news

Competence centre for data science Statistical methods, data science and artificial intelligence: the FSO and UniNE intensify their cooperation 25. The University of Neuchâtel (UniNE) and the Federal Statistical Office (FSO) are reinforcing their cooperation in the field of data science and statistical methods.

A digital twin of our planet is to simulate the Earth system in future. It is intended to support policy-makers in taking appropriate measures to better prepare for extreme events. A new strategy paper by European scientists and ETH Zurich computer scientists shows how this can be achieved. To become climate neutral by 2050, the European Union launched two ambitious programmes: " Green Deal " and " DigitalStrategy ".

After finding a vulnerability in certain credit cards for the first time last year, ETH researchers have now found a way to outsmart the PIN codes for other payment cards. Making a contactless payment with a credit or debit card is quick and easy, and has proved particularly useful during the current pandemic.

An independent report commissioned by EPFL's upper management recommends drastic measures and more comprehensive carbon accounting in order to reduce the substantial environmental impact caused by the use of digital technology at the School. A recent assessment of EPFL's digital-technology carbon footprint found that the use of computer equipment by staff and students accounts for 25% of the School's total greenhouse gas emissions.

New EPFL/INRIA research shows for the first time that it is possible for our mobile devices to conduct machine learning as part of a distributed network, without giving big global tech companies access to our data. Every time we read news online or search for somewhere to eat out, big tech collects huge amounts of our behavioral data.

Researchers from the University of Basel have developed a virtual reality app for smartphones to reduce fear of heights. Now, they have conducted a clinical trial to study its efficacy. Trial participants who spent a total of four hours training with the app at home showed an improvement in their ability to handle real height situations.

EPFL engineers teamed up with luxury watchmaker Vacheron Constantin to develop an innovative system that uses lasers to create 3D sculptures within sapphire watch crystals.

Scientists have developed a metamaterial whose mechanical properties can be reprogrammed on demand and whose internal structure can be modified by applying a magnetic field. Over the past 20 years, scientists have been developing metamaterials, or materials that don't occur naturally and whose mechanical properties result from their designed structure rather than their chemical composition.

Researchers in EPFL's Digital and Cognitive Musicology Lab in the College of Humanities used an unsupervised machine learning model to 'listen to' and categorize more than 13,000 pieces of Western classical music, revealing how modes - such as major and minor - have changed throughout history. Many people may not be able to define what a minor mode is in music, but most would almost certainly recognize a piece played in a minor key.

An international team of scientists have developed a photonic processor that uses rays of light inside silicon chips to process information much faster than conventional electronic chips. The exponential growth of data traffic in our digital age poses some real challenges on processing power. And with the advent of machine learning and AI in, for example, self-driving vehicles and speech recognition, the upward trend is set to continue.

For the first time, researchers at ETH Zurich have successfully automated the modelling of turbulence. Their project relies on fusing reinforcement learning algorithms with turbulent flow simulations on the CSCS supercomputer "Piz Daint". The modelling and simulation of turbulent flows is crucial for designing cars and heart valves, predicting the weather, and even retracing the birth of a galaxy.

Behavioral scientists at EPFL introduce DeepLabCut-Live!, a deep-learning tool that can enable real-time feedback studies on animal movement and posture. The software features "maker-less" real-time motion capture, can interface with lab hardware for neurological analysis, and is now available open source for use by researchers.

DeepChest and DeepBreath, new deep learning algorithms developed at EPFL that identify patterns of COVID-19 in lung images and breath sounds, may help in the fight against other respiratory diseases and the growing challenge of antibiotic resistance. For Dr Mary-Anne Hartley, a medical doctor and researcher in EPFL's intelligent Global Health group (iGH), 2020 has been relentless.

Make geothermal energy safer by using supercomputer simulations. That is the aim of the research project FASTER (Forecasting and Assessing Seismicity and Thermal Evolution in Geothermal Reservoirs) which involves Università della Svizzera italiana (USI), the Swiss Seismic Service (SED), the Swiss Federal Institute of Technology Zurich (ETH), and the Swiss National Centre for Scientific Computing (CSCS).

Behavioral scientists at EPFL have developed a virtual reality test that assesses a person's vulnerability to stress while exploring immersive environments. The resulting model offers the field of stress research one of the first such tools that does not rely on subjective evaluations. We all react to stress in different ways.

Fiber optic sensors - used in critical applications like detecting fires in tunnels, pinpointing leaks in pipelines and predicting landslides - are about to get even faster and more accurate. EPFL engineers have developed an advanced encoding and decoding system that allows fiber optic sensors to send data up to 100 times faster and over a wider area.

In order for robots to be able to achieve more than simple automated machines in the future, they must not only have their own "brain". Empa researchers postulate that artificial intelligence must be expanded to include the capabilities of a Physical Artificial Intelligence, PAI. This will redefine the field of robotics and the relationship between man and machine.

Database systems are under pressure to become more and more powerful. But reliability seems to be suffering as a result. Now, ETH computer scientists have developed a tool to automatically detect logic errors in database systems using three different methods. They found and reported over 450 unique, previously unknown bugs.

EPFL engineers have developed a computer chip that combines two functions - logic operations and data storage - into a single architecture, paving the way to more efficient devices. Their technology is particularly promising for applications relying on artificial intelligence. It's a major breakthrough in the field of electronics.

A team of researchers from ETH Zurich has used simulations on the CSCS supercomputer "Piz Daint" to investigate how ageing mechanisms of soot particles in the atmosphere affect cloud formation. The results show that the influence of ozone and sulfuric acid on soot ageing alters cloud formation and, ultimately, the climate.