首页|Tongji University Details Findings in Machine Learning (Compressive Strength Det ection of Tunnel Lining Using Hyperspectral Images and Machine Learning)
Tongji University Details Findings in Machine Learning (Compressive Strength Det ection of Tunnel Lining Using Hyperspectral Images and Machine Learning)
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 DailyNews Daily News-Research findings on Machine Learning are discussed in a new report. Accordingto news reporting out of Shanghai, Peop le's Republic of China, by NewsRx editors, research stated,"Traditional tunnel lining strength detection techniques are mostly contact-based, with relatively l owdetection efficiency. This study innovatively proposes hyperspectral imaging method to rapidly detecttunnel concrete lining strength from a machine vision p erspective."Funders for this research include National Key Research & Developm ent Program of China, QingdaoGuoxin Jiaozhou Bay Second Submarine Tunnel Co., L td.Our news journalists obtained a quote from the research from Tongji University, "Hyperspectral cameraswere employed in indoor experiments to capture hyperspect ral images of concrete specimens with differentcompressive strength levels. The differences of concrete strength based on hyperspectral reflectancecharacteris tics were analysed using hyperspectral images and machine learning algorithms. F irstly, theK-Nearest Neighbors (KNN) classification algorithm was used to predi ct the classification of the concretehyperspectral dataset with accuracy mostly exceeding 90 %. The results indicate distinctive differences inhy perspectral reflectance characteristics among concrete specimens. Furthermore, c ompressive strengthprediction of different concrete specimens was carried out u sing Principal component regression (PCR),Partial least squares regression (PLS R), and Least Squares Support Vector Machine (LSSVM) machinelearning models on both original and Savitzky-Golay(S-G) processed spectral data. LSSVM and PLSR models performed excellently in the visible light spectrums(400-1000 nm), with LSS VM excelling in the nearinfraredspectrums(900-1700 nm). Finally, the feasibili ty of using Hyperspectral imaging(HSI) technologyto detect tunnel lining streng th was demonstrated at the shield tunnel model site."
ShanghaiPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine LearningTongji University
NETL
NSTL
