โSignal Processing in the AI eraโ was the tagline of this yearโs IEEE International Conference on Acoustics, Speech and Signal Processing, taking place in Rhodes, Greece.
In this context, Brent de Weerdt, Xiangyu Yang, Boris Joukovsky, Alex Stergiou and Nikos Deligiannis presented ETRO’s research during poster sessions and oral presentations, with novel ways to process and understand graph, video, and audio data. Nikos Deligiannis chaired a session on Graph Deep Learning, attended the IEEE T-IP Editorial Board Meeting, and had the opportunity to meet with collaborators from the VUB-Duke-Ugent-UCL joint lab.
Featured articles:
- De Weerdt, B. et al., โDesigning Transformer Networks for Sparse Recovery of Sequential Data Using Deep Unfoldingโ (https://ieeexplore.ieee.org/abstract/document/10094712)
- Yang X. et al., โRelevance Propagation through Deep Conditional Random Fieldsโ (https://ieeexplore.ieee.org/abstract/document/10095075)
- Stergiou A. et al., โPlay it back: Iterative attention for audio recognitionโ (https://ieeexplore.ieee.org/abstract/document/10096532, developed at the University of Bristol)
Researchers at ETRO VUB have developed the ๐ง๐ฟ๐ฎ๐ป๐๐ถ๐ฒ๐ป๐ ๐ฅ๐ฎ๐ฑ๐ฎ๐ฟ ๐ ๐ฒ๐๐ต๐ผ๐ฑ (๐ง๐ฅ๐ ), a non-invasive tool to visualize what’s hidden inside our buildings. TRM can:
โ
Offer a clear picture of insulation in walls
โ
Identify reinforcement types inside concrete pillars
โ
Determine moisture levels in walls
โ
Conduct year-round thermal assessments
โ
Monitor real-time carbon uptake in building materials
The team is now seeking partners to help bring this innovation to the market and transition the construction industry toward a more sustainable future.
๐ก Interested in a partnership?
Join the pitch session by Prof. Johan Stiens at the Klimaat Parlement ๐ถ๐ป ๐๐ถ๐บ๐ฏ๐๐ฟ๐ด ๐ผ๐ป ๐ญ๐ต ๐ฆ๐ฒ๐ฝ๐๐ฒ๐บ๐ฏ๐ฒ๐ฟ ๐ฎ๐ฌ๐ฎ๐ฑ to learn more.
You can also contact him directly at jstiens@etrovub.be.
๐ Read all the details here: https://lnkd.in/exmkJ7CU
Ali Pourkazemi, Ashkan Zarghami Iliya Hakani
Loris Giordano got the best student paper award at the AMAI workshop of MICCAI 2025 for the paper “A modular deep-learning pipeline for automated aorta characterization on CT”, co-authored by Loris Giordano, Jakub Ceranka, Selene De Sutter, Kaoru Tanaka, Gert Van Gompel, Tom Lenaerts, and Jef Vandemeulebroucke.
ETRO’s Peter Schelkens has put his shoulders under the new Spin-off Swave Photonics, an innovator in Holographic eXtended Reality (HXR) technology. It is a Spin-off of IMEC and VUB.
โOur vision is to help build the fundamental holographic technology to bring the metaverse to life and work,โ saidย Theodore Marescaux, CEO and founder, Swave Photonics. โSwaveโs HXR gigapixel technology will forever change the way we see and experience displayed still images, videos and live imaging. True, lifelike and immersive metaverse experiences powered by Swave technology are poised to replace every AR/VR display and headset to the point where virtual, augmented or eXtended reality is practically indistinguishable from the real world.โ
โWe are convinced that Swave can bring to the market a fundamental technology we have been developing for more than five years through substantial R&D programs and imec investments,โ saidย Luc Van den hove, president and CEO of imec. โImec has a strong track record of innovation and productization that can scale across a wide range of applications. We are committed to make Swave a success and have great confidence that with their extensive patent portfolio and continued support of our teams and ecosystem, Swave can become one of the biggest disruptors for immersive 3D displays and a key accelerator for applications like the metaverse.โ
Two extra assistants join ETRO: Joris Lievens and Jan Cornelis (electronic circuits and instrumentation) – Prototype PCB manufacturing facility. Bulky instruments based on 74xx MSI ICs are designed: e.g. calculator, noise generator, datalogger with multipen printer, โฆ
- The lab receives the MC6800 development kit – the logic state analyser, was the mostly used development instrument, followed by programming in assembler. The system was interfaced to a mechanical teletype.
- First thesis work in microelectronics technology on CCD-MNOS combination. Roger Vounckx join the lab.
- An analogue bucket brigade system is built with discrete components.
- Worldwide first BSPM measurement system with 128 channels based on MSI ICs.
- Marc Nyssen joins the lab (August 1975).
- New instrument designs – Digital correlator and Histogram measurement system, Fourier transformer.
- CDC central ULB-VUB computer facility exclusively for numerical calculus, with punch card readers as interface; FORTRAN is the dominating programming language.
On May 27th 2024 at 16:00, Yifei Da will defend their PhD entitled โDATA-DRIVEN CAUSAL MODELLING FOR DE-BIASING SENTIMENT ANALYSIS MODELS AND MULTIVARIATE STOCK PRICE MOVEMENT PREDICTIONโ.
Everybody is invited to attend the presentation in room I.0.01, or digitally viaย this link.
In this thesis, we address the stock price movement prediction problem by investigating the interdependencies between sentiments from financial news and international stock markets in stock forecasting. To provide reliable sentiment analysis results, especially to reduce bias, we studied sentiment analysis methods and detected, evaluated, and mitigated bias that was picked up on and amplified by large pre-trained models. To retrieve intra- and inter-market interdependencies, we adopt the Transfer Entropy theory to detect and incorporate the information flow between financial news sentiment and the dynamics of the stock markets. We contribute to these two sub-tasks by (i) proposing a new method for debiasing sentiment analysis models that leverages the causal mediation analysis to identify the parts of the model primarily responsible for the bias and apply targeted counterfactual training for model debiasing. Furthermore, (ii) a causal-enhanced multi-modality model for multivariate stock price movement prediction is proposed based on establishing an accurate information flow propagation between stocks and sentiments. To repeatedly validate the feasibility, the Dow Jones Industrial Average indexes of 13 countries and daily financial news data from the New York Times are used in stock Price and Return forecasting.