This week’s list of top data news highlights covers December 31, 2022 to January 6, 2023 and includes articles on creating tsunami prediction models and using an AI system to classify hummingbirds.
DoNotPay, a U.S.-based legal technology company, has announced that its AI system will be used for the first time to fight a speeding ticket in court. The AI system will listen to court arguments in real-time via a smartphone and issue instructions for responses via headphones.
The Chattanooga Department of Innovation Delivery and Performance has partnered with the University of Tennessee at Chattanooga and Seoul Robotics, a software company based in South Korea, to build 86 smart intersections across Chattanooga’s downtown area. Officials will install lidar sensors in each intersection to monitor roadways and collect real-time data on pedestrian and vehicular traffic. Officials will also use the data in a digital twin of the city that can inform future traffic management projects.
Researchers at the RIKEN Prediction Science Laboratory in Japan have created an AI system that can predict the impact of a tsunami in less than a second. The team trained the system with over 3,000 simulated tsunamis and tested it with additional simulated tsunami scenarios as well as actual tsunami data. The system improves upon current prediction methods, which typically take around 30 minutes to complete.
4. Discovering Galaxy Characteristics
An international team of researchers has used a supercomputer to process images from the James Webb Telescope and found two barred galaxies, or galaxies with bar-shaped structures in their center, from around 11 billion years ago. The two galaxies, which are older than any previously discovered barred galaxies, suggest that current theoretical models for galaxy evolution may not accurately chronicle the growth of new stars in young galaxies.
Apple has launched a narrating service that uses an AI system for audiobooks. The company currently sells AI-narrated audiobooks for select titles in the fiction and romance genres and plans to expand to nonfiction and self-development books next.
Ottonomy, a U.S.-based autonomous delivery company, has created a robot that can transport and deliver goods. The robot uses cameras, sensors, and an AI system to navigate its surrounding environment and a mobile shelf to drop goods off at their destination. It improves upon previous models by eliminating requirements that a human be physically present to receive their order.
Nvidia has created an AI system that can sharpen edges and remove artifacts in videos. The system can transform most videos watched in the Edge or Chrome browsers.
Bird Buddy, a bird feeder manufacturing company, has created a smart hummingbird feeder. The feeder has an AI-powered camera that can detect and identify 350 different hummingbird species with wing speeds up to 60 miles per hour. The team trained the system by collecting over two million photographs of birds and partnering with a local ornithologist to classify the images.
9. Predicting Adverse Opioid Outcomes
Researchers at the University of Alberta, the College of Physicians and Surgeons of Alberta, and Okaki, a health technology company based in Canada, have created a machine learning model that can predict a patient’s risk of opioid-related hospitalization, emergency department visit, or mortality within 30 days of an opioid prescription dispensation. The team trained the system with prescription drug records from over 850,000 patients who received at least one opioid dispensation, population and vital statistics, and hospitalizations and emergency department visits in Alberta.
Researchers at the University of Helsinki, Aalto University, and Ko Akademi University in Finland have created a virtual reality game that medical providers can use to assess ADHD symptoms in pediatric patients. Researchers used the game headset and a machine learning model to track patients’ eye movements during the game, and found that patients with ADHD focused on objects in the game longer and moved their gaze faster than patients without ADHD.
Image credit: Flickr user L1mey