VUB, ULB and the Brussels Capital Region government announce the launch of a new Artificial Intelligence for the Common Good Institute during the Belgian AI Week of AI4Belgium.
Today, Annemie Schaus and Caroline Pauwels, respectively rectors of ULB and VUB, were proud to announce the launch of FARI the Artificial Intelligence institute for the Common Good. It was also endorsed by the Brussels Capital Region ministers Barbara Trachte and Bernard Clerfayt.

FARI is a unique structure that aims at gathering over 300 researchers in AI (amongst others the ETRO dept) and associated disciplines, around projects that could benefit the general interest. The institute will promote research on trustworthy, transparent and explainable artificial intelligence. It will also aim at helping the Brussels Region and its inhabitants address some of the challenges they face in various domains. FARI researchers will provide ideas and contribute to projects on transportation, sustainable development, healthcare services, civic consultations on AI and algorithms. Its projects will actively involve citizens and reinforce education on AI and its impacts in the region.

The institute aims at creating a bridge between AI experts, citizens, companies and local organizations. It will have three hubs: an Research & Innovation Hub, a Think Tank on AI, Data and Society, and an AI Test and Experience Hub.

https://today.vub.be/en/article/fari-a-new-artificial-intelligence-institute-in-brussels

https://fari.brussels/

Tripat Kaur followed the Masters in Applied Computer Science in 2020. His interest in Computer Science goes back to his school days. Not only the theory classes were very interesting, he also enjoyed the practical assignments to the fullest. His first-ever programming language C++. was a thrill. He made his first program on the blue screen of Turbo to get a ‘Hello Tripat’ output on the black screen. Ever since programming has been his passion.

The MACS program started teaching from a very basic level. Even if one had no computer science background, it was not a problem because everything is taught from scratch, but the study load in the first year was very high. Tripat enjoyed Advanced Programming Concepts the most by far. It helped him improve his programming skills a lot. Tripat studied during the corona year and his first year was through remote teaching. It was very different from what he had imagined. Even though being in different countries, his fellow students made sure that he did not have to worry about the time differences. They always adjusted with him making it fun to work on team projects. Tripat is now a more confident person as his horizons have widened. Not only technically but even his soft skills have improved thanks to this program. Tripat says: Never be afraid to dream. Word hard and believe in yourself, things will fall into place. His ideal future is to be completely independent and settled not only in terms of finances but in terms of happiness and confidence. Also, being able to support his family the way they have till now.

Zamzam won the award for the third place in the Best Student Paper category at the World Congress on Medical Informatics in Sydney for the paper “Baseline Survey on Referrals and Healthcare Provider Needs in View for an Electronic Referral System” authored by Zamzam Kalume, Bart Jansen, Marc Nyssen, Jan Cornelis and Frank Verbeke .

On October 3rd 2024 at 16:00, Michiel Dhont will defend their PhD entitled “UNSUPERVISED ANALYTICS FOR MULTI-SOURCE TIME SERIES DATA”.

Everybody is invited to attend the presentation in room I.2.02 or online via this link.

There has been an explosion of impressive success stories recently with deep learning (DL) approaches in various fields such as natural language processing, computer vision, healthcare, and robotics. The advent of transformers has further amplified the capabilities of DL models to understand complex patterns, establishing them as a cornerstone of modern AI advancements across a broad spectrum of applications. Initially, transformers revolutionised large language models like GPT-4 and BERT, enabling them to process and generate human-like text with remarkable coherence and accuracy. Now, their impressive performance is also being demonstrated in other domains, extending their impact. Given sufficient high-quality labelled data and computational resources, DL models are able to achieve an accuracy that were previously unattainable.

Unfortunately, most of the real-world application contexts generate datasets which significantly diverge from the idealised benchmark datasets used to validate novel AI methodologies. Real-world data is typically characterised with presence of noise, missing values, complicated parameter names, different data types, lack of ground-truth, context-dependent features, etc. The latter makes it very challenging to immediately dive into any AI model application since it is often not clear which modelling paradigm best suit the problem at hand. This PhD research is built around the conception and validation of a heuristic data analytics methodology with the aim to benefit maximum from the different facets, while mitigating the imperfections, of real-world datasets.

Nowadays, most of the available datasets originating from industrial activities are composed of multitude of different parameters. The inherent multi-source nature of such datasets makes it impossible to directly integrate different data types without information loss. To address this challenge, a multi-view data integration approach has been devised as a part of this PhD, which identifies and considers different data views explicitly, allowing to fully harness the richness of heterogeneous datasets while retaining all relevant information.

The ongoing trend of increasingly more data being captured, goes parallel with an increasing complexity of extracting valuable insights from it. For instance, the remote monitoring of infrastructures (e.g., roads and power supplies) typically generates complex spatio-temporal data streams captured at high sampling rate across different locations. Combining and making sense of such data streams is not trivial. In this PhD research, a spatio-temporal profiling methodology is proposed, allowing to uncover insightful spatial patterns and dependencies while taking full advantage of the temporal dimension. Additionally, the exciting domain of visual analytics has been explored, resulting into the conception of several novel visualisation approaches, blending advanced visualisation with intelligent analysis to effectively reveal key iinsights.

By far, the hardest challenge associated with the analysis of real-world data is the lack of ground truth, which limits the choice of learning paradigms to only unsupervised ones. In this PhD research, a novel modelling framework is conceived, capable of extracting semantically interpretable states from unlabelled data. The latter facilitates a better understanding of system behaviour in terms of state transitions and allows to convert the unsupervised data modelling problem into a supervised one. Several different neural and neuro-symbolic forecasting workflows have been proposed for this purpose

Gaurav is one of the two winners of 2020-21 International Student Circuit Contest by IEEE Solid-state Circuits society. Gaurav solved the problem below:
Provide an example of an amplifier where, despite the presence of a positive feedback, the system cannot latch since the topology guarantees always a positive gain margin (regardless the components values or mismatches)? In your answer please clarify the expression of the loop gain and show that there is actually a positive feedback but the magnitude can never exceed one.

On October 6th 2025 at 16:00, Ran Zhao will defend their PhD entitled “DEEP LEARNING-BASED HUMAN POSTURE NORMALIZATION AND AUTOMATIC ANTHROPOMETRIC MEASUREMENT”.

Everybody is invited to attend the presentation in room D.2.01 or online via this link.

Accurate and user-friendly anthropometric measurement remains a major challenge in computer vision, as existing approaches typically require controlled scanning conditions, standard postures, or unclothed bodies. These constraints limit their usability in practical scenarios.

This thesis proposes a sequence of deep learning-based solutions to overcome these limitations. We first introduce OrienNormNet, an iterative network for robust orientation normalization, ensuring that scans are consistently aligned without manual preprocessing. Building on this, PoseNormNet is presented as the first posture normalization framework that transforms arbitrarily posed scans into a canonical T-pose while preserving identity details, removing the need for skeleton rigging. Next, W2H-Net demonstrates the feasibility of directly estimating the waist-to-hip ratio from partial dressed scans, showing that reliable indicators can be derived even from incomplete data. Finally, MeasureXpert provides a breakthrough toward real-world usability: it enables automatic extraction of anthropometric measurements from only two unregistered, partial, and clothed scans acquired in arbitrary poses.

To support these developments, the BWM dataset was synthesized for training, validation, and evaluation. Comprehensive experiments on both synthetic and real-world data confirm the effectiveness and robustness of the proposed methods. Collectively, the contributions progressively address key challenges related to cost, posture, and clothing, moving the field closer to practical, flexible, and accessible body measurement solutions.

The algorithms presented in this thesis have been disseminated through prestigious journals and conferences, demonstrating a modest yet meaningful impact on both academic research and industrial applications.