Search

Your search keyword '"Chen, Zhengwei"' showing total 584 results
Start Over Author "Chen, Zhengwei"
584 results on '"Chen, Zhengwei"'

2. Adaptive Graph Convolutional Subspace Clustering

Author

Wei, Lai, Chen, Zhengwei, Yin, Jun, Zhu, Changming, Zhou, Rigui, and Liu, Jin

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Spectral-type subspace clustering algorithms have shown excellent performance in many subspace clustering applications. The existing spectral-type subspace clustering algorithms either focus on designing constraints for the reconstruction coefficient matrix or feature extraction methods for finding latent features of original data samples. In this paper, inspired by graph convolutional networks, we use the graph convolution technique to develop a feature extraction method and a coefficient matrix constraint simultaneously. And the graph-convolutional operator is updated iteratively and adaptively in our proposed algorithm. Hence, we call the proposed method adaptive graph convolutional subspace clustering (AGCSC). We claim that by using AGCSC, the aggregated feature representation of original data samples is suitable for subspace clustering, and the coefficient matrix could reveal the subspace structure of the original data set more faithfully. Finally, plenty of subspace clustering experiments prove our conclusions and show that AGCSC outperforms some related methods as well as some deep models., Comment: Accepted by CVPR 2023

Published
2023

5. Contributors

Author

Chen, Zhengwei, primary, Chintapula, Uday, additional, Dudala, Sohan, additional, Goel, Sanket, additional, Gopinathan, Kaustav, additional, Gupta, Kshitiz, additional, Jain, Vandana, additional, Jakkam, Leela Kishan, additional, Javed, Arshad, additional, Kalambe, Jayu, additional, Karuppusamy, Jayaprakash, additional, Kishori, Kajal, additional, Ko, Jina, additional, Kolluri, Rajesh, additional, Lim, Jianhua, additional, Mishra, Avanish, additional, Mondal, Pranab K., additional, Morales, Renee-Tyler, additional, Oh, Daniel, additional, Patrikar, Rajendra M., additional, Pyne, Sumanta, additional, Reynolds, David E., additional, Roh, Yoon Ho, additional, Shyam, Sudip, additional, Swain, Jyotiranjan, additional, Wankawala, Dhruvkumar H., additional, and Wereley, Steven T., additional

Published
2024
Full Text
View/download PDF

16. Development of a dynamic gas lock inhibited model for EUV-induced carbon deposition.

Author

Hao, Ming, Teng, Shuai, Liu, Jiaxing, Xie, Yuanhua, Ba, Dechun, Bian, Xin, Ba, Yaoshuai, Chen, Zhengwei, and Liu, Kun

Abstract

The optical surface of extreme ultraviolet (EUV) lithography machines is highly vulnerable to contamination by hydrocarbons, resulting in the formation of carbon deposits that significantly degrade the quality and efficiency of lithography. The dynamic gas lock (DGL) has been proven as an effective approach to alleviate carbon deposition. However, the majority of existing studies on carbon deposition neglect the influence of the DGL. This paper is dedicated to investigating the phenomena of hydrocarbon adsorption, desorption, and cleavage with considering the effects of the DGL. A comprehensive mathematical model of the carbon deposition process is established, and the impact of radiation intensity, temperature, and hydrocarbon types on the depositing rate is considered. The results suggest that the primary cause of carbon deposition is the direct cracking of hydrocarbons induced by photons with a wavelength range between 12.5 and 14.5 nm. Additionally, it has been observed that the carbon deposition rate decreases exponentially as clean gas flow increases when EUV radiation intensity exceeds 50 mW/mm2. Conversely, at low EUV radiation intensity, clean gas flow has little effect on the carbon deposition rate. An effective approach to mitigate carbon deposition is to elevate the temperature of the optical surface and employ light hydrocarbon materials in the EUV process. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

37. Fractional amplitude of low-frequency fluctuation and voxel-mirrored homotopic connectivity in patients with persistent postural-perceptual dizziness: resting-state functional magnetic resonance imaging study

Author

Liu, Yueji, primary, Peng, Xiyu, additional, Lin, Cunxin, additional, Liu, Dan, additional, Sun, Yang, additional, Huang, Feiran, additional, Liu, Tengfei, additional, Xiao, Lijie, additional, Wei, Xiue, additional, Wang, Kai, additional, Chen, Zhengwei, additional, and Rong, Liangqun, additional

Published
2024
Full Text
View/download PDF

49. Enhancing the accuracy of physics-informed neural networks for indoor airflow simulation with experimental data and Reynolds-averaged Navier–Stokes turbulence model.

Author

Zhang, Chi, Wen, Chih-Yung, Jia, Yuan, Juan, Yu-Hsuan, Lee, Yee-Ting, Chen, Zhengwei, Yang, An-Shik, and Li, Zhengtong

Subjects
AIR flow, TURBULENCE, DEEP learning, DIFFERENTIAL equations, RESEARCH personnel, ACQUISITION of data
Abstract

Physics-informed neural network (PINN) has aroused broad interest among fluid simulation researchers in recent years, representing a novel paradigm in this area where governing differential equations are encoded to provide a hybrid physics-based and data-driven deep learning framework. However, the lack of enough validations on more complex flow problems has restricted further development and application of PINN. Our research applies the PINN to simulate a two-dimensional indoor turbulent airflow case to address the issue. Although it is still quite challenging for the PINN to reach an ideal accuracy for the problem through a single purely physics-driven training, our research finds that the PINN prediction accuracy can be significantly improved by exploiting its ability to assimilate high-fidelity data during training, by which the prediction accuracy of PINN is enhanced by 53.2% for pressure, 34.6% for horizontal velocity, and 40.4% for vertical velocity, respectively. Meanwhile, the influence of data points number is also studied, which suggests a balance between prediction accuracy and data acquisition cost can be reached. Last but not least, applying Reynolds-averaged Navier–Stokes (RANS) equations and turbulence model has also been proved to improve prediction accuracy remarkably. After embedding the standard k–ε model to the PINN, the prediction accuracy was enhanced by 82.9% for pressure, 59.4% for horizontal velocity, and 70.5% for vertical velocity, respectively. These results suggest a promising step toward applications of PINN to more complex flow configurations. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results