news from the lab 2017

For the very first time, the "Innovation Lab", a special exhibition for digital transformations in the construction industry, will be held at Swissbau 2018 from 16 to 20 January. NEST, the modular research and demonstration platform from Empa and Eawag, will be presenting with its partners (in hall 1.1, booth L88) how digital construction is implemented in reality and exactly what kind of potential for digital innovation is offered by the set of demonstrators on the Empa campus in Dübendorf.

EPFL researchers have shown how human operators can maintain control over a system comprising several agents that are guided by artificial intelligence. In artificial intelligence (AI), machines carry out specific actions, observe the outcome, adapt their behavior accordingly, observe the new outcome, adapt their behavior once again, and so on, learning from this iterative process.

EPFL researchers have come up with a fact-based system to measure urban cleanliness. Municipal authorities will now be able to draw on objective assessments when planning their street cleaning - a sector with multi-million-franc budgets. The concept is straightforward: on one hand, vehicles equipped with video cameras to record the city streets, and on the other, a computer able to spot waste, identify it and classify it - in the blink of an eye.

Technis, an EPFL spin-off, has developed a system that combines a connected floor surface with artificial intelligence to track people's trajectories as they walk through a shopping mall or convention center, for example.

Students from EPFL and HEC have just launched an app that streamlines how you organize a meal out with friends.

EPFL researchers have shown that a simple camera can detect and track flying drones. Plus, the lightweight, energy-efficient and inexpensive technology could be installed directly on the drones themselves and enhance safety in the skies. The rising number of drones in air space poses numerous challenges.

Ingo Scholtes from the Chair of Systems Design has developed an analytical method that takes account of the chronological order of connections within networks. This not only makes it possible to more accurately identify links between topics on the internet, but also makes it easier to predict the spread of epidemics, for example.

Does clicking on a link or liking a product have an impact on your privacy and your personal information? An EPFL researcher has come up with a way to browse the internet without revealing too much about yourself and without having to forgo the convenience of online product recommendations. Nowadays it is common for people to buy a book or other product that was recommended to them based on their online profile.

Filming of spectacular action scenes is expensive and the creative possibilities are often limited. An ETH doctoral student has developed an algorithm that allows drones to implement the desired picture compositions independently.

A deep-learning algorithm developed by EPFL scientists can generate melodies that imitate a given style of music.

An EPFL researcher has created a system that scans Wikipedia for important articles that are missing in other languages. This project could help expand the online encyclopedia's coverage in minority languages, such as Romansh. With 40 million articles in 293 languages, Wikipedia is the largest encyclopedia ever made.

Using a special multi-angle camera, EPFL researchers have gained important insights into the structure of snowflakes. Their aim is to improve the accuracy of snowfall measurements and winter weather forecasts. Imagine taking pictures of thousands of snowflakes from three different angles with a specialized instrument installed at an altitude of 2,500 meters.

In working sentence by sentence, translation algorithms omit much of the context and make mistakes. A project supported by the SNSF has developed new algorithmic techniques designed to do a better job of taking the entire text into account. Researchers supported by the Swiss National Science Foundation (SNSF) have come up with a new approach to improving machine translation tools such as the famous Google Translate, which processes hundreds of billions of words daily.

'Is this your sister'' That's the kind of question asked by image-recognition systems, which are becoming increasingly prevalent in our everyday devices. They may soon be used for tumor detection and genomics, too. These systems rely on what is known as 'deep-learning' architectures - an exciting new development in artificial learning.

ETH Zurich researchers and Disney Research have produced a new algorithm that allows non-invasive reconstruction of the teeth and gums from digital photos.

Theoretical physicists from ETH Zurich deliberately misled intelligent machines, and thus refined the process of machine learning. They created a new method that allows computers to categorise data - even when humans have no idea what this categorisation might look like. When computers independently identify bodies of water and their outlines in satellite images, or beat the world's best professional players at the board game Go, then adaptive algorithms are working in the background.

EPFL researchers have developed an algorithm for automated vehicles to operate in traffic alongside manually-driven vehicles.