Search

Your search keyword '"Li, Qingyong"' showing total 383 results
Start Over Author "Li, Qingyong" Language english
383 results on '"Li, Qingyong"'

33. Hypermucoviscous Multidrug-Resistant Klebsiella variicola Strain LL2208 Isolated from Chinese Longsnout Catfish (Leiocassis longirostris): Highly Similar to Human K. variicola Strains.

Author

Li, Qingyong, Yu, Xin, Ye, Lin, Hou, Tongyu, Liu, Yi, Liu, Guiming, Wang, Qing, and Zhang, Defeng

Subjects
MICROBIAL sensitivity tests, GENOME size, AQUATIC animals, FRESHWATER fishes, BACTERIAL diseases
Abstract

Outbreaks of bacterial diseases occur in farmed Chinese longsnout catfish (Leiocassis longirostris). Due to limited information on aquatic Klebsiella variicola-infected animals, this study aimed to identify strain LL2208 isolated from diseased L. longirostris, determine its biological features, and evaluate its risk to public health. Strain LL2208 was tested for molecular identification, challenge, string, biofilm formation, and antimicrobial susceptibility. Furthermore, the whole genome of the strain was sequenced and analyzed. Based on molecular identification, strain LL2208 was identified as K. variicola. Artificial infection showed that this strain was moderately virulent to L. longirostris with an LD50 = 7.92 × 107 CFU/mL. Antibiotic sensitivity tests showed that this strain was resistant to penicillins, macrolides, aminoglycosides, amphenicols, glycopeptides, and lincosamide, indicating multidrug resistance. Strain LL2208 has a genome size of 5,557,050 bp, with a GC content of 57.38%, harboring 30 antimicrobial resistance genes and numerous virulence-related genes. Its molecular type was ST595-KL16-O5. Collinearity analysis showed that strain LL2208 was highly similar to the human-derived K. variicola strain. In conclusion, the multidrug-resistant and virulent K. variicola strain LL2208 was isolated from fish and may have originated from humans. These results provide a foundation for further studies on the transmission of K. variicola between humans and aquatic animals. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

36. CAC: Confidence-Aware Co-Training for Weakly Supervised Crack Segmentation.

Author

Liang, Fengjiao, Li, Qingyong, Li, Xiaobao, Liu, Yang, and Wang, Wen

Subjects
*COLLABORATIVE learning, *SUPERVISED learning, *GAUSSIAN mixture models
Abstract

Automatic crack segmentation plays an essential role in maintaining the structural health of buildings and infrastructure. Despite the success in fully supervised crack segmentation, the costly pixel-level annotation restricts its application, leading to increased exploration in weakly supervised crack segmentation (WSCS). However, WSCS methods inevitably bring in noisy pseudo-labels, which results in large fluctuations. To address this problem, we propose a novel confidence-aware co-training (CAC) framework for WSCS. This framework aims to iteratively refine pseudo-labels, facilitating the learning of a more robust segmentation model. Specifically, a co-training mechanism is designed and constructs two collaborative networks to learn uncertain crack pixels, from easy to hard. Moreover, the dynamic division strategy is designed to divide the pseudo-labels based on the crack confidence score. Among them, the high-confidence pseudo-labels are utilized to optimize the initialization parameters for the collaborative network, while low-confidence pseudo-labels enrich the diversity of crack samples. Extensive experiments conducted on the Crack500, DeepCrack, and CFD datasets demonstrate that the proposed CAC significantly outperforms other WSCS methods. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Synthetic‐to‐realistic domain adaptation for cold‐start of rail inspection systems.

Author

Huang, Qilong, Wang, Jianzhu, Song, Yixiao, Cui, Wenkai, Li, Hailang, Wang, Shengchun, Dai, Peng, Zhao, Xinxin, and Li, Qingyong

Subjects
DEEP learning, SURFACE defects, INSPECTION & review, IMAGE converters, NEW business enterprises
Abstract

Rail surface defects are potential danger factors for railway systems, and visual inspection of surface defects plays a vital role in rail maintenance. Recently, the methods based on deep learning have been widely used in rail inspection systems, but such systems often face the problem of a lack of defect samples for training deep learning models at start‐up, which is called the cold‐start problem. It is challenging to obtain sufficient defect samples since defects are sparse and even non‐existent for a running railway system. Therefore, a synthetic‐to‐realistic domain adaptation (SRDA) method is proposed for real‐world rail inspection. SRDA adapts synthetic images to look more realistic for reducing the domain gap between synthetic images and realistic rail surface images and obtains translated images that consist of synthetic defect information and realistic rail background. After that, the translated images are used to train a detector for rail inspection of rail surface defects. In order to make the detector more robust to complex backgrounds, SRDA generates images with the same defect‐level semantics but with different texture appearances and makes the detector align these images in the learned feature space. In addition, the synthetic and realistic rail surface defects (SRRSD) dataset containing 20,662 images is built. The experimental results on SRRSD show that SRDA achieves higher detection performance than other established domain adaption methods with 19.0% for F1score${\mathrm{F}}1\ {\mathrm{score}}\ $ and 26.7% for average precision. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results