American Sign Language (ASL) recognition systems often struggle with accuracy due to similar gestures, poor image quality and inconsistent lighting. To address this, researchers developed a system that translates gestures into text with 98.2% accuracy, operating in real time under varying conditions. Using a standard webcam and advanced tracking, it offers a scalable solution for real-world use, with MediaPipe tracking 21 keypoints on each hand and YOLOv11 classifying ASL letters precisely.

New research in JNCCN from The Ohio State University Wexner Medical Center and James Comprehensive Cancer Center found socially vulnerable patients with metastatic pancreatic cancer were significantly less likely to receive key components of quality care and had poorer survival.

Nanoplastics are an increasing threat to the ecosystem; however, their mobility in the soil is still underexplored. Against this backdrop, researchers from Waseda University and the National Institute of Advanced Industrial Science and Technology investigated the adsorption and aggregation behavior of nanoplastics in different types of soil under different pH conditions. The study offers new perspectives on the migration and environmental interactions of nanoplastics, while broadening our knowledge of pollution dynamics and soil contamination processes.

As global crises and inequalities escalate, UN University identifies five deep, fundamental changes needed to address several of the world’s most pressing problems at their roots -- societal structures and mindsets -- to achieve effective, lasting solutions. Throughout the report, authors highlight successful sustainability initiatives worldwide.