Alexandre Carvalho

Alexandre Valle de Carvalho has been a University Professor since 2001, and Assistant Professor in the Department of Computer Engineering (DEI) at the Faculty of Engineering of the University of Porto (FEUP) since 2009. He is a researcher at the Center for Information Systems and Computer Graphics (CSIG) at INESCTEC, since 2001 and senior researcher since 2009. The scientific area of Computer Graphics has been present throughout its academic path, starting with Raytracing and Radiosity Hybrid for the Calculation of Photorealistic Images, of 1994, in the Graphical Interface of the Input Module of Data from the VALORAGUA Model, from 1997, in the Image Synthesis for Virtual Environments Experiences with the RENDERCACHE technique, from 2001., culminating with his PhD entitled “Spatio-temporal Information Management and Visualization” in 2009. Furthermore, other professional activity in Geographic Information Systems, as a scholarship, technical staff and then as a researcher at INESC Porto, motivated the scientific study in this area and in the application domain of urban information management, eDemocracy and eGovernment. The joining of both areas - computer graphics and information systems - as well as the background in urban data management resulted in the theme and PhD work, in management and visualization of space-time information, completed in 2009, where he defended two hypothesis: one in information systems and another in information visualization. Alexandre performs research in these two areas until the present time. Furthermore, he has participated in a considerable number of research and development projects, framed by European projects, R&D national projects and specialized consultancy, having publications indexed in scientific conferences and journals. Regarding economic and direct knowledge extension to society, Alexandre founded SIAGHOS in 2012, towards systems and technology to support observational clinical studies. In this context, it conceived, produced and innovated in information systems to support the registration and analysis processes of observational clinical studies for hematology-oncology diseases. These systems were used by a considerable number of Portuguese hematologists, between 2012 and 2018. Furthermore, in 2015 Alexandre co-founded MITMYNID, an INESC TEC spinoff towards innovative solutions for the Transport and Logistics Sector. At MITMYNID, Alexandre participated in the coordination BIZCARGO and of projects with a high degree of innovation and in the elaboration and execution of proposals and provision of services where innovation is also evident. Examples of this are two P2020 demonstration projects and collaboration on two European projects. In the context of university management, Alexandre performed scientific and pedagogical coordination of curricular units, course groups and degree and master courses.

Domains

Human-Centered Computing and Information Science Artificial Intelligence Computer Science and Engineering

Projects

MoST

The general scope of the MOST Project (INESCTEC and University of Aveiro): Recent technological advances have allowed the collection of data volumes on the evolution of spatio-temporal phenomena much higher than the existing capacity to analyze them and extract relevant information in various scientific areas. Therefore, tools capable of automating processes of quantitative analysis of spatio-temporal data are increasingly necessary, ensuring levels of objectivity, precision, and reproducibility compatible with the performance of scientific work. Currently, there are well-known tools for processing static spatial data (e.g., Geographic Information Systems), but support for modeling dynamic phenomena is limited, often requiring a great effort in programming complex algorithms that are specific to a particular problem. This project focuses on the development of advanced tools for modeling and analyzing spatio-temporal data, using continuous representation models in space and time. The key element will be a data management system capable of modeling generic spatial transformations (e.g., shape change, size change, translation, rotation, aggregation or fractionation of entities or objects) representing the phenomena of interest over time. This system will be accessible through a query language providing functions for the management, query, and processing of large volumes of data. Methods will also be developed to create spatio-temporal representations from sequences of images or videos, and data visualization tools and user interaction. An integrated set of tools will be provided to simplify the conduct of studies on spatio-temporal phenomena. The goal is to reduce the time and effort that today is necessary to dedicate to the development of complex data management and processing procedures, thus freeing resources for the performance of the studies themselves. The proof of concept is based on two case studies involving the modeling of spatio-temporal phenomena with distinct characteristics. The first consists of modeling the propagation of forest fires from aerial images, with a view to conducting studies on carbon emissions to the atmosphere. The second consists of creating a database characterizing the morphological changes that cells undergo when they move in their own environment. The quantification of these characteristics is important in biological processes such as embryonic development or tumor formation. The origins of the data are microscopic videos. In the future, it is also intended that the results of this project can be applied in other areas, for example, in studies on coastal erosion, river silting, or others.

Modeling, querying and interactive visualization of spatiotemporal data

EESDataLab

Scientists and engineers working in fields such as the environmental sciences, the oceans, climate, or earth sciences have access to massive amounts of geo-referenced data. These data allow monitoring and studying the behavior of objects or events of interest over time, making diagnoses and predictions, etc. These tasks assume the existence of good quality data and methods and tools to analyze the data with little effort. Currently, there are many tools help on managing, processing, and analyzing spatial data, but the same does not happen when one intends to work with spatial data that evolves over time. The project as a whole focuses on the development of models and tools for the processing of spatiotemporal (SPT) data, based on two case studies: environmental engineering and marine ecology. The focus will be on SPT data modeled as 2D and 3D geometries that can change position, shape, or size continuously over time (moving objects). For example, we can model an iceberg as a 3D moving object (thus representing its movement and changes in size and shape over time). This model has advantages over discrete models, particularly when one intends to represent the evolution of geometrically definable objects or events, as it allows for more compact and intuitive representations, and guarantees the independence of the data from the acquisition process. The duration of the project was 12 months, and the strategy consisted of testing solutions and defining guidelines for future research. The team had mind the study of solutions for the areas of databases and GIS, as well as more recent trends, namely machine learning, data stream analysis, and digital twins. The participating institutions are the University of Aveiro, INESC TEC Porto, and the Polytechnic Institute of Leiria. The team consists of six researchers: four from the area of computer engineering and computer science, one from environmental engineering, and another from the area of marine ecology. Professor Justin Solomon, leader of the “Geometric Data Processing” group of the “Computer Science and Artificial Intelligence” laboratory at MIT, will also collaborate with this project.

View all projects

Publications

BEYOND FRONT AND BACK OFFICE: VISUALIZATIONS, REPRESENTATIONS AND ACCESS THROUGH POSTCOLONIAL LENSES BETWEEN A RESEARCH PLATFORM AND AN ARTS EDUCATION ARCHIVE

Assis, T;Martins, C;Valle, A;Santos, A;Castro, J;Osório, L;Silva, P;

2023

ICERI2023 Proceedings - ICERI Proceedings

A Comparison of Point Set Registration Algorithms for Quantification of Change in Spatiotemporal Data

Gomes M.;De Carvalho A.V.;Oliveira M.A.;Carneiro E.;

2023

Iberian Conference on Information Systems and Technologies, CISTI

A spatiotemporal extension for dealing with moving objects with extent in Oracle 11g

Matos, L;Moreira, J;Carvalho, A;

2012

ACM SIGAPP Applied Computing Review

Representation and management of spatiotemporal data in object-relational databases

Matos, L;Moreira, J;Carvalho, A;

2012

Proceedings of the ACM Symposium on Applied Computing

View all publications

Supervised theses

Cross-platform application for determination of sulfonamides in water using digital image colorimetry

Fábio Alexandre Matos Azevedo

M - 2021

UP-FEUP

Centres

Human-Centered Computing and Information Science

The Centre for Human-Centered Computing and Information Science (HumanISE) brings together engineers, scientists, and designers with expertise in Human-Centred Computing (HCC), Computer Science (CS), and Information Science (IS). Interdisciplinarity, one of the Centre’s defining features, fosters the development of software systems, methods, and tools designed to empower individuals and their communities. The excellence and impact of HumanISE’s research, innovation, and consultancy activities allow addressing increasingly complex, volatile, heterogeneous, ambiguous, and uncertain challenges, while ensuring compliance with legal, ethical, and organisational standards and frameworks. Value transfer is achieved through close collaboration with academia and industry partners. HumanISE’s core research areas include Human-Computer Interaction; Computer Graphics and Interactive Digital Media; Information Management and Information Systems; Software Engineering; and Large-Scale and Special-Purpose Computing Systems, Languages, and Tools; as well as Computing for Embedded and Cyber-Physical Systems. HumanISE also explores innovation domains like Earth, Ocean and Space Sciences; Personalised Health Research; Geospatial Information Systems Engineering; and Applied Information Systems and Computing.