Category Archives: Highlights

PhD Defense in Digital Media: ”Images as data and metadata: management practices to promote Findability, Accessibility, Interoperability and Reusability of research data”

Posted on

Candidate
Joana Patrícia de Sousa Rodrigues

Date, Time and Location 
June 17, 14:00, Sala de Atos FEUP

President of the Jury
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia, Universidade do Porto.

 Members
Cláudia Maria Bauzer Medeiros, PhD, Professor, Departamento de Sistemas de Informação, Instituto de Computação, Universidade Estadual de Campinas, Brasil;
Maria Manuel Lopes de Figueiredo Costa Marques Borges, PhD, Associate Professor with Habilitation, Departamento de Filosofia, Comunicação e Informação, Faculdade de Letras, Universidade de Coimbra;
José Luís Brinquete Borbinha, PhD, Full Professor, Departamento de Informática do Instituto Superior Técnico da Universidade de Lisboa;
Cândida Fernanda Antunes Ribeiro, PhD, Full Professor, Departamento de Ciências da Comunicação e da Informação, Faculdade de Letras, Universidade do Porto;
Maria Cristina de Carvalho Alves Ribeiro, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia, Universidade do Porto;
Carla Alexandra Teixeira Lopes, PhD, Assistant Professor, Departamento de Engenharia Informática, Faculdade de Engenharia, Universidade do Porto (Supervisor).

Abstract
The evolution of the use and production of images is notorious. Technological development favors the emergence of images. This scenario is also applicable in the field of scientific research, where more and more instruments are used to facilitate image capture. With this context as a motto, and knowing that images have particular characteristics, this work explores the dynamics of images in research according to two scenarios: images as data and images as metadata. From a perspective of images as data, the aim is to understand how they can sufficiently represent the data obtained, favoring description. From the perspective of images as metadata, the aim is to understand how they can be used as a tool capable of faithfully describing a dataset and promoting its adequate contextualization and interpretation. Through exploratory research, several experiments with images as data and as metadata wereconducted, based on the dynamics and principles of Research Data Management (RDM). The work begins with an overview of the literature on the subject, in which the management of research data and its relationship with the use and production of images is explored, namely a study of the evolution of the image in the context of scientific, going through its challenges and opportunities, to the way it is treated by researchers, always with RDM as a guiding line. Subsequently, we move on to a view of the informational behavior of those who use and produce images in the context of research, namely in the search to identify behavior patterns in four studies. The first study starts from the perspective of a specific research project and the remaining three studies take a perspective that includes more stakeholders from different research domains. Thus, the scenarios of images as data and as metadata are explored, through the presentation of experiences that mostly involved researchers. For the case of images as data, four studies are presented, with specific contributions, starting with the proposal of a new metadata model for describing data in image format and their respective controlled vocabularies. The remaining three studies focus on automatic image processing, the publishing and sharing of data, and, finally, the definition of guidelines for using and producing images in the context of research. For the case of images as metadata, we conducted two studies, the first exposing a new perspective on data description, through the use of images as metadata. It is this new perspective that challenges us to take a new approach, which culminates in the second study, which is based on an experience developed with researchers and aims to alert and raise awareness of the use of other types of documents in the scientific process. This work has made it clear that images do not always have a formal, standardized role in research data management. However, researchers are open to including images more formally in the scientific process. Furthermore, it is clear that researchers can identify advantages in the use and production of images. The general trend of exponential growth in the production and use of images (motivated by technological developments and new sharing and dissemination tools) is also seen in the context of research, as the various participants in the studies carried out identified it as such, which points to an imminent need to make the role of images representative in the context of research data collection. The contributions obtained from this work are reflected in the response to the need for including images in the RDM. Starting from a more conceptual approach, a consistent overview was obtained about the habits of those who use and produce images through the analysis carried out in the literature, namely through the systematic review carried out and which includes several analysis variables, up to studies carried out through questionnaires and surveys and which allowed direct contact with researchers, thus allowing us to relate what theory tells us with what practice does. In the context of images as data, the metadata model and controlled vocabularies are a significant contribution, as they explore new possibilities of description, much more focused on the type of data in question (images). Furthermore, studies of sharing platforms, as well as the possibilities of automatic description of images, made it possible to generate a starting point and determine the path to follow. Still, in the context of images, it is important to highlight the guidelines for the use and production of images that appear as a contribution to the scientific community, in the sense that they guide specific image practices and needs. In the context of images as metadata, the great contribution lies, precisely, in the presentation of an innovative approach to data description, where the particular characteristics that images have are highlighted and that position them as allies of researchers in the data description process and present practical examples of how this description through images could occur.

Keywords: Image; Image as Data; Image as Metadata; Information Behavior; Research Data; Management.

PhD Defense in Digital Media: ”Narratives of Our Age: Intergenerational Digital Storytelling and Cultural Identity”

Posted on

Candidate
Juliana Carolina Campos Monteiro

Date, Time and Location 
June 4, 14h30, Room Professor Joaquim Sarmento (G129), DEC, FEUP

President of the Jury
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia, Universidade do Porto.

Members
Paulo Nuno Gouveia Vicente, PhD, Associate Professor, Departamento de Ciências da Comunicação, Faculdade de Ciências Sociais e Humanas, Universidade Nova de Lisboa;
Daniel da Cruz Brandão, PhD, Assistant Professor, Departamento de Ciências da Comunicação, Instituto de Ciências Sociais, Universidade do Minho;
Teresa Margarida Loureiro Cardoso, PhD, Assistant Professor, Departamento de Educação e Ensino à Distância, Universidade Aberta;
Dinis Miguel de Almeida Cayolla Ribeiro, PhD, Assistant Professor, Departamento de Ciências da Arte e do Design, Faculdade de Belas Artes, Universidade do Porto;
Carla Susana Lopes Morais, PhD, Assistant Professor, Departamento de Química e Bioquímica, Faculdade de Ciências, Universidade do Porto (Supervisor).

Abstract
The expansion of digital tools and participatory media created unprecedented possibilities for the maintenance and sharing of social memory and cultural identity knowledge. These possibilities are expanding in parallel with a context of an increasingly aged society, where elders are privileged keepers of regional cultural knowledge but often don’t have the opportunity to pass it on to future generations, making it prone to shortly disappear. This research approaches digital storytelling during intergenerational exchanges as a stage for a participatory contribution to the maintenance of cultural identity. We sought to determine how intergenerational dynamics can give place to cultural identity narratives, as well as how digital media can support the maintenance of cultural identity. For that purpose, we promoted the project NOOA: Narratives Of Our Age, with the premise of bringing generations together in sharing stories on topics such as Memories, Crafts, Myths, and Traditions, to endorse the continuity of the cultural identity of the Vale do Sousa region, using the potential of digital media in this process. With an action research design and an ethnographic approach, from 2018 to 2021, this project reunited three intergenerational groups, composed of participants aged 16 to 85 years old, in a set of activities designed to foster intergenerational dynamics. We sought to gather qualitative perceptions about the phenomenon of storytelling in the participatory maintenance of cultural identity through intergenerational dynamics. To this end, our research was based on data collected through detailed observations and through the application of semi-structured interviews and group discussions. We developed a five-step intergenerational storytelling framework to encourage the exchange of cultural identity knowledge, including digital registration, dissemination, and discussion in-person and online. This framework was submitted to a cyclical evaluation and its adjustments, in accordance with the action-research method, and it was implemented in three phases: phase one corresponded to a group dynamic component, through brainstorming and story planning; phase two corresponded to the creation of digital stories; phase three corresponded to dissemination, with the publication and sharing of these stories in the project’s digital spaces. These steps were conducted through in-person digital storytelling activities, in which cultural identity knowledge was shared and discussed in intergenerational partnerships, resulting in the participatory creation of 35 digital stories, that were afterwards shared and also discussed on the Project’s digital spaces. The outcomes of the activities, as well the enthusiasm and the reflections that occurred during the process, highlight the investment of participants in the transmission and maintenance of knowledge related to their experiences and knowledge acquired throughout life, in a family and community context. The observations of intergenerational dynamics, as well as the results of the semi-structured interviews, suggested a growing curiosity, involvement and overall understanding and retention of the stories of cultural identity, by both seniors and juniors, as well as a growing curiosity of senior participants regarding the pervasive digital reality presented to them by the juniors. Likewise, we observed the importance of empowering groups with spaces of sharing, both face-to-face and online, to enhance intergenerational exchanges around the knowledge of cultural identity. By promoting opportunities for intergenerational dialogue and empowering groups with face-to-face and online sharing spaces, we contributed with the development and application of a storytelling framework and digital spaces to safeguard, discuss and disseminate some of the specific cultural knowledge of the region of Vale do Sousa in Portugal. We observed the potential of using digital storytelling dynamics to break through barriers of communication between generations and to perpetuate and value cultural identity knowledge, acquired throughout life. This research goes beyond the aim of documenting the envisaged cultural identity knowledge, by combining creativity during the digital storytelling processes with connectivity among the participants on a community level, by sparking the dialogue between generations and enhancing the social impact of cultural identity knowledge and the self-knowledge value that generations are able to share through stories. We examined the opportunities and challenges of digital media as a platform and a catalyst for cultural identity maintenance, situating the problematic of cultural literacy in a contemporary setting. We conducted a thorough assessment of the stakeholders involved in participatory cultural identity maintenance in our present context, adding the observation of their synergies in a real context. This allowed us to examine the diversity of outcomes and the multiplicity of variables that contribute to it, as well as to grasp the impact that this new information flow paradigm may have on how we currently approach cultural identity maintenance.

Keywords: Intergenerational Digital Storytelling, Cultural Identity, Cultural Literacy, Participatory Action-Research.

PhD Defense in Digital Media: ”Computing by going back in time: Composing video sequences through multimodal generative coordination”

Posted on

Candidate:
Luís Henrique Pinto Arandas

Date, Time and Place:
June 03, 14:30, Sala de Atos FEUP

President of The Jury:
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia, Universidade do Porto.

Members:
Luísa Maria Lopes Ribas, PhD, Assistant Professor, Departamento de Design de Comunicação, Faculdade de Belas-Artes, Universidade de Lisboa;
David Fernandes Semedo, PhD, Assistant Professor, Departamento de Informática, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa;
André Sier, PhD, Invited Assistant Professor, Departamento de Artes Visuais e Design, Universidade de Évora;
José Miguel Santos Araújo Carvalhais Fonseca, PhD, Full Professor, Faculdade de Belas Artes, Universidade do Porto (Supervisor);
Gilberto Bernardes de Almeida, PhD, Assistant Professor, Departamento de Engenharia Informática, Faculdade de Engenharia, Universidade do Porto.

The thesis was co-supervised by Professor Mick Grierson, Professor in Computing, and research leader at the Institute of Creative Computing at the University of the Arts, London.

Abstract
This project proposes a set of methods, inspired by the human experience of vision and time, for developing video sequences using trained generative models. The methods serve the production of video sequences, with patterns derived from trained models found in literature on metacreation and in the artworld. This project defines possible futures where the now pervasive generative models can be reused in computer simulations that focus on the human experience of video and mental images; models which, because of how they are trained through archives and records representing both the human and the physical world, can capture media themselves and represent specific moments in time.

The research outputs are in film and audiovisual installation, proposing that practice can further benefit from self-reference, using deep generative models as synthesisers of video, sound, and text. The methods produced take advantage of natural language guidance and deep generative models in ways that can be understood as sampling, sequencing, and translation, following computing literature and AI design. Each result can be understood in larger domains such as: 1) short films from text inputs, in the film Irreplaceable Biography; 2) discursive installations from video datasets, in the installation Time as meaning; and 3) short films from video inputs, in the film Man lost in the convergence of time and the collaboration all YIN no YANG. This research extends on the use of generative practice following a construct of language in the human mind, behaviour, and visual experience as inspiration for the experience of video. These projects further define what can be a broader understanding of directionality and representation of the past using systems of memory that learn, are networked and produced following structure found in nature and human experience.

Keywords: Video composition; Deep generative models; Time-travelling; Human visual experience; Predictive representations.

PhD Defense in Informatics Engineering: ”Enhancing Forecasting using Read & Write Recurrent Neural Networks”

Posted on

Candidate
Yassine Baghoussi

Date, Time and Place
May 29, at 09:30, Sala de Atos FEUP

President of the Jury
Pedro Nuno Ferreira da Rosa da Cruz Diniz, PhD, Full Professor, Department of Informatics Engineering, Faculty of Engineering, University of Porto.

Members
Joydeep Chandra, Phd, Associate Professor, Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Índia;
Mykola Pechenizkiy, PhD, Full Professor, Department of Mathematics and Computer Science, Eindhoven University of Technology, The Netherlands;
Luís Filipe Pinto de Almeida Teixeira, PhD, Associate Professor, Department of Informatics Engineering, Faculty of Engineering, University of Porto;
João Pedro Carvalho Leal Mendes Moreira, PhD, Associate Professor, Department of Informatics Engineering, University of Porto (Supervisor).

The thesis was co-supervised by Professor Carlos Manuel Milheiro de Oliveira Pinto Soares, Associate Professor at the Department of Informatics Engineering, University of Porto.

Abstract

“Machine Learning (ML) relies on both data and algorithms for optimal functioning. While conventional ML research often emphasizes algorithmic improvements, the significance of data processing is frequently overlooked. In contrast, preprocessing data stands as a distinct task, executed before feeding it into algorithms. The diversity of preprocessing methods tailored for various ML algorithms underscores its importance. However, the feedback loop between algorithms and data is often neglected. Data-related issues pose significant challenges for predictive ML algorithms, adversely affecting forecasting accuracy. These challenges arise because problems in data are inherently unpredictable, lacking a discernible pattern. In this doctoral thesis, we introduce Read and Write Machine Learning (RW-ML), an innovative paradigm enhancing time series forecasting accuracy by integrating data modification techniques into the learning process. The RW-LSTM, an adaptation of the backpropagation algorithm, unifies preprocessing with recurrent neural networks (RNNs), significantly outperforming traditional models such as LSTM. RW-LSTM enables the transition from read-only RNNs, which merely learn from data, to RW-ML, allowing direct alterations for improved predictions. Expanding the framework, the Corrector Long Short-Term Memory (cLSTM) addresses the limitations of read-only RNNs, demonstrating enhanced forecasting accuracy through empirical verification and extensive experiments. The final chapter provides a real-world evaluation, highlighting the competitive advantage of cLSTM over LSTM models in various scenarios.”

This research was carried out as part of SonaeIM.Lab@FEUP, involving Inovretail.

DEI TALKS | “Graph@FIT – activities in research of Image/Video/Graphics at FIT BUT” by Prof. Pavel Zemčík

Posted on

“The talk will introduce the Graph@FIT, the research group of Brno Unviersity of Technology (BUT), Faculty of Information Technology (FIT) active in Image/Video/Graphics research (See also Computer Graphics Research Group – GRAPH (vut.cz)). The talk will include and overview of the research with several examples of research topics and results of the research, such as Road Traffic Video Processing, Hardware Accelerated Imaging Algorithms, and exploitation of Neural Networks.”

“Graph@FIT – activities in research of Image/Video/Graphics at FIT BUT” will be presented May 27, at 17:30, in room I -105, moderated by Prof. António Coelho (DEI).

“Pavel Zemčík is a Professor at Brno University of Technology (BUT), Faculty of Information Technology (FIT), vice-dean for research, development and foreign affairs. Between 2016 and 2024 he served as a dean of FIT. His interests include image and video processing, computer graphics, embedded systems, acceleration of algorithms in hardware, etc. He is author/co-author of over 100 scientific papers in journals and at conferences.”

PhD Defense in Informatics Engineering: ”Enhancing Research Data Lifecycle: Solving Observation-centric and Reproducibility Challenge”

Posted on

Candidate
Artur Jorge da Silva Rocha

Date, Time and Place
May 17, 14:30, Sala de Atos FEUP

President of the Jury
Pedro Nuno Ferreira da Rosa da Cruz Diniz, PhD, Full Professor, Faculdade de Engenharia da Universidade do Porto

Members
José Luís Brinquete Borbinha, PhD, Full Professor, Department of Informatics Engineering, Instituto Superior Técnico da Universidade de Lisboa;
Irene Pimenta Rodrigues, PhD, Associate Professor, Informatics Department, Universidade de Évora;
Rosaldo José Fernandes Rossetti, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto;
Ademar Manuel Teixeira de Aguiar, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto (Supervisor).

Abstract
“Observation is central to most research methods independent of the paradigms used. From the observational roots of positivism to the subjective individual experiences of interpretivism, most, if not all, scientific studies require repeatedly observing features over time. Documenting observations and the processes used to acquire them, capturing the context of observations, and identifying relationships between observed features in a structured and meaningful manner is extremely important for the interpretability and reproducibility of research results. It is common that the effort preceding data processing, including steps such as data cleansing and structuring, vastly outweighs the time spent writing and tailoring the algorithms for processing and analysis. Therefore, having a conceptual framework instantiated in models, methods, and tools to effectively record observations in a structured way, independently of their nature, along with associated features and context, would help reduce the effort of preprocessing and potentially contribute to increasing the quality of results. Analogously, derived features resulting from the processing of the original observations can benefit from a similar approach, thus making the workflows on research data more explicit and reproducible. This research work is focused on the data collection and analysis stages of the research data lifecycle. It has been done in the context of diverse research projects, over several years, contributing to structure knowledge across different research domains. The research encompassed the identification of new needs, the design and prototyping of novel solutions, and their application to concrete high-demand environments to test, refine, and validate the proposed solutions, which are collectively consolidated as an enhanced approach for the lifecycle of research data. As a result, this work provided contributions of different types, of which we highlight observation templates and observation framework. These main contributions were validated in the context of the respective research projects and scientific publications.”

50 years of democracy: thinking the future!

Posted on

What do we want the next 50 years of democracy to be like? What are the new challenges in a changing Europe? Will it be a different democracy from the one we have today?

These were some of the questions that journalist Eduarda Maio raised for discussion on “Consulta Pública”, Antena 1 programme, in its 15th episode on 2024, recorded on 24 April.

Henrique Lopes Cardoso, a lecturer at DEI and member of LIACC, was on the panel with Catarina Neves (Nova School of Business and Economics), José Neves (NOVA FCSH), Paulo Machado (Instituto Superior de Ciências Policiais e Segurança Interna) and João Cerejeira (School of Economics and Management, Universidade do Minho), and looked at the role of new technologies in general, and Artificial Intelligence in particular, as an enabler of democracy, leaving a positive message about the wealth of relevant applications in today’s society, although did point out that there are real concerns about the manipulation of technology and disinformation, something that in his opinion should be fighted with a growing commitment to digital literacy in all generations.

For 1h43m the five guests “thought the future of democracy”, exchanging opinions and arguments and bringing different opinions and perspectives on the subject to the discussion.

The episode can be listened in full here.

“Florensics” team wins TecStorm 2024

Posted on

The awards ceremony of the 8th edition of TecStorm took place over the weekend of April 21-22, at the Champalimaud Foundation, where it honoured four projects by university students in the categories of Improving Lives through Connectivity, Energy Solutions for a Low Carbon Future, Health 4.0 and Data-Driven Sustainable Mobility Solutions.

Florensics, a team composed of Eunice Amorim, Francisco Pires and Lucas Santos, final year students of the Master in Informatics and Computing Engineering (M.EIC), was one of the winners of this edition, in the Improving Lives through Connectivity category, with a cash prize of 2,500 euros, sponsored by Vodafone.

The winning project is characterised by an innovative system based on IoT (Internet of Things), which consists of a network of devices (equipped with flame and carbon monoxide sensors, among others), strategically distributed throughout a forest area to collect data to prevent and fight fires more efficiently and earlier.

When asked about the experience, the team shares that TecStorm provided them with a unique experience that allowed to validate and present an idea with the potential to contribute to fire prevention, something especially relevant to our country. For 24 hours “we had the opportunity to put not only our engineering skills to the test, but also our teamwork, presentation, prototyping, planning and time management skills. We’re proud that our work has been recognised, and we’d like to thank all the organisers and participants who made this event a reality”, shares Lucas Santos.

TecStorm is the country’s largest technology competition, which encourages young entrepreneurship and the launch of innovative ideas capable of generating an impact on society.

It was created by JUNITEC, the junior company of the Instituto Superior Técnico, and stands out for being the oldest junior company in Portugal. Its core business is technological consultancy, where its mission is to realise projects with innovative technologies that have a high impact on society and bridge the gap between the student community and the business community.

Photo by JUNITEC

NIAEFEUP at Shift APPens 2024

Posted on

Last weekend, the C. F. União de Coimbra Pavilion welcomed the 250 participants of Shift APPens, a 48-hour hackathon organised by Núcleo de Estudantes de Informática da Associação Académica de Coimbra and jeKnowledge, FCTUC’s Junior Enterprise.

In this 10th edition, the team made up of João Torre Pereira and Diogo Fernandes (L.EIC 3rd year) and Linda Albuquerque and Rafael Fernandes (Master’s in Design and Multimedia at FCTUC), won the 2nd place with the project BookShifter – Shift your head in the right direction, a mobile application that avoids tilting the head when exploring books in a bookshop/library. The mobile phone camera is used to read the books on the shelf and to get all the information about them without having to open them.

The pitch presented to the jury and the demo can be seen here.

Luis Duarte (L.EIC 3rd year) and Rubem Neto (L.EIC 2nd year) were also awarded prizes in challenges organised by the companies GoodBarber and RedLight, respectively. All L.EIC students mentioned are members of NIAEFEUP, Núcleo de Informática da Associação de Estudantes da FEUP.

As well as being a programming and entrepreneurship competition, where teams of up to four elements develop a project in the field of technology over 48 hours, Shift APPens is also the stage for talks, workshops, mentoring, contact with companies, personalised challenges, prizes, games, socialising and, of course, lots of fun.

Creativity Talks | “ ‘Design thinking’ and its relationship to other disciplinary approaches” by Prof. Nathan Crilly

Posted on

Efforts to promote creativity often centre on encouraging people to engage in ‘design thinking’. Although this term has many different meanings, many of these meanings centre on the idea that even non-designers should behave more like designers. That is, people should treat whatever they are influencing as though it is something they are designing, whether that is a service, an organisation, some legislation, a piece of policy or anything else. The application of design thinking to these projects might include (amongst other things) an emphasis on developing an understanding for users, visualising ideas and iteratively testing prototype solutions. Although design thinking is often considered in isolation, it can easily be connected to approaches such as ‘systems thinking’ and ‘entrepreneurial thinking,’ which are also relevant to how problems are identified, framed and solved.

In this talk, Prof. Nathan Crilly will consider how these different approaches are related to each other, and how they are related to other similar approaches from other disciplines that might support us in undertaking creative work.

“ ‘Design thinking’ and its relationship to other disciplinary approaches” will be presented April 23, at 6pm,  at the CTalks YouTube channel, moderated by Prof. António Lucas Soares (DEI).

All the information about the talk can be seen at the Creativity Talks webpage.

“Nathan Crilly is Professor of Design at the University of Cambridge, where he researches human behaviour as it relates to design. This includes studying the behaviour of the people doing design work (e.g. designers’ creativity), and the experiences of those people who interact with design outcomes (e.g. users’ experiences). Nathan teaches design, creativity and communication at the undergraduate and postgraduate levels. He also teaches design thinking at the executive level, promoting innovation across a broad range of business sectors. Nathan plans, manages and conducts commercial research to deliver user insights for design projects focused on various markets, including consumer health, digital devices and sporting equipment.”