Gunfire or plastic bag popping? Trained computer can tell the difference
Peer-Reviewed Publication
FAU engineering researchers have developed a gunshot detection algorithm and classification model that can discern similar sounds such as gunfire or a plastic bag popping. Discerning between a dangerous audio event like a gun firing and a non-life-threatening event, such as a plastic bag bursting, can mean the difference between life and death. Additionally, it also can determine whether or not to deploy public safety workers. Humans, as well as computers, often confuse the sounds of a plastic bag popping and real gunshot sounds.
In the largest meta-analysis of trials on digital interventions for the treatment of depression, researchers found that computer- and smartphone-based treatments offer a promising method to address the growing mental health needs. However, support from a human is still needed to ensure people adhere to treatment.
Physicists from Trinity College Dublin have unlocked the secret that explains how large groups of individual “oscillators” – from flashing fireflies to cheering crowds, and from ticking clocks to clicking metronomes – tend to synchronise when in each other’s company. This new discovery has a suite of potential applications, including developing new types of computer technology that uses light signals to process information.
Range anxiety with electric commercial vehicles is real, since running out of battery can have serious consequences. Researchers at Chalmers University of Technology, Sweden, have developed tools to help electric delivery-vehicles navigate strategically to use as little energy as possible. The secret lies in looking beyond just the distance travelled, and instead focusing on overall energy usage – and has led to energy savings of up to 20 per cent.
An international team led by SWOG Cancer Research Network has developed statistical models to predict the risk of early death in patients being treated with non-intensive therapies for acute myeloid leukemia (AML). Results of analyses using the models will be given in an oral presentation at the 2021 American Society of Hematology (ASH) Annual Meeting on December 11.
As digitalization continues to make headway, finding ways of increasing the security of the exchange of sensitive information becomes ever more important. One of the main methods proposed to achieve this is a communication network that operates based on the laws of quantum physics. This would ensure that undetected eavesdropping is made impossible. Development of such a system is the aim of the joint research project QuantumRepeater.Link (QR.X). The project is to receive total funding of some EUR 35 million from the German Federal Ministry of Education and Research (BMBF) over the next three years.
Dead-end Discovery is a new learning model can identify high-risk treatments in urgent situations, and in some cases alert doctors when a patient is approaching a medical dead-end that will likely result in their death.