Author Archive: José Barboza

2022 MDSE – Sunset Session: Ethics and Responsability in AI

Posted on

With the preparation of the 3rd edition of the M.Sc. on Data Science and Engineering (https://dei.fe.up.pt/mdse/) well under way, it is time to look back at what was accomplished so far and also to project the future. This will be done as part of the 2022 MDSE Sunset Session, on the 2nd July (Saturday), in room B032, in a relaxed environment but focused on a very important topic: Ethics and Responsability in AI.

The program will feature two keynote talks, by Ana Costa e Silva (Mercer) and Pedro Saleiro (Feedzai), as well as a panel discussion including Inês de Matos Pinto (S&D Group @ European Parliament), Inês Sousa (Fraunhofer Portugal) and Peter van der Putten (Pegasystems & U. Leiden), moderated by Eugénio Oliveira (FEUP). During the event MDSE students will also present some of their projects.

The event is targeted both to companies, looking for talent in Data Science, as well as prospect students, looking for an advanced education on Data Science.

Participation is free but requires registration here.

 Program

14:30 – Opening – João Mendes Moreira – Director of the M.Sc. on Data Science and Engineering (MDSE)

14:40 – Ana Costa e Silva – Global Chief of Data Science @ Mercer, TBA – introduced by António Pedro Aguiar

15:10 – Pedro Saleiro – Director of AI Research @ Feedzai, challenges in the development of responsible AI research/solutions in Industry – introduced by José Luís Borges

15:40 – MDSE Student Showcase – introduced by Ana Aguiar

  • Cláudia Pinheiro: AI-based cancer characterization using semi-supervised learning algorithms
  • Diogo Queirós: Reconciling prediction in the regression setting: an application to Portuguese breweries’ market share prediction
  • Nuno Gaspar: Prediction of Shell Finite-Element Stresses using Convolutional Neural Networks (CNN)
  • Rafael Guedes: Data, machine vision and reinforcement learning for explainable and safe autonomous driving of platooning vehicles
  • Wagner Ceulin: Predicting customer purchasing behavior of a self-care online store
  • João Pedro Pêgo: Predicting candidate engagement in a job matchmaking site

16:30 – Coffee Break

17:10 – Panel discussion – moderated by Eugénio de Oliveira – Emeritus Professor @ FEUP

18:20 – Closing João Mendes Moreira – Director of the MDSE

18.30 – Sunset Drinks & Networking

19.30 – End of the event

We are very grateful to our partner for their support

DEI Talks | ”Mergeable Nervous System for Robot Swarms” by Marco Dorigo

Posted on

Marco Dorigo is the proponent of the well-known “Ant Colony Optimization” meta-heuristic optimization algorithm and a leading researcher in the field of swarm robotics, which allows groups of individually very simple agents/robots to obtain group intelligence that allows coordinating large groups of autonomous agents/robots without relying on any external infrastructure or any form of centralized control. This approach is very promising for performing tasks that are too difficult or dangerous for humans using very simple and inexpensive sets of agents/robots.

 ”Mergeable Nervous System for Robot Swarms” will be presented June 29, at 16:00, in room I-105.

 Abstract:

Typically, robot swarms coordinate through self-organization. With the proposal of the mergeable nervous system concept, we study how self-organization can be made more powerful as a tool to coordinate the activities of a robot swarm by injecting some components of hierarchical control. In the presentation, I will give a brief overview of the mergeable nervous systems concept and then illustrate the first steps we have made in implementing it in a heterogeneous swarm composed of drones and ground robots.

Bio:

Marco Dorigo received the Ph.D. degree in electronic engineering in 1992 from Politecnico di Milano, Milan, Italy. From 1992 to 1993, he was a Research Fellow at the International Computer Science Institute, Berkeley, CA. In 1993, he was a NATO-CNR Fellow, and from 1994 to 1996, a Marie Curie Fellow. Since 1996, he has been a tenured Researcher of the FNRS, the Belgian National Funds for Scientific Research, and co-director of IRIDIA, the artificial intelligence laboratory of the ULB. His current research interests include swarm intelligence, swarm robotics, and metaheuristics for discrete optimization. He is the Editor-in-Chief of Swarm Intelligence, and an Associate Editor or member of the Editorial Boards of many journals on computational intelligence and adaptive systems. Dr. Dorigo is a Fellow of the AAAI, EurAI, and IEEE. He was awarded numerous international prizes among which the Marie Curie Excellence Award in 2003, the IEEE Frank Rosenblatt Award in 2015, and the IEEE Evolutionary Computation Pioneer Award, awarded in 2016.

Habilitation Exams: “Case studies of development of verified programs with Dafny”

Posted on

Habilitation exams in the field of Computing Engineering: “Case studies of development of verified programs with Dafny”

Requested by:

João Carlos Pascoal de Faria, PhD

July 7 2022, 14:30, Sala de Atos FEUP

Assessment of the curriculum and the report on the study cycle: “Do Mestrado Integrado à Licenciatura e Mestrado em Engenharia Informática e Computação na FEUP”

July 8 2022, 14:30, Sala de Atos FEUP

Discussion of the summary lesson entitled: “Case studies of development of verified programs with Dafny”

President of the Jury:

– João Bernardo de Sena Esteves Falcão e Cunha, PhD, Full Professor and Dean of the Faculdade de Engenharia da Universidade do Porto.

Members:

– Vasco Manuel Thudichum de Serpa Vasconcelos, PhD, Full Professor at Departamento de Informática da Faculdade de Ciências da Universidade de Lisboa;

– Luís Manuel Marques da Costa Caires, PhD, Full Professor at Departamento de Informática da Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa;

– José Nuno Fonseca Oliveira, PhD, Full Professor at Departamento de Informática da Universidade do Minho;

– Rui Filipe Lima Maranhão de Abreu, PhD, Full Professor at Departamento de Engenharia Informática da Faculdade de Engenharia da Universidade do Porto;

– Pedro Nuno Ferreira da Rosa da Cruz Diniz, PhD, Full Professor at Departamento de Engenharia Informática da Faculdade de Engenharia da Universidade do Porto.

DEI Talks | “A Geographies of born-digital translation: TRANS.MISSION[A.DIALOGUE] as a case study” by Anne Karhio

Posted on

Dr Anne Karhio’s work addresses topics related to contemporary poetry and technology, Irish literature and culture, and literary landscapes in various media environments. After her appointment as Associate Professor in English at the Norway Inland University of Applied Sciences, she is currently based in the National University of Ireland, Galway, as Lecturer in Contemporary English Literature in the School of English and Creative Arts. She is also Associate Professor II in Digital Culture at the University of Bergen, Norway, and has published widely on contemporary Irish poetry, digital literature, and the aesthetics of space and landscape.

“A Geographies of born-digital translation: TRANS.MISSION[A.DIALOGUE] as a case study” will be presented June 27, at I-105, 15:00.

Abstract:

 This presentation addresses the challenges of linguistic, geographical, and cultural translation through the specific case of J.R. Carpenter’s born-digital work TRANS.MISSION[A.DIALOGUE] and its translation from English into Finnish. I will consider how the challenges of linguistic translation from a European to a non-European language are further complicated by the requirements of code, as well as the translation of sociocultural context. Through its focus on technology, mobility, and migration, I suggest, Carpenter’s work invites us to consider the entangled connections between infrastructural geographies and the language of communications technology.

PhD Defense in Digital Media: “Migration as movement – repurposing the voice/interface to explore aspects of human migratory movement through artistic research”

Posted on

Candidate:
Terhi Tuulikki Marttila

Date, Time and place:
June 27, 10:00, Sala de Atos of FEUP

 President:

António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Faculdade de Engenharia da Universidade do Porto.

Members:

Anne Karhio, PhD, Associate Professor, Faculty of education of Inland Norway, University of Applied Sciences;

Manuel José de Freitas Portela, PhD, Full Professor, Faculdade de Letras da Universidade de Coimbra;

Vitor Manuel Pereira Duarte dos Santos, PhD, Assistant Professor, NOVA IMS da Universidade Nova de Lisboa;

José Miguel Santos Araújo Carvalhais Fonseca, Professor Auxiliar da Faculdade de Belas Artes da Universidade do Porto;

Diamantino Rui da Silva Freitas, PhD, Associate Professor, Faculdade de Engenharia da Universidade do Porto (Supervisor).

Abstract:

In this artistic research we start from the idea that digital works can be utilized for imagining and playing with yet impossible realities, for asking questions, and for portraying aspects of life such that we can explore these from a distance. This dissertation consists of three browser-based artworks programmed by myself in HTML, Javascript and CSS. These art experiences unfold on the screen, asking the person to interact with them in order to complete their meanings. The works incorporate, among other things, voice interaction through synthetic speech and speech input, the uses of which form an essential component of the works meanings. Each work is concerned with very different types of questions around migration, but overall, and as a triptych, the works explore what the movement brought about by migration implies from a human standpoint. The themes encompassed extend from exploring perspectives on language, where movement results in linguistic accent which provokes a notion of the Other through external difference (in We cannot take them all), or exploring the movement induced by the tension between our body and our personal needs and desires, but that is governed by (shifting) borders (in Speak out) and finally, at exploring migratory movement through the ambivalent relationship between the here and the there, the simultaneous processes of (re-)rooting and of living with homesickness (in Transplanted). While this research may not depart from clear research questions, it nevertheless arrives at observations about the artistic strategies that emerge when migration is explored through notions of voice/interaction. The works themselves open up a space of contemplation about the respective themes, inviting participation through voice.

Keywords: migration, voice interaction, electronic literature, digital art, artistic research

LGP is back on June 15 for “The Unboxing Edition”

Posted on

Lionesa Business Hub hosts on June 15 the event Linking Great Partners, which takes place throughout the day with a fair space (for demonstration of the products developed), several lectures and networking space. This year’s edition of the event was named “The Unboxing Edition“, as it is the first time that it takes place outside the walls of the University, in order to reinforce the importance of the connection with companies.

There are 24 proto-startups created by about 250 students enrolled in the curricular unit of Project Management Laboratory (LGP), from several courses of the Faculty of Engineering (FEUP) and also involving 5 students from the Faculty of Fine Arts (FBAUP) of the U.Porto, to respond to real problems identified by the 16 partner organizations and to problems identified in the market.

As stated by the European Commissioner for Innovation, Research, Culture, Education and Youth Mariya Gabriel at the launch of the European initiative “Innovation Capacity Building for Higher Education”, universities play a critical role in the development and growth of local and regional innovation ecosystems. By promoting experimentation and the connection between science, technology, culture and art, this educational project at the U.Porto, this year supported by the INVENTHEI project – Innovation and Entrepreneurship in HEIs (http://www.inventhei.eu), fits into the foundations of the European initiative, developing in students the skills that allow them to create innovative solutions that result from a creative and interdisciplinary mentality.

By applying agile software development methods and lean experimentation, student teams have developed several innovative technological solutions, such as AutoRocket+, a rocket navigation simulator, designed for all levels of primary and secondary education, in which students can design and program a rocket with autonomous decision-making capacity, at the request of Visionarium. In this 2022 edition, a solution for the interactive identification of defects in the automobile industry was also designed for the Stellantis Production Centre in Mangualde, and also the app CheapShop, an entrepreneurial project that aims to help choose the best place to do the weekly shopping. There is also an installation that merges art with technology and that has the war in Ukraine as its theme. These are just some examples of the projects that will be demonstrated during the event.

Gil Gonçalves, coordinator of the curricular unit and Professor of the Department of Informatics Engineering of FEUP, highlights that this initiative is essential for “students to understand that the collaborative, entrepreneurial and creative spirit are fundamental ingredients in the innovation and success of any project” and adds that “LGP”, through its teaching-learning model and the links it promotes and enhances between education, research and society, aims to have a systemic impact on the university, contributing to increase the innovation and entrepreneurship capacity of its students, as well as enhancing the contribution of students and the university in the regional innovation ecosystem. ”

For Raul Vidal, Emeritus Professor of the Faculty of Engineering, “by involving students from various curricular spheres and distinct profiles in a collaborative work that instigates critical and creative thinking, the LGP assumes itself as a unique opportunity to develop skills in the areas of project management, teamwork, interaction with clients, marketing, communication, and so many other valences that make our students future professionals with a truly differentiated profile and prepare them to be future leaders.”

The Linking Great Partners event can be followed on the event’s social networks and Youtube channel:

Linkedin, Instagram, Facebook, Youtube

PhD Defense in Informatics Engineering: ”An Agent-based Approach to Design Decentralized Cloud-Edge Data Analysis in Cyber-Physical System”

Posted on

Candidate:
Jonas Felipe Pereira de Queiroz

Date, Time and place:
June 14, 14:00, Sala de Atos of FEUP

President:

Carlos Manuel Milheiro de Oliveira Pinto Soares, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Members:

Luís Filipe Santos Gomes, PhD, Associate Professor with Habilitation, Departamento de Engenharia Electrotécnica e de Computadores, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa;

Maria Goreti Carvalho Marreiros, PhD, Coordinating Professor with Habilitation, Departamento de Engenharia Informática, Instituto Superior de Engenharia do Porto;

Paulo Jorge Pinto Leitão, PhD, Full Professor, Departamento de Engenharia Eléctrica, Instituto Politécnico de Bragança (Supervisor);

Rosaldo José Fernandes Rossetti, PhD, Associate Professor, Departamento de Engenharia Informática, Faculdade de Engenharia da Universidade do Porto.

Abstract:

The 4th industrial revolution is characterized by the digitization of industrial environments, based on the use of Internet of Things, Cloud/Edge Computing and Artificial Intelligence technologies. This technological advances are pushed by the ever-changing market that besides posing new business challenges, further increase the already existing complexity and related issues faced by industries at the operational environments. In this context, Cyber-Physical Systems (CPS) have been considered the new paradigm to develop the next generation of intelligent and distributed industrial automation systems that can achieve higher levels of flexibility and dynamic adaptation. Although data analysis has shown to be a key enabler of industrial CPS in the development of smart machines and products, the traditional Cloud-centric solutions are not suitable to attend the data and time-sensitive requirements. Aiming to cope with that, Edge Computing has been adopted to enable the data processing capabilities at or close to the physical components, complementing the Cloud solutions. However, defining what data analysis capabilities should be deployed along Cloud-Edge computational layers is not a straightforward task. Motivated by this challenge, this work proposes a conceptual framework that defines a modular agent-based architecture to design and develop cyber-physical components, together with a general guideline to support the system engineers to evaluate and determine the most suitable computing layer to deploy a given data analysis task. The proposed framework was implemented and evaluated considering some experiments based on a smart machine CPS testbed, and different scenarios that illustrate the benefits of distributing the data analysis capabilities along Cloud-Edge layers. The modular structure of the agent-based cyber-physical component architecture shown to be suitable, enabling to easily configure and distribute data analysis tasks along the CPS components and their deployment in the different computing layers, also providing a seamless and transparent interaction between the components. In addition, the proposed guideline and the Fuzzy Logic decision-making systems were used to recommend, in a less ad-hoc manner, the most suitable layer to deploy three data analysis tasks identified in the case study. 

Keywords: Cyber-Physical Systems, Data Analysis, Multi-Agent Systems, Edge Computing

XIX Conference on Information Science – 27th June 2022

Posted on

“JCI – Jornadas de Ciência da Informação” are an annual event promoted and organized by the students of the Bachelor and Master Degrees in Information Science (LCI and MCI), taught in partnership by the Faculty of Arts and the Faculty of Engineering of the University of Porto (FLUP and FEUP). Being a reference in the scientific community and among professionals in the area, this event has been an opportunity for guests and participants from the industry, public institutions and academia to interact and debate current issues in the field of Information and its management.

In its 19th edition, the JCI will take place at the FLUP’s Amphitheatre, on June 27th, between 9am and 6pm. Under debate will be “THE ROLE OF INFORMATION SCIENCE FOR DIGITAL TRANSFORMATION”.

Registration is free but compulsory (given the limited number of places available).

Follow the event on its social networks, Instagram, Facebook and Linkedin.

PhD Defense in Digital Media: “Modular Architecture for 3D Game Environment Art with Photogrammetry”

Posted on

Candidate:
Nataska Statham

 Date, Time and place:
June 22, 09:00, remotely with streaming at: https://www.youtube.com/channel/UCvsg2ymeaHLRLbsGt67JmKw

 President:

Doutor António Fernando Vasconcelos Cunha Castro Coelho, Associate Professor with Habilitation, Departamento de Engenharia Informática of Faculdade de Engenharia, Universidade do Porto.

Members:

PhD Richard A. Bartle, Senior Lecturer and Honorary Professor of Computer Game Design at the University of Essex, UK;

PhD Andrija Bernik, Assistant Professor at the Department of Multimedia, Design and Application, University North in Varazdin, Croácia;

PhD Rui Pedro da Silva Nóbrega, Assistant Professor, Departamento de Informática of Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa;

PhD Luís Filipe Pinto de Almeida Teixeira, Assistant Professor, Departamento de Engenharia Informática of Faculdade de Engenharia, Universidade do Porto;

PhD João Tiago Pinheiro Neto Jacob, Technical Product Owner at Mindera Gaming (Supervisor).

Abstract

 Photogrammetry is a technology increasingly used in games for modelling 3D characters and natural environments, with the potential of time-efficient generation of realistic meshes with a higher level of detail than is normally achieved via hand-modelling. In architectural environments, however, although textures are photoscanned, meshes are still hand-modelled. A key challenge is that architecture for games tends to rely on modular meshes, which require high precision and standardisation, whereas photoscans of real-world architecture tend to output irregular meshes that are hard to conform to modularity. This investigation aims to address this lack of integration with a focus on high granularity modular architecture for 1st and 3rd person 3D games. It starts with a review of 3D game graphics production and modular architectural assets for games, as well as the integration of photogrammetry in the creation of 3D assets for games and for 3D environment art in particular. This is followed by a theoretical contribution, consolidating the principles of modular architecture for games within the game development lifecycle. Next, it identifies the inherent incompatibilities preventing the integration of photogrammetry with modular architecture for games and postulates solutions, implemented and tested via a series of controlled experiments using commonly available software. It concludes that integration is possible, but that a manual process is presently required due to the lack of tools designed to conform detailed surfaces to the profile of standardised reference meshes. The investigation proposes a workflow to achieve sectional modularity of architectural photoscans via tileable borders to which mesh variations can be integrated via modular swapping. It proposes a modified game development lifecycle with longer pre-production and potentially multiple photoscanning sessions to incorporate architectural photoscans into modular game environment art production. Via this workflow, a wide range of types of photoscanned architectural surfaces and types of geometry were standardised into the requirements optimal for modular meshes for 3D environment art, indicating its viability as a workflow for game development in general.

 Keywords: 3D environment art, game development lifecycle, level design, modular architecture, photogrammetry.

PhD Defense in Digital Media: ”Literacia visual e comunicação”

Posted on

Candidate:
Jorge Luís Pacheco Barcelos

Date, Time and place:
May 31,10:30, remotely with streaming at: https://www.youtube.com/channel/UCvsg2ymeaHLRLbsGt67JmKw

President of the jury:
PhD Jorge Manuel Pinho de Sousa, Full Professor at Faculdade de Engenharia of Universidade do Porto

Members:
PhD Paulo Nuno Vicente, Assistant Professor at Departamento de Ciências da Comunicação of Faculdade de Ciências Sociais e Humanas of Universidade Nova de Lisboa;

PhD Luís Francisco Mendes Gabriel Pedro, Assistant Professor at Departamento de Comunicação e Arte of Universidade de Aveiro;

PhD Maria da Conceição Gonçalves Costa, Associate Professor at Escola de Comunicação, Arquitetura, Artes e Tecnologias da Informação of Universidade Lusófona;

PhD José Manuel Pereira Azevedo, Associate Professor at Departamento de Ciências da Comunicação e da Informação of Faculdade de Letras of Universidade do Porto (Supervisor);

PhD António Fernando Vasconcelos Cunha Castro Coelho, Associate Professor at Departamento de Engenharia Informática of Faculdade de Engenharia of Universidade do Porto.

Abstract:

This thesis seeks to verify the degree of visual literacy that individuals in undergraduate and graduate studies at the Universities of Porto and Paraíba Federal, in the courses of design, multimedia, digital media, engineering, communication, have when interpreting an image. These interpretations present three important dimensions such as affective, compositional, and critical when analyzing an image, be it a painting, a photograph, a work of art, or an audiovisual piece, materialized in a verbal text. The theoretical framework of this research is given by reading a corpus of visual literacy such as Dondis (1974), Housen (1983), Braden and Bacca (1991), Arnheim (2001), Averignou and Pettersson (2011), Duchak (2014), Serafini (2014), Brumberger (2019), Kedra (2019), Supsakova (2020); and on image with Kress and Van Leeuwen (1996), Mirzoeff (1999), Cartwright & Sturken (2001), Villafañe (2006), and Mitchel (2009); and communication with Hall (2001), Berger (2000), Baylen&D’alba (2005), Horkenheimer & Adorno (2006), Santaella & Noth (2020), and in methodologies with Bloom (1956); Leung (2000); Amantes&Borges (2008), Hassan (2011), Biggs &Collins (2014), Rautiainen&Jappinen (2017), Arneson&Offerdahl (20018), Fernades (2019). This research has developed the Multimodal Assessment Method of Visual Literacy (MAMLV) that uses both quantitative and qualitative methodologies, with the qualitative aspect assisting in providing greater detail of the interpretive experience. The data collection instrument was a semi-structured interview that allows the interviewee to vent their interpretive thoughts, with minimal interference from the interviewer. These statements were collected and classified through the use of a coding manual that aids in classification. The statements were classified into categories of domains and subcategories, the topics. Depending on the number of statements, the individual belongs to a certain level of visual literacy. There are three levels of visual literacy, although the Multimodal Assessment Method of Visual Literacy (MAMLV) considers intermediate levels between each level. Thus, it can be observed that individuals despite being immersed in a visual world still present a low degree of visual literacy, as they do not have the skills and competencies fully developed to know the communicative interactions between the visual elements, their design principles and the visual grammar that are contained in an image. Although there are also individuals with a high degree of visual literacy. The findings suggest that this happens due to the lack of teaching curricula that contemplate visual and media literacy in the different levels of primary, secondary and university education, considering the curricular structures of the courses involved, and the results found, we can conclude that the inclusion of visual literacy in systematized teaching is of paramount importance for the formation of fully visually literate individuals.

Keywords: Visual Literacy; Image; Communication, Methodology