“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)
Are you interested in taking part in our research survey on the topic of deepfakes detection, and become a contributor in the creation of a new human perception dataset?
We invite you to visit our new website http://qxviz.ai and answer a short and fun survey to test your skills at identifying fake human faces.
Despite the great success of AI models to detect deep fakes, it remains difficult to explain how these models perceive the content of the images they are presented with. To this end, our website allows you to draw your reasoning to why you think an image is fake. You will discover if visual explanations generated by existing explainable AI techniques match with your own perception.
Visit http://qxviz.ai/ Â and help us advance towards more transparent and human-friendly artificial intelligence!Â
Financed by IMEC, CAD for VLSI circuits is launched at ETRO.
On March 18th 2024 at 17::00, Pieter Boonen will defend their PhD entitled “4D-CT for Detailed Diagnosis of Peripheral Arterial Disease and Diabetic Foot Ulcers. Is it worth our time?”.
Everybody is invited to attend the presentation at the Auditorium Piet Brouwer (Faculty of Medicine and Pharmacy), or digitally via this link.
 Peripheral arterial disease affects over 230 million people globally, causing arterial narrowing in the legs which can lead to a reduced blood flow and tissue damage. When combined with poorly managed diabetes, it can lead to serious issues like diabetic foot ulcers that may require amputation if untreated.
The current imaging methods, such as computed tomography angiography and magnetic resonance angiography lack hemodynamic information on the blood flow and tissue perfusion which can be crucial for diagnosing vascular disease and treatment monitoring.
This PhD thesis explores the application of a new technique called 4D-CT for diagnosing peripheral arterial disease and diabetic foot ulcers. By capturing multiple CT volumes over the same structure, the injected contrast bolus can be tracked through arteries and tissue.
Through a series of phantom and clinical studies, this thesis explored the feasibility of applying 4D-CT to measure and visualise the arterial blood flow and to examine the effect of peripheral arterial disease on the blood flow. An automated image processing pipeline was developed to segment arteries and tissues, facilitating the quantification of blood flow. The results of this thesis highlight the potential of 4D-CT in the diagnosis of vascular disease.
Pratap Renukaswamy presented a live demo of his FMCW radar at ISSCC 2023
Dear colleagues,
We’re pleased to announce that the AI4WCM research team will be hosting a presentation in the Marconi meeting room at PL9.2 on the 16th of October from 13:30 to 14:30. During this one-hour session, each team member will share their latest research and findings in a relaxed and informative manner. It’s a great opportunity to stay updated on the work happening within our group.
Please mark your calendars and keep an eye out for more details. We look forward to sharing our research progress with you!
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.