13Jan2026
PhD Students Seminar
This year, IEETA is starting a new initiative, a cycle of Seminars of our PhD students. The goal of these seminars is to promote the research developed within IEETA, while providing the opportunity for students to share their work in a supportive environment. Through these sessions, participants will receive constructive feedback both from peers and […]
15Dec2025
-
15Dec2025
Beyond the Lab: Federated, Interpretable Trees That Don’t Leak Your Data
A privacy-aware framework for Random Forests & XGBoost in distributed settings, built for practitioners who need auditability, not black boxes. Most federated learning toolkits focus on deep nets and often overlook interpretability. If you work with regulated data (e.g. healthcare or finance), that’s a non-starter. This work delivers a federated, PySyft-based approach for tree models […]
11Dec2025
-
11Dec2025
IEETA successfully concludes the “Connected Home for Healthy Aging” B5G pilot within IMAGINE-B5G Open Call 2
IEETA (University of Aveiro, Portugal) successfully completed its participation in IMAGINE-B5G Open Call 2, developing and testing solutions for healthy aging at home at the Instituto de Telecomunicações (Aveiro) facility over a 9-month period. In the scope of the “eHealth” vertical, trials demonstrated a virtual gym and a solution for physical activity monitoring based on […]
11Dec2025
UA-Bosch Thermotechnology Collaboration Wins Bosch International User Experience Award
A Bosch Thermotechnology team has been awarded an international Bosch prize on User Experience (UX). The winning project was developed in close collaboration with researchers from IEETA – Institute of Electronic and Computer Engineering of Aveiro, within the framework of the ILLIANCE agenda.
27Nov2025
-
27Nov2025
Seminar: Towards Improved Privacy in Service Environments
The concept of privacy in the digital age is subjective and multifaceted, presenting significant challenges due to diverse interpretations and inadequate interfaces for comprehending risks. This thesis introduces the DevPrivOps methodology, based on privacy quantification frameworks to ensure robust compliance throughout the SDLC. As part of this effort, we evaluated the effectiveness of Differential Privacy […]
24Nov2025
-
24Nov2025
Beyond the Lab: Informed decision-making strategy for resampling in pain assessment
In many real-world classification problems, datasets exhibit a skewed class distribution, known as class imbalance, where one class has significantly more samples than another. Machine learning models trained on imbalanced data tend to favor the class with more samples. This bias toward the majority class leads to poor classification performance on rare but important cases, […]
13Nov2025
-
13Nov2025
IEETA researcher receives the SPE Award
Ana Martins, researcher at IEETA, has been awarded the @ 2024 SPE – Sociedade Portuguesa de Estatística Award. This award recognizes her contributions to developments in the field of statistical models for time series of counts. Ana received this award at the 2025 SPE Congress (22-25 October) organized by University of Algarve
13Nov2025
-
13Nov2025
IEETA hosted RECPAD2025 at the University of Aveiro
On October 31st, IEETA hosted the 31st Portuguese Conference on Pattern Recognition (RECPAD2025, https://sites.google.com/view/recpad2025/home), promoted by the Portuguese Association for Pattern Recognition (APRP, https://aprp.pt). It was an event aimed to foster cooperation, knowledge exchange and networking within the scientific community in the fields of Pattern Recognition, Image Analysis and Processing, Artificial Intelligence, Soft Computing and […]
13Nov2025
-
13Nov2025
Seminar by Mihaela van der Schaar – University of Cambridge, UK
Title: Discovering New Science using Agentic Collaborative Networks Abstract: This presentation will explore how AI agents can evolve from narrow tools of automation into genies – adaptive and multi-capable collaborators that expand human creativity and agency. This talk will outline the essential capabilities these agents must develop and present 101 fundamental ML questions that must […]
13Nov2025
-
13Nov2025
Seminar by Armando J. Pinho
Title: Data Compression and Large Language Models – University of Aveiro, PT Abstract: The use of large language models (LLMs) has seen a meteoric rise since the introduction of the transformer neural network architecture. In one of its configurations, known as decoder-only, a transformer operates as a next token (or symbol) predictor. Because prediction is […]