Search

Your search keyword '"Sui, Qingmei"' showing total 409 results
Start Over Author "Sui, Qingmei"
409 results on '"Sui, Qingmei"'

4. Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network

Author

Yang, Senlin, Wang, Zhengfang, Wang, Jing, Cohn, Anthony G., Zhang, Jiaqi, Jiang, Peng, and Sui, Qingmei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing, Physics - Geophysics
Abstract

This research proposes a Ground Penetrating Radar (GPR) data processing method for non-destructive detection of tunnel lining internal defects, called defect segmentation. To perform this critical step of automatic tunnel lining detection, the method uses a CNN called Segnet combined with the Lov\'asz softmax loss function to map the internal defect structure with GPR synthetic data, which improves the accuracy, automation and efficiency of defects detection. The novel method we present overcomes several difficulties of traditional GPR data interpretation as demonstrated by an evaluation on both synthetic and real datas -- to verify the method on real data, a test model containing a known defect was designed and built and GPR data was obtained and analyzed., Comment: 24 pages,11 figures

Published
2020

24. Characterization of Molybdenum (IV) Sulfide Prepared by Chemical Vapor Deposition Using Differential Reflectance Spectroscopy.

Author

Wang, Yina, Zhang, Lei, Guo, Yingqing, Lv, Shanshan, and Sui, Qingmei

Subjects
CHEMICAL vapor deposition, REFLECTANCE spectroscopy, MOLYBDENUM, SULFIDES, OPTICAL properties, MOLYBDENUM disilicide
Abstract

Molybdenum (IV) sulfide is widely employed in electronic device applications. Recognized as one of the most efficacious methods for fabricating high-quality molybdenum (IV) sulfide, the chemical vapor deposition (CVD) method's application necessitates the development of a straightforward, swift and nondestructive characterization tool. Thus, this paper presents a rapid and reliable differential reflectance spectroscopy (DRS) instrumentation, grounded on the optical microscope, capable of characterizing two-dimensional materials prepared by CVD. This universal nondestructive identification tool facilitates the investigation of two-dimensional materials on both opaque and transparent substrates. MoS2 samples prepared by CVD were characterized on SiO2/Si and sapphire substrate. The results indicate that the exciton absorption peak can be accurately identified, validating the instrumentation's utility for material detection and monolayer identification. The characterization results, corroborated by the Raman spectra with a wavenumber difference of approximately 20 cm−1 and the triangular appearance of the optical image, affirm the application of this instrumentation. Ultimately, the DRS instrumentation provides a swift and nondestructive route to characterize physical properties such as bandgap and optical properties for two-dimensional materials. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

29. Robotic Subsurface Defect Inspection System and an Unsupervised Deep Neural Network-Based Abnormal Traces Reconstruction Method for Ground Penetrating Radar Data Autonomous Collection

Author

Wang, Zhengfang, primary, Li, Zhenpeng, additional, Gao, Sheng, additional, Wang, Wenying, additional, Li, Wenhao, additional, Guo, Xiaoqin, additional, Jiang, Haonan, additional, Wang, Jing, additional, Gao, Yang, additional, Gao, Shuhua, additional, and Sui, Qingmei, additional

Published
2024
Full Text
View/download PDF

35. Unsupervised deep learning-based ground penetrating radar image translation for internal defect recognition of underground engineering structures.

Author

Wang, Zhengfang, Lei, Ming, Wang, Jing, Li, Bo, Xu, Jing, Jiang, Yuchen, Sui, Qingmei, and Li, Yao

Subjects
DEEP learning, GROUND penetrating radar, STRUCTURAL engineering, UNDERGROUND construction
Abstract

Anomaly detection of internal defects in underground engineering structures is critical. This paper proposes an unsupervised deep learning image-to-image translation method tailored for ground penetrating radar (GPR) images. The proposed model can translate real-world GPR images to simulated ones. In this manner, labeling real GPR images is not necessary, and only the target detection model trained on simulated GPR images is required to directly identify defects in real GPR images. The unsupervised deep learning network introduces geometry-consistency constraints into the CycleGAN, which largely prevents the problem of semantic distortion in translation. Validation of the proposed method was performed using GPR data collected in various scenarios using GPR of different center frequencies and manufacturers. Moreover, to verify its adaptability and feasibility for defect recognition, commonly used deep learning-based defect recognition methods, which were trained only on simulated GPR images, were used to detect the translated GPR images. The findings indicate that the type and location of internal defects in translated GPR images can be accurately identified using the proposed method. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

45. Rapid and Sensitive Screening of Trace Infectious Disease Nucleic Acids Using a High-Density Surface Modified AuNPs@Ta2C-MXene/Au/TFBG Sensor

Author

Yan, Jie, Yang, Wen, Liu, Runcheng, Xie, Yan, Jiang, Shouzhen, Li, Peilong, Wang, Chuanxin, Sui, Qingmei, Liu, Ti, and Jiang, Mingshun

Abstract

Rapid and accurate detection technology is significant for screening on population scale and control of infectious diseases. The dilution and contamination of samples can affect the accuracy of response signal, resulting in false positives, which makes diagnosis challenging, especially for early patients with mild symptoms. Here, an AuNPs@Ta2C-M/Au/TFBG sensor with saturation sites was reported for specific detection of pathogen taking SARS-CoV-2 as an example. Homogeneous periodic AuNPs@Ta2C-M structure was deposited on Au film-coated TFBG by a photo-induced method to further extend the SPR performance and surface plasmon polaritons (SPPs) response range. The ssDNA probes are immobilized on the sensing platform in a higher density using a double modification method to solve the targets concealment problem caused by the spatial secondary conformational structure of long sequence nucleic acids. Synergistic effect between the high-density probes and multi-plasmon structure enables a noticeable improvement in hybridization efficiency and signal transduction of trace target sequences. The experimental results demonstrate that the sensor can accurately detect 30 clinic samples within 5 min without amplification, which shows high agreement with RT-PCR (Kappa index = 1). In particular, dilution kinetic experiments with clinical single samples (LOD:2 pg/ml) and 10-in-1 pooled sample (Maximum dilution ratio:105) validates the excellent trace analysis capability of the sensor. Overall, this bio-sensing method provides a promising approach for trace detection of infectious pathogens.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results