Buffalo's deadly blizzard revealed when travel bans lose their power over time
Peer-Reviewed Publication
Updates every hour. Last Updated: 18-Dec-2025 14:11 ET (18-Dec-2025 19:11 GMT/UTC)
A research paper by scientists at the Beijing Institute of Technology proposed a brain–machine hybrid intelligent system for sound target detection (STD), featuring a neuroanatomy-informed EEG decoding network and an adaptive confidence-based fusion strategy to address poor robustness and limited generalization of existing methods under low signal-to-noise ratio (SNR) conditions or with unseen target classes.
The new research paper, publishede journal Cyborg and Bionic Systems, presented the development, validation, and optimization of the hybrid system, demonstrating that integrating neuroanatomical priors into EEG decoding and fusing brain-machine decisions can significantly enhance STD performance in complex acoustic environments.Harvard engineers, as part of Project CETI, have built an open-source bio-logger that adheres to sperm whales and records high-fidelity, multi-channel audio plus rich behavioral and environmental data. The data are tailored for machine learning analysis so that researchers can better understand whale communication.
New findings shed light on the mechanisms behind a natural purification process and identify the key microbial “teammates” that enable mosses to remove metals from water. A promising moss species was discovered in abandoned mine sites where few other plants survive. Upcoming tests will evaluate their performance in iron-rich forest drained ditches.
Extracellular vesicles serve as essential mediators of communication between immune cells and tumor cells, and the recent advances in artificial induction strategies offer an adaptable and efficient platform for engineering extracellular vesicles, enabling their application as next-generation strategies in cancer immunotherapy.