados e Ciência e Visualização de Dados em plataformas MobiTrafficBD
- Published
- 2021
18. Segmentação automática de memórias pessoais
- Author
-
Coelho, David Miguel Casaca, Pires, João Moura, and Datia, Nuno Miguel Soares
- Subjects
Photographic picture ,Evento social ,Social event ,Informação temporal e geográfica ,Fotografia ,Temporal information ,Segmentation of personal photographic sets ,Segmentação de conjuntos de fotografias ,Geographical information - Abstract
Dissertação para obtenção do grau de Mestre em Engenharia Informática e de Computadores Na era digital há um aumento na produção de fotografias para consumo pessoal. Este acréscimo no número de fotografias produzidas torna mais difícil recuperar e visualizar fotografias relacionadas com um determinado evento social. No entanto a metadata associada a cada fotografia é também mais rica, incluindo frequentemente informação sobre o local onde cada fotografia é tirada. Para que seja facilitado o acesso às colecções de fotografias, é vantajoso apresentálas divididas em conjuntos com contexto semelhantes. Dado o grande número de fotografias, é importante que essa divisão seja feita automaticamente. Neste trabalho pretende-se construir um algoritmo de segmentação de conjuntos de fotografias, que assenta exclusivamente na informação presente na metadata, especificamente a informação temporal e geográfica. O objectivo é conseguir que cada segmento encontrado — um conjunto de fotografias — seja, na medida do possível, representativo de um evento social na vida do utilizador. O algoritmo desenvolvido é uma evolução de um outro, que efectua a segmentação apenas considerando a informação temporal, aqui estendido para incorporar também a informação geográfica. Nesse sentido, com ambas as segmentações é possível avaliar se a informação geográfica é redundante em relação à informação temporal. Com os testes efectuados, quer de caracterização, quer com utilizadores, verificouse que a informação geográfica aparenta ter vantagens quando utilizada como complemento à informação temporal. Os testes com utilizadores revelaram essa tendência, sendo necessário uma amostra maior para confirmar estatisticamente esta conclusão. Abstract: In the digital age the production of personal photographic images is increasing. As the number of photographic images increases, it becomes harder to retrieve and to visualize photos from a given social event. However, the metadata associated to each picture is richer, often including information about the place where it was taken. To ease the access to personal photo collections, one can divide them into sets, each with it’s own context. Considering the large number of photos in each collection, it is important to automate such division. In this work, a segmentation algorithm is constructed, which is intended to segment sets of photographic pictures, a process that is based exclusively in the information present in the metadata, specifically the temporal and geographic information. Each segment found — a set of photographic pictures — represents a social event in the life of the user. The algorithm developed in this work is na evolution of another algorithm, which performs the process of segmenting picture sets considering only the temporal information, here extended to include geographic information as well. This way, with both segmentations it becomes possible to evaluate if the geographic information is redundant when we consider that temporal information is always present. The algorithms were tested using both theoretical tests and user tests. It was verified that the geographical information appears to have advantages when used as a complement to the temporal information. User tests revealed that tendency, despite the fact that a larger sample is needed to increase statistical power of the conclusion.
- Published
- 2014
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.