Using AI and old reports to understand new medical images

Getting a quick and accurate reading of an X-ray or some other medical images can be vital to a patient's health and might even save a life. Obtaining such an assessment depends on the availability of a skilled radiologist and, consequently, a rapid response is not always possible. For that reason, says Ruizhi "Ray" Liao, a postdoc and a recent PhD graduate at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), "we want to train machines that are capable of reproducing what radiologists do every day." Liao is first author of a new paper, written with other researchers at MIT and Boston-area hospitals, that is being presented this fall at MICCAI 2021, an international confe..

phys.org : computer-sciences Using AI and old reports to understand new medical images

When accidents happen, drones weigh their options

Flying cars, drones, and other urban aerial mobility vehicles have real potential to provide efficient transportation and delivery solutions, but what happens if a drone delivering cheeseburgers breaks down over a city park or in the middle of a crowded street? Researchers at the University of Illinois Urbana-Champaign developed a method to measure vehicles' ability to recover and complete its mission safely.

phys.org : computer-sciences When accidents happen, drones weigh their options

Resolving the where and when of social media events

Researchers from the University of Melbourne (UoM) and the Singapore University of Technology and Design (SUTD) have developed an algorithm that can detect important events based on the time and geographical scale of topics being actively discussed on social media. Their algorithm, detailed in the Journal of Big Data, does not require knowing which events to detect upfront and can be tailored to use smaller or larger geographical and time resolutions to reflect the dynamic nature of real-life events.

phys.org : computer-sciences Resolving the where and when of social media events

Finding the needles in a haystack of high-dimensional data sets

One of the challenges in the era of Big Data is dealing with many independent variables, also known as the "curse of dimensionality." Therefore, there is an urgent need to develop algorithms that can select subsets of features that are relevant and have high predictive powers. To address this issue, computer scientists at the University of Groningen developed a novel feature selection algorithm. The description and validation of their method was published in the journal Expert Systems with Applications on 16 September 2021.

phys.org : computer-sciences Finding the needles in a haystack of high-dimensional data sets

DRNets can solve Sudoku, speed scientific discovery

Say you're driving with a friend in a familiar neighborhood, and the friend asks you to turn at the next intersection. The friend doesn't say which way to turn, but since you both know it's a one-way street, it's understood.

phys.org : computer-sciences DRNets can solve Sudoku, speed scientific discovery

DronePaint: A human-swarm interaction system for environment exploration and artistic painting

Researchers at Skolkovo Institute of Science and Technology (Skoltech) in Russia have recently developed an innovative system for human-swarm interactions that allows users to directly control the movements of a team of drones in complex environments. This system, presented in a paper pre-published on arXiv is based on an interface that recognizes human gestures and adapts the drones' trajectories accordingly.

phys.org : computer-sciences DronePaint: A human-swarm interaction system for environment exploration and artistic painting

Development of dendritic-network-implementable artificial neurofiber transistors

Advances in artificial-intelligence-based technologies have led to an astronomical increase in the amounts of data available for processing by computers. Existing computing methods often process data sequentially and therefore have large time and power requirements for processing massive quantities of information. Hence, a transition to a new computing paradigm is required to solve such challenging issues. Researchers are currently working towards developing energy-efficient neuromorphic computing technologies and hardware that are capable of processing massive amounts of information by mimicking the structure and mechanisms of the human brain.

phys.org : computer-sciences Development of dendritic-network-implementable artificial neurofiber transistors

An autonomous system that can reach charge mobile robots without interrupting their missions

Researchers at Skolkovo Institute of Science and Technology in Russia have recently developed MobileCharger, an autonomous robotic system designed to charge other robots as they complete their missions. This system, presented in a paper pre-published on arXiv, can transfer energy to mobile robots without forcing them to fly back to designated charging stations when their power is depleted.

phys.org : computer-sciences An autonomous system that can reach charge mobile robots without interrupting their missions

Supercomputer probes the limits of Google's quantum processor

CPQM's Laboratory for Quantum Information Processing has collaborated with the CDISE supercomputing team "Zhores" to emulate Google's quantum processor. Reproducing noiseless data following the same statistics as Google's recent experiments, the team was able to point to a subtle effect lurking in Google's data. This effect, called a reachability deficit, was discovered by the Skoltech team in its past work. The numerics confirmed that Google's data was on the edge of a so-called, density-dependent avalanche, which implies that future experiments will require significantly more quantum resources to perform quantum approximate optimization. The results are published in the field's leading jou..

phys.org : computer-sciences Supercomputer probes the limits of Google's quantum processor

Technologies can help drivers maintain the two-second rule to improve road safety and traffic flow

The two-second rule, taught in driver's ed classes across the country, is a rule of thumb that helps drivers maintain a safe distance from the car ahead at any speed. Adhering to the two-second rule can be difficult. A team of engineers led by Dan Work, associate professor of civil and environmental engineering, has developed an assistive technology to help drivers maintain this guidance to smooth out traffic jams and improve safety.

phys.org : computer-sciences Technologies can help drivers maintain the two-second rule to improve road safety and traffic flow

A machine learning technique that can learn local equilibria in symmetric auction games

Over the past few decades, computer scientists have been exploring the potential of applying game theory and artificial intelligence (AI) tools to chess, the abstract strategy board game go, or other games. Another valuable use of game theory is in the economic sciences, particularly as a framework to explain strategic interactions in markets and the resulting outcomes.

phys.org : computer-sciences A machine learning technique that can learn local equilibria in symmetric auction games

A multi-task learning network to recognize the numbers on jerseys of sports team players

When reporting on sports games live or remotely, commentators should be able to quickly recognize the numbers on the players' jersey shirts, as this allows them to keep up with what's happening and communicate it to their audience. However, quickly identifying players in sports videos is not always easy, as these videos are often taken at a distance to capture the overall progression of the game. A further difficulty is the fast motion of the broadcast camera that often results in motion blur.

phys.org : computer-sciences A multi-task learning network to recognize the numbers on jerseys of sports team players