Scientists propose a deep neural network-based platform for identifying candidate antimicrobial peptides Antimicrobial peptides (AMPs) are a promising new weapon for combating the growing antimicrobial resistance of bacteria and other harmful microorganisms. Now, researchers from the Gwangju Institute of Science and Technology developed a new, easily interpretable AI-powered prediction model…

The protective tetraphenylporphyrin layer prevents the degradation of inexpensive nickel­–iron catalysts Nickel–iron (Ni–Fe) catalysts are promising materials for the production of green hydrogen, but they are limited by the easy dissolution of Fe inside water-splitting cells. …

The new two-stage stochastic optimization model accounts for variations and uncertainty in renewable energy to make the optimal scheduling decision Microgrids are crucial for integrating renewable energy into the electrical grid. But current microgrid models ignore the inherent uncertainty of renewable energy supply. Now, scientists from Gwangju Institute of Science…

It utilizes an object detection algorithm that learns human spectating data to find engaging viewports Human game observers are a vital part of the Esports industry. They use extensive domain knowledge to decide what to show to the spectators. However, they may miss important events, necessitating the need for automatic…

Researchers from Korea develop a new image retrieval system using deep learning algorithms Sifting through large amounts of data available on the internet is a difficult task. …

Gwangju Institute of Science and Technology Researchers Design AI-based Model that Predicts Extreme Wildfire Danger Combining artificial intelligence and weather forecast models can boost extreme wildfire forecasts by up to 7 days, finds new study Accurate wildfire risk prediction is essential for an efficient allocation of resources for their mitigation…

They achieve this by removing residual organic metal-binding ligands from the transition metal oxide thin films, enhancing device stability and performance Organic photovoltaics with a transition metal oxide (TMOs) interface layer are emerging as a promising alternative to conventional silicon-based photovoltaics. However, their electrical properties are often affected by unwanted…

With this approach, the developed photocathodes exhibit a remarkable stability and demonstrate sunlight-driven clean hydrogen production by water splitting Organic semiconductors (OSs) used in organic solar cells show promise as a candidate for facilitating clean hydrogen production from sunlight. However, they suffer from slow charge transfer and chemical instability. Addressing…

The approach involves a post-correction network optimized by a self-supervised machine learning framework to improve the quality of unfamiliar images High-quality visual displays rendered using the “path tracing” algorithm are often noisy. Recent supervised learning-based denoising algorithms rely on external training dataset, take long to train, and do not work…