首页|Findings from Princeton University Update Knowledge of Machine Learning (Crack P attern-based Machine Learning Prediction of Residual Drift Capacity In Damaged M asonry Walls)
Findings from Princeton University Update Knowledge of Machine Learning (Crack P attern-based Machine Learning Prediction of Residual Drift Capacity In Damaged M asonry Walls)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A new study on Machine Learning is now available. According to news reporting originating in Princeton, New Jersey, by NewsRx jou rnalists, research stated, “In this paper, we present a method based on an ensem ble of convolutional neural networks (CNNs) for the prediction of residual drift capacity in unreinforced damaged masonry walls using as only input the crack pa ttern. We use an accurate blockbased numerical model to generate mechanically c onsistent crack patterns induced by external actions (earthquake-like loads and differential settlements).” Financial supporters for this research include Horizon 2020 - Marie Sklstrok;odo wska-Curie Actions, European Union (EU).
PrincetonNew JerseyUnited StatesNo rth and Central AmericaCyborgsEmerging TechnologiesMachine LearningPrinc eton University
NETL
NSTL
