SCROLL NEWS / DISCOVERY
Search headlines
Find the stories shaping the conversation.
Results for " seoul national university of science and technology " 6 found 🔀 AI-powered Shuffle
Seoul National University of Science and Technology Researchers Show How Smartphones Can Help Detect Lung Problems in Children
/PRNewswire/ -- Respiratory disease in children is a major global concern. Although stethoscopes help clinicians detect abnormal lung sounds, access to...
Seoul National University of Science and Technology Researchers Develop a Reliable AI System for SSD Failure Prediction
/PRNewswire/ -- Solid-state drives (SSDs), which store data in computers and servers, are critical to data center reliability. SSD failures can cause service...
Seoul National University of Science and Technology Develops AI Framework to Test and Improve Vision-System Robustness
/PRNewswire/ -- In computer vision and robotics, ensuring that AI systems remain reliable under real-world conditions is a growing challenge. Deep neural...
Seoul National University of Science and Technology develops AI framework to test and improve vision-system robustness
A new artificial intelligence (AI)-based system shows how natural damage to traffic signs can mislead deep neural network (DNN)-based vision systems. The framework, AdvWT, uses a generative model to learn realistic damage patterns and then optimize them to trigger misclassification. Tests across multiple AI architectures showed strong attack success, transferability and physical-world robustness. The approach can identify vulnerabilities and improve AI generalization to real-world damage.
Seoul National University of Science and Technology researchers explore how probabilistic analysis can help improve nuclear safety
Traditional approaches for designing primary coolant pipes in nuclear power plants consider highly unlikely, extreme scenarios. Estimating pipe rupture frequency is a more practical approach. In a new study, researchers investigated the pipe rupture frequency of coolant pipes using a probabilistic framework that accounts for material properties, degradation pathway, and even inspection performance, offering a risk-informed approach to design and evaluation.
Seoul National University of Science and Technology researchers develop AI framework for optimizing solid oxide electrolysis cells
As countries invest in green hydrogen to decarbonize heavy industry, transportation, and energy systems, researchers are seeking faster ways to accelerate the development of hydrogen technologies. Solid oxide electrolysis cells are among the most efficient systems for producing green hydrogen from steam, but identifying their optimal operating conditions requires thousands of computationally intensive simulations, slowing innovation and increasing development costs.