Universiteit Leiden

nl en

AI research in Zuid-Holland: three examples

How designers are even more creative with a robot in their team, how Twitter could predict the stock market, and how to catch a single bacterium in the act of infecting a cell. Artificial intelligence has penetrated every corner of science in Zuid-Holland. Three researchers from Delft University of Technology, Erasmus University Rotterdam and Leiden University talk about their diverse range of work with AI.

AI literally opens new worlds for the life sciences

Bacteria caught red-handed, frozen just as they were about to cause Lyme’s disease. Professor Ariane Briegel is wildly enthusiastic about the wonders she observes thanks to three elements: a freezing technique, a camera-equipped microscope and AI. ‘It’s fascinating. Every single cell is different.’

Bacteria follow their ‘noses’ towards a food source. Well, strictly speaking not noses, but receptor proteins, neatly arranged like honeycomb. Briegel has watched as these prick through cell walls. On the outside they detect signals; on the inside they set the cell to work swimming in the right direction.

The camera in Briegel’s microscope takes approximately 100 photographs of the same number of cell slices. Smart software then turns these 100 photographs into a comprehensible 3D image. This has revealed a new world to Briegel and her colleagues: they can observe in great detail what cell structures and organs look like and how something such as ‘moving’ comes about in bacteria. 

And that’s just the begining. ‘When I completed my PhD 20 years ago, I was producing two datasets a day at most. Now it’s 40 to 50, far more than researchers could ever look at. And we want to tackle even larger projects.’ Like mapping the 1.5 kilograms of bacteria on and inside the human body. ‘Regardless whether you’re looking at infection, cancer or growth: these techniques will soon enable us in the life sciences to elucidate so many biological systems.’

Competing in the AI age

Professor of Digital Business Ting Li studies how companies can benefit from data at the Erasmus Centre for Data Analytics. You may not realise it, but Google gets smarter with every search you make. ‘It’s a learning algorithm and it’s becoming omre and more precise. The more often we click on a page, the higher that page will appear in the list of search results,’ she explains.

AI is everywhere, says Li. It’s in cars and banking systems, in dating sites and all over the media. Companies often use recommendation systems – a form of AI – to recommend products, such as movies on Netflix, music on Spotify, and all manner of items on Amazon. ‘You might think that you never click on those recommendations, but 30 to 35% of Amazon’s sales come from smart recommendation systems that are increasingly being fine-tuned by their data engineers,’ she says.

One of Li’s PhD candidates is helping an insurance company to understand why customers switch from the one insurer to another. ‘We analyse the data to find out whether customers are primarily motivated to switch by comparison sites such as Independer, by Google search ads, by links on other websites or after being called by a sales representative,’ Li continues.

In another project, Li is investigating whether you can use Twitter or Facebook to predict the stock market. ‘Algorithms can browse through those media and distil sentiments. For example, the sentiment “Apple did well in the first quarter” might enable you to predict their performance on the stock market,’ she says. It’s not yet certain whether this will work; it could also be that the sentiment only becomes more positive once the share price has risen.

It is not just about making money. ‘Such data and AI systems could also help you improve your service. For example, I work with public transport companies who want to improve their fare structure based on travel patterns, or to ensure that passengers don’t have to stand.’ Li describes the core of her research as follows: ‘I’m always looking for the relevance of information, be it for the benefit of companies, individuals or society as a whole.’

Algorithm helps design teams collaborate more effectively

Computer scientist Catharine Oertel (Delft University of Technology) is studying how an artificial system such as a robot can strengthen a team. ‘It will need to be able to hear everything that is said but only remember the important bits, and see how people move and what they look at. It will need to be familiar with relevant scenarios and compare these with all important social and cognitive processes in a team. It will ultimately need to be able to positively influence the way the team cooperates,’ she says.

That’s quite a tall order. ‘Our holy grail is to achieve this degree of interaction with several people simultaneously and over a longer period of time,’ Oertel continues. She has come to Delft for the coming five years to continue her search for this holy grail in the world of industrial design. Whereas designers used to be commissioned to simply design the best streamlined aircraft for the best price, today they also have to take account of such aspects as the working conditions in the mines where the raw materials are extracted and the threat of those raw materials becoming depleted.

Delft University of Technology’s strong reputation in the fields of industrial design and artificial intelligence comes together in the Designing Intelligence Lab, one of 24 AI labs currently being established at the University. Each lab has two principal investigators, and Oertel will be working at the Designing Intelligence Lab with Senthil Chandrasegaran over the coming five years, assisted by four PhD candidates .

De sterke reputaties van de TU Delft op het gebied van industrieel ontwerp en kunstmatige intelligentie komen bij elkaar in het Designing Intelligence Lab, een van de 24 TU Delft AI-labs die de universiteit momenteel opstart. Elk AI-lab in Delft heeft twee principal investigators, bij het Designing Intelligence Lab werkt Oertel samen met Senthil Chandrasegaran; vijf jaar lang gaan zij met vier promovendi aan de slag.

Oertel does not expect to have created a fully-fledged system that will lighten the load of design teams within these five years. ‘But I do think we will take important steps in the development of a real-time visual analytical system that will be a valuable addition to the AI toolkit of designers and other teams,’ she says.

This article was previously published on the website of LDE Universities, an alliance bteween the universities of Leiden, Delft and Rotterdam. 

This website uses cookies.  More information.