An AI message decoder based on bacterial growth patterns

Researchers developed a brain decoder to restore communication between the brain and spinal cord, allowing for rehabilitation and potentially restoring movement. The decoder used electroencephalography to predict movement intention, outperforming previous methods.

A new AI-based tool can translate a person's thoughts into continuous text without requiring language comprehension, and it can be trained in under an hour. The system was developed by adapting a previous brain decoder to a new person using short, silent videos.

The partnership is dedicated to tackling health issues arising from climate change, reflecting both institutions' commitment to innovative research. The five selected projects will bring together top researchers from Duke and Duke-NUS, leveraging unique strengths to advance basic, translational, and clinical research.

Researchers from Duke and Duke-NUS are investigating genetic features controlling infection susceptibility across populations to develop new treatments. They will compare cohorts in Singapore and the US, analysing how genetic variants shape disease vulnerability.

USC researchers found that climate change graphics are too complex, even for policymakers and practitioners. The study recommends limiting each graphic to one key message and suggests a detailed checklist to improve design. Effective graphics should convey a clear message and target broad audiences.

Researchers found that automated text message reminders significantly reduced bench warrants and pretrial incarceration rates. The study used software sent to clients of public defenders in California, resulting in a 20-21% decrease in missed court dates.