“Signal Processing in the AI era” was the tagline of this year’s 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., “Designing Transformer Networks for Sparse Recovery of Sequential Data Using Deep Unfolding” (https://ieeexplore.ieee.org/abstract/document/10094712)
- Yang X. et al., “Relevance Propagation through Deep Conditional Random Fields” (https://ieeexplore.ieee.org/abstract/document/10095075)
- Stergiou A. et al., “Play it back: Iterative attention for audio recognition” (https://ieeexplore.ieee.org/abstract/document/10096532, developed at the University of Bristol)
Exciting news for the start of this academic year in the team of Prof. Nikos Deligiannis: a prestigious FWO grant has been awarded to 2nd year PhD candidate Brent de Weerdt. Brent will start a new research project with a goal in mind: merging optimization algorithms and deep learning algorithms, to create more efficient models for image, video processing and computer vision. Additionally, PhD candidates Esther Rodrigo and Boris Joukovsky successfully passed the 2 years evaluation mark for their FWO grants. Their respective research on explainable graph deep learning on video deep learning have been consequently extended.
On October 13th 2023 at 15.30, Johan Hoang-Dung Nguyen will defend his PhD entitled “HIGH-EFFICIENCY TRANSMITTERS FOR 5G COMMUNICATION AT MMWAVE FREQUENCIES”.
Everybody is invited to attend the presentation at the Room D.2.01, or digitally via this link.
The fifth generation (5G) wireless communication technology started its deployment in 2019 to meet the increasing global demands for highspeed connectivity. The radio frequency spectrum will be progressively expanded to millimeter-wave ranges to meet the growing demand for mobile broadband applications. 5G targets wireless data rates of up to 10 Gbit/s. A broad deployment of applications that are based on these high data rates is only possible if the power consumption of the transmit and receive part does not grow out of hand. In a mm-wave transceiver, the transmit part often consumes most of the energy. This doctoral work focuses on the design and calibration of digital polar transmit architectures operating at mm-wave frequencies, which could bring a high data rate for less power consumption. In a polar transmitter, the signal is split in amplitude path and a phase path. The amplitude is modulated using a so-called RF-DAC, while the phase is modulated via phase modulators.
One big design achievement of this Ph.D. work is the 60-GHz digital polar chip in 28-nm Bulk CMOS. Compared to earlier digital polar transmitters operating around 60GHz, the RF-DAC used here does not suffer from leakage from disabled cells. In this way, it is possible to modulate with a higher modulation depth. Two leakage reduction techniques have been suggested from which a patent is issued: the dynamic driver and the inverter switch. The phase modulator is a Cartesian one, using a 90 degrees hybrid, that splits the input signal into an in-phase (I) and a quadrature (Q) component, which are weighted with a very linear variable gain, made with variable-gain amplifiers (VGAs). Thanks to this phase modulator and to the leakage-mitigation improvements, this chipachieves a raw data rate of 10.52 Gb/s using a 64-QAM modulation. The on-chip impedance matching is accomplished with transformers. In this work, a design flow based on ABCD matrices has been developed to speed up the design of these transformers. The same framework is later used to design a 140-GHz transceiver front-end with a transmit/receive switch.
Synchronization between the amplitude path and the phase path is vital in digital polar architectures. To facilitate and speed up this synchronization, a non-iterative method is proposed here. This strategy is then extended to retrieve and compensate AM-AM and AM-PM distortion from the VGAs. It is also possible to estimate the IQ imbalance of the hybrid. Higher bandwidths can be achieved by using the method to calculate an equalization filter for the phase samples.
A full immersive experience of Augmented Reality for neurosurgical planning and real-time intervention, demonstrated by Taylor on the FARI immersive CAVE during the Agoria HealthTech roundtable event June 17th , 2024.
4D CT scanners add the dimension of time to three-dimensional images and visualise the movement of the heart in detail. The imec.icon project DIASTOLE, involving VUB, UZ Brussel and imec, is paving the way to safely implement 4D scans in heart surgery.
Researchers from the radiology department of VUB-UZ Brussel developed a model to calculate the radiation dose of 4D scans on the skin, and immediately applied it to draw up a safe protocol. For a usable 4D scan, on the one hand the quality has to be sufficient, on the other hand you want to avoid the radiation dose being too high at certain places on the body. Unlike classic CT scans, a 4D scan repeatedly irradiates the same region of the body, so we need to specifically monitor the dose to the skin.
https://press.vub.ac.be/cardiology-prepared-for-the-fourth-dimension
…and ETRO.RDI colleagues have brand new stands.
- Acoustic Painting
- An Urban Climate Model using AI
- Crypto Escape Room
- Discover what light says about you!
Do not miss the opportunity to visit us from 13th – 15th of October
@ Tour & Taxis, sheds 1&2, BrusselsÂ
Front cover of the June issue of Neurosurgery for the joint research of Taylor Frantz with UZBrussels! High-Accuracy Augmented Reality Guidance for Intracranial Drain Placement Using a Standalone Head-Worn Navigation System: First-in-Human Results
Article link : https://journals.lww.com/neurosurgery/fulltext/2025/06000/high_accuracy_augmented_reality_guidance_for.8.aspx
Journal issue link:Â https://journals.lww.com/neurosurgery/pages/currenttoc.aspx
