Search

Your search keyword '"Tian, Dan"' showing total 523 results
Start Over Author "Tian, Dan" Publication Year Range Last 3 years
523 results on '"Tian, Dan"'

8. Cyclegan Network for Sheet Metal Welding Drawing Translation

Author

Song, Zhiwei, Yao, Hui, Tian, Dan, and Zhan, Gaohui

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

In intelligent manufacturing, the quality of machine translation engineering drawings will directly affect its manufacturing accuracy. Currently, most of the work is manually translated, greatly reducing production efficiency. This paper proposes an automatic translation method for welded structural engineering drawings based on Cyclic Generative Adversarial Networks (CycleGAN). The CycleGAN network model of unpaired transfer learning is used to learn the feature mapping of real welding engineering drawings to realize automatic translation of engineering drawings. U-Net and PatchGAN are the main network for the generator and discriminator, respectively. Based on removing the identity mapping function, a high-dimensional sparse network is proposed to replace the traditional dense network for the Cyclegan generator to improve noise robustness. Increase the residual block hidden layer to increase the resolution of the generated graph. The improved and fine-tuned network models are experimentally validated, computing the gap between real and generated data. It meets the welding engineering precision standard and solves the main problem of low drawing recognition efficiency in the welding manufacturing process. The results show. After training with our model, the PSNR, SSIM and MSE of welding engineering drawings reach about 44.89%, 99.58% and 2.11, respectively, which are superior to traditional networks in both training speed and accuracy.

Published
2022

9. RT-RPA-PfAgo detection platform for one-tube simultaneous typing diagnosis of human respiratory syncytial virus

Author

Jia-Yu Liao, Xue-Yong Feng, Jie-Xiu Zhang, Tian-Dan Yang, Min-Xuan Zhan, Yong-Mei Zeng, Wei-Yi Huang, Hao-Bin Lian, Lin Ke, Si-Si Cai, Nan-Fei Zhang, Jin-Wen Fang, Xiao-Ying Cai, Jun-Duo Chen, Guang-Yu Lin, Li-Yun Lin, Wei-Zhong Chen, Yu-Yan Liu, Fei-Fei Huang, Chuang-Xing Lin, and Min Lin

Subjects
human respiratory syncytial virus (HRSV), typing diagnosis, reverse transcription recombinase polymerase amplification (RT-RPA), pyrococcus furiosus argonaute, point of care (POC), Microbiology, QR1-502
Abstract

Human respiratory syncytial virus (HRSV) is the most prevalent pathogen contributing to acute respiratory tract infections (ARTI) in infants and young children and can lead to significant financial and medical costs. Here, we developed a simultaneous, dual-gene and ultrasensitive detection system for typing HRSV within 60 minutes that needs only minimum laboratory support. Briefly, multiplex integrating reverse transcription-recombinase polymerase amplification (RT-RPA) was performed with viral RNA extracted from nasopharyngeal swabs as a template for the amplification of the specific regions of subtypes A (HRSVA) and B (HRSVB) of HRSV. Next, the Pyrococcus furiosus Argonaute (PfAgo) protein utilizes small 5’-phosphorylated DNA guides to cleave target sequences and produce fluorophore signals (FAM and ROX). Compared with the traditional gold standard (RT-qPCR) and direct immunofluorescence assay (DFA), this method has the additional advantages of easy operation, efficiency and sensitivity, with a limit of detection (LOD) of 1 copy/μL. In terms of clinical sample validation, the diagnostic accuracy of the method for determining the HRSVA and HRSVB infection was greater than 95%. This technique provides a reliable point-of-care (POC) testing for the diagnosis of HRSV-induced ARTI in children and for outbreak management, especially in resource-limited settings.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results