摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑-每日新闻-一项关于人工智能的新研究现在可用。根据NewsRx记者在南达科他州拉皮德市的新闻报道，研究表明，“表征二维材料中的缺陷，例如化学气相沉积(CVD)生长的六方氮化硼(H BN)中的裂纹，对于评估材料质量和可靠性至关重要。”这项研究的财政支持者包括国家科学基金会（Nsf）Rii Fec奖；Nsf Cbet奖；国家卫生研究院的国家普通医学研究所。新闻记者从南达科他州矿业与技术学院的研究中获得了一句话：“传统的表征方法往往耗时和主观，并且会受到H BN有限的光学对比度的阻碍。为了解决这个问题，我们使用了YOLOv8n深度学习模型来自动检测转移的CVD生长的hBN薄膜中的CRA CK，利用MATLAB的图像标签器和监督进行细致的标注和训练。该模型展示了裂纹检测能力,准确识别不同规模和复杂程度的裂纹,损失曲线分析揭示了渐进学习。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news reporting from Rapid City, South Dakota, by NewsRx journalists, research stated, "Characterizing defects in 2D materials, s uch as cracks in chemical vapor deposited (CVD)-grown hexagonal boron nitride (h BN), is essential for evaluating material quality and reliability." Financial supporters for this research include National Science Foundation (Nsf) Rii Fec Awards; Nsf Cbet Award; National Institute of General Medical Sciences of The National Institutes of Health. The news journalists obtained a quote from the research from South Dakota School of Mines and Technology: "Traditional characterization methods are often time-c onsuming and subjective and can be hindered by the limited optical contrast of h BN. To address this, we utilized a YOLOv8n deep learning model for automated cra ck detection in transferred CVD-grown hBN films, using MATLAB's Image Labeler an d Supervisely for meticulous annotation and training. The model demonstrates pro mising crack-detection capabilities, accurately identifying cracks of varying si zes and complexities, with loss curve analysis revealing progressive learning."
NETL
NSTL