Machine learning unlocks superior performance in light-driven organic crystals
Peer-Reviewed Publication
Updates every hour. Last Updated: 10-Sep-2025 07:11 ET (10-Sep-2025 11:11 GMT/UTC)
Researchers have developed a machine learning workflow to optimize the output force of photo-actuated organic crystals. Using LASSO regression to identify key molecular substructures and Bayesian optimization for efficient sampling, they achieved a maximum blocking force of 37.0 mN—73 times more efficient than conventional methods. These findings could help develop remote-controlled actuators for medical devices and robotics, supporting applications such as minimally invasive surgery and precision drug delivery.
An Osaka Metropolitan University team has developed an explainable AI model for automatic collision avoidance between ships.
An Osaka Metropolitan University team has demonstrated unprecedented virtual radical coupling of mixed-metal trinuclear complexes via interunit metal–metal bond formation to afford a hexanuclear cluster induced by aerobic oxidation. The electrochemical and chemical redox behavior of the hexanuclear cluster was also investigated, showing that the cluster dissociates into two trinuclear complexes upon reduction and is regenerated by oxidation of the trinuclear complex.
A new study led by Professor Sayaka Nakamura from Sophia University in Japan and Professor Shiko Maruyama from Jinan University in China published in the journal Health Economics reveals the significant positive impact of the Japanese school lunch program on the weight of early teenagers. The research, titled "Wholesome Lunch to the Whole Classroom: Short- and Longer-Term Effects on Early Teenagers’ Weight," found that the program effectively reduces Body Mass Index (BMI), Percent Overweight (POW), and obesity rates, particularly among students from lower socioeconomic backgrounds.