Winners of the DSSC XS package
- Achieving robustness to distribution shifts in instance segmentation of time-lapse microscopy: A brain-inspired inhibition approach (Dr. George Azzopardi - BI; Dr. Andreas Milias Argeitis - GBB)
The aim of this project is to develop instance segmentation algorithms for the delineation of budding yeast cells in brightfield time-lapse microscopy images. This is important for the automatic extraction of cellular readouts in high volumes of imaging data. The main scientific challenge is the high variability in brightfield imaging, especially across labs and imaging platforms (microfluidic chips, agarose pads, glass slides). The proposed methodology will integrate a brain-inspired inhibition mechanism in instance segmentation convolutional neural networks and evaluate them in terms of generalization ability on various real brightfield imaging data sets from international labs. More specifically, we will develop a computational model of the push-pull inhibition phenomenon, which is known to contribute to generalization in the mammalian brain, and integrate with state-of-the-art segmentation networks (e.g. Mask R-CNN).
- Visual analysis of dis/misinformation and hateful meme (Dr. Jiapan Guo - BI; Dr. Kun He - Faculty of Arts, Media Studies)
The widespread dissemination of mis/disinformation and hate speech through digital media has worsened the already uncertain and turbulent state of the world, especially during the COVID-19 pandemic and the Ukraine-Russia war. Although extensive research has been conducted to detect and analyze text-based mis/disinformation, there is a lack of research on the spread and evolution of visual mis/disinformation and hateful memes. Compared to textual mis/disinformation, visual mis/disinformation is more effective in evoking emotions and influencing people's attitudes, which further fuels social division and polarization. This project aims to address this gap by analyzing the diffusion and evolution of visual mis/disinformation and hateful memes on digital platforms, such as 4chan and Twitter. The project will employ various approaches that combine human expert knowledge with the processing power of computers, utilizing supervised and unsupervised machine learning algorithms.
- Machine Learning to Optimize Dense Wave Energy Converter Arrays (Prof. Kerstin Bunte - BI, Prof. Bart Besselink - BI, Prof. Antonis Vakis - ENTEG)
Last modified: | 16 March 2023 11.31 a.m. |
More news
-
16 April 2024
UG signs Barcelona Declaration on Open Research Information
In a significant stride toward advancing responsible research assessment and open science, the University of Groningen has officially signed the Barcelona Declaration on Open Research Information.
-
02 April 2024
Flying on wood dust
Every two weeks, UG Makers puts the spotlight on a researcher who has created something tangible, ranging from homemade measuring equipment for academic research to small or larger products that can change our daily lives. That is how UG...
-
18 March 2024
VentureLab North helps researchers to develop succesful startups
It has happened to many researchers. While working, you suddenly ask yourself: would this not be incredibly useful for people outside of my own research discipline? There are many ways to share the results of your research. For example, think of a...