news 2023

More than a decade of research at TU/e, led by Fons van der Sommen, has culminated in a scientific publication in The Lancet Digital Health this December. The study focuses on the use of artificial intelligence (AI) to detect incipient esophageal cancer in people with Barrett's esophagus. It is 2011.

Mark Bouwman defended his PhD thesis at the Department of Mathematics and Computer Science on October 23rd. In a few years, the safety system for switches and signals along European railroads will change so that the same system will be used across the entire network. The system will no longer be controlled via a direct cable, but with packets of information transmitted through a fiber optic network.

Last week, researchers and Bachelor's students from the University of Twente investigated whether an escape room simulation of a cyber attack could contribute to increasing cybersecurity awareness. The participants were staff of healthcare facilities in the Twente and eastern Achterhoek regions. Initial results show that the escape room increases cybersecurity awareness among healthcare workers: for instance, participants say they are more alert to phishing, installing software updates promptly, and the use of strong passwords.

How can we engineer better software by using artificial intelligence (AI)- TU Delft and JetBrains are joining their knowledge and expertise on AI and software development in the new AI for Software Engineering Lab (AI4SE). The goal of the collaboration is to develop a deep understanding of how novel AI technologies can strengthen the effectiveness and efficiency of software engineering processes.

Many local authorities respond too slowly or inadequately to reports about security vulnerabilities. These coordinated vulnerability disclosures (CVD reports) are often made by ethical hackers who aim to make the internet safer. While this process has improved in recent years, the study by the University of Twente and the Dutch Institute for Vulnerability Disclosure (DIVD) indicates that there is still much room for improvement for local authorities.

Data visualizations, including diagrams, are a frequent sight in the media. Histograms, in particular, are popular for their ability to present data concisely. Unfortunately, many people find these diagrams challenging to interpret. Lonneke Boels conducted an investigation into why this occurs, using artificial intelligence to analyse eye movements.

Researchers from Delft established a way to address many quantum dots with only a few control lines using a chessboard-like method. This enabled the operation of the largest gate-defined quantum dot system ever. Their result is an important step in the development of scalable quantum systems for practical quantum technology.

In this series we show what contribution projects can make to FAIR research IT. The research teams of the projects in these interviews have received a grant from the FAIR Research IT Innovation Fund . Good news for scientists whose technological skills are limited, but who want to work with social media data in their research: now you can use 4CAT, a tool that helps you to harvest and analyse such research data in a simple way.

AI engineer Hilde Weerts on fairness of algorithms Ever since ChatGPT hit the scene, all eyes have been fixed on the meteoric development of Artificial Intelligence. Experts around the world are expressing concerns and speculating about what these large language models may lead to. In this series, Cursor and the scientific director of EAISI Wim Nuijten talk to TU/e researchers about their perspectives on the future of AI.

New algorithm developed to monitor sleep with wearables in patients with sleep disorders have been tested in the clinical setting Approximately 10% of the world's population are affected by insomnia, which is just one of a variety of serious sleep disorders.

The Dutch Research Council for Scientific Research (NWO), has awarded Vidi funding to four UT research projects. These are studies led by Arnd Hartmanns, Linn Leppert, Jelmer Renema and Roland van Rijswijk-Deij. With this contribution of 800,000 euros, they can develop an innovative line of research and set up a research group in the coming five years.

Generative AI programmes can generate images from textual prompts. These models work best when they generate images of single objects. Creating complete scenes is still difficult. Michael Ying Yang, a UT-researcher from the faculty of ITC recently developed a novel method that can graph scenes from images that can serve as a blueprint for generating realistic and coherent images.

Scientists of the department of Natural Resources (ITC Faculty - University of Twente) recently published an article in the scientific journal Nature Communications . In their research, associate professor from the NRS Department Dr Tiejun Wang (corresponding author) and his master's student Ms.

Developments are rapid around data, algorithms, machine learning and artificial intelligence (AI), especially since the launch of ChatGPT late last year. Software engineering is highly relevant here, because AI systems are essentially made up of software, and also because the two fields influence each other.

Algorithms will inevitably play an increasing role in our lives in the coming years. Yet it is often suggested that people are wary of computer systems taking over their everyday choices. For example, do we trust computers with our health and money? A new publication in AI & Society by Radboud researchers shows that humans are quite open to algorithms' decisions, as long as we believe that this is to our benefit.

Special Chair of Text-Mining Jan Scholtes on how ChatGPT actually works, why it's an amazing achievement and where we should probably exercise a bit of caution.

Nowadays, it is quite common to develop and use code and software for research. Graduate Keven Quach wanted to know how FAIR the code and software is developed by researchers at Utrecht University. So he dived into GitHub, an online platform where you can develop, manage and publish code and software.

How do you find the fastest route if you can't see all possible links? For example when "routing" Internet traffic - something which is now done based on trust - or protein pathways in the body, insights wherein can lead to completely new understandings diseases and medicines? Scientists have been racking their brains over the question since the 1950s.