Smart cruise control, better human decisions. Michigan Tech engineers study how cars and trucks move cooperatively on the road, respond to each other's environmental sensors and react as a group to lessen traffic jams and protect the humans inside.
EPFL scientists have developed a digital pathology tool for quantifying bone marrow compartments in standard histological sections. Named 'MarrowQuant', the software makes it possible to examine bone marrow biopsies as well as to re-examine historical collections of bone-marrow samples and even old clinical trials.
The Hyperspectral Stripe Projector captures spectroscopic and 3D imaging data for applications like machine vision, crop monitoring, self-driving cars and corrosion detection.
In his recent paper published in the Association of Computing Machinery's journal, Interactions, City, University of London's Dr Alex Taylor calls on the industries and practitioners who build technologies, and the scholars who study them, to imagine different futures which are responsive to and responsible for the full diversity of lives lived.
Engineers at CSEM have developed a new machine-learning method that paves the way for artificial intelligence to be used in applications that until now have been deemed too sensitive. The method, which has been tested by running simulations on a climate-control system for a 100-room building, is poised to deliver energy savings of around 20%.
Researchers developed a new mathematical model to predict economic performance of crops. It can assist the breeders to obtain the plants with the highest possible quality.
Artificial intelligence (AI) experts at the University of Massachusetts Amherst and the Baylor College of Medicine report that they have successfully addressed what they call a "major, long-standing obstacle to increasing AI capabilities" by drawing inspiration from a human brain memory mechanism known as "replay."
Artificial intelligence researchers have improved the performance of deep neural networks by combining feature normalization and feature attention modules into a single module that they call attentive normalization. The hybrid module improves the accuracy of the system significantly, while using negligible extra computational power.
Before autonomous vehicles participate in road traffic, they must demonstrate conclusively that they do not pose a danger to others. New software developed at the Technical University of Munich (TUM) prevents accidents by predicting different variants of a traffic situation every millisecond.
Signals sent from the retina to the brain have a lot of background noise, yet we see the world clearly. Duke researchers show that to achieve visual clarity the brain must accurately measure how this noise is distributed across neurons when processing the signals sent down the optic nerve. These results are likely to shape the design of future retinal prosthetics and other brain-machine interfaces.