Search

Your search keyword '"Hou, Xiaonan"' showing total 669 results
Start Over Author "Hou, Xiaonan"
669 results on '"Hou, Xiaonan"'

1. Element-wise Multiplication Based Deeper Physics-Informed Neural Networks

Author

Jiang, Feilong, Hou, Xiaonan, and Xia, Min

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing
Abstract

As a promising framework for resolving partial differential equations (PDEs), Physics-Informed Neural Networks (PINNs) have received widespread attention from industrial and scientific fields. However, lack of expressive ability and initialization pathology issues are found to prevent the application of PINNs in complex PDEs. In this work, we propose Deeper Physics-Informed Neural Network (Deeper-PINN) to resolve these issues. The element-wise multiplication operation is adopted to transform features into high-dimensional, non-linear spaces. Benefiting from element-wise multiplication operation, Deeper-PINNs can alleviate the initialization pathologies of PINNs and enhance the expressive capability of PINNs. The proposed structure is verified on various benchmarks. The results show that Deeper-PINNs can effectively resolve the initialization pathology and exhibit strong expressive ability.

Published
2024

2. Spatio-temporal Attention-based Hidden Physics-informed Neural Network for Remaining Useful Life Prediction

Author

Jiang, Feilong, Hou, Xiaonan, and Xia, Min

Subjects
Electrical Engineering and Systems Science - Systems and Control, Computer Science - Machine Learning
Abstract

Predicting the Remaining Useful Life (RUL) is essential in Prognostic Health Management (PHM) for industrial systems. Although deep learning approaches have achieved considerable success in predicting RUL, challenges such as low prediction accuracy and interpretability pose significant challenges, hindering their practical implementation. In this work, we introduce a Spatio-temporal Attention-based Hidden Physics-informed Neural Network (STA-HPINN) for RUL prediction, which can utilize the associated physics of the system degradation. The spatio-temporal attention mechanism can extract important features from the input data. With the self-attention mechanism on both the sensor dimension and time step dimension, the proposed model can effectively extract degradation information. The hidden physics-informed neural network is utilized to capture the physics mechanisms that govern the evolution of RUL. With the constraint of physics, the model can achieve higher accuracy and reasonable predictions. The approach is validated on a benchmark dataset, demonstrating exceptional performance when compared to cutting-edge methods, especially in the case of complex conditions.

Published
2024

3. Densely Multiplied Physics Informed Neural Networks

Author

Jiang, Feilong, Hou, Xiaonan, and Xia, Min

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

Although physics-informed neural networks (PINNs) have shown great potential in dealing with nonlinear partial differential equations (PDEs), it is common that PINNs will suffer from the problem of insufficient precision or obtaining incorrect outcomes. Unlike most of the existing solutions trying to enhance the ability of PINN by optimizing the training process, this paper improved the neural network architecture to improve the performance of PINN. We propose a densely multiply PINN (DM-PINN) architecture, which multiplies the output of a hidden layer with the outputs of all the behind hidden layers. Without introducing more trainable parameters, this effective mechanism can significantly improve the accuracy of PINNs. The proposed architecture is evaluated on four benchmark examples (Allan-Cahn equation, Helmholtz equation, Burgers equation and 1D convection equation). Comparisons between the proposed architecture and different PINN structures demonstrate the superior performance of the DM-PINN in both accuracy and efficiency., Comment: 15 pages, 9 figures

Published
2024

5. Role of macrophages in pulmonary blood-air barrier impairment induced by PM2.5 exposure

Author

YAO Mengfei, WANG Guozhen, and HOU Xiaonan

Subjects
macrophages, pm2.5, blood-air barrier, pulmonary alveoli, Medicine (General), R5-920
Abstract

Objective To investigate the role of macrophages in the process of fine particulate matter (PM2.5) exposure induced damage to pulmonary blood-air barrier. Methods Eighteen male BALB/C mice (aged of 10 weeks, weighing 24~27 g) were randomly divided into control group and low- and high-dose PM2.5 exposure groups (receiving 1.8 and 16.2 mg/kg, respectively), with 6 mice in each group. The control group received tracheal instillations of normal saline on days 1, 4, and 7, whereas the exposure groups were administered corresponding dose of PM2.5 exposure at the same time points. In 24 h after last exposure, pathological changes in the lung tissues were observed, and the contents of total protein (TP), lactate dehydrogenase (LDH), and alkaline phosphatase (AKP) in bronchoalveolar lavage fluid (BALF), and F4/80 protein level in lung tissue were measured to evaluate the blood-air barrier damage and macrophage infiltration within the lung tissues. Additionally, an in vitro model of the blood-air barrier was established using A549 alveolar epithelial cells and EA.hy926 vascular endothelial cells. In combination with a THP-1 macrophage model, the supernatant PM2.5 supernatant, macrophage supernatant, and PM2.5-macrophage supernatant were incubated with the barrier model for 24 h, respectively. Transmembrane electrical resistance (TEER), sodium fluorescein permeability of the barrier model, and LDH release from the barrier cells were measured to ascertain the extent of macrophage-mediated enhancement in barrier damage induced by PM2.5 exposure. Furthermore, the expression of inflammatory cytokines, such as TNF-α, IL-1β, IL-6, and IL-8 in the macrophages after PM2.5 exposure was analyzed with quantitative real-time PCR (qPCR) and enzyme-linked immunosorbent assay (ELISA). Results PM2.5 exposure induced lung tissue damage in mice in a dose-dependent manner, significantly elevated the contents of TP, LDH and AKP in the BALF and caused marked infiltration of macrophages into the lung tissue, especially the high-dose exposure when compared with the mice from the control group (P

Published
2024
Full Text
View/download PDF

12. SPOP mutation induces DNA methylation via stabilizing GLP/G9a.

Author

Zhang, Jianong, Gao, Kun, Xie, Hongyan, Wang, Dejie, Zhang, Pingzhao, Wei, Ting, Yan, Yuqian, Pan, Yunqian, Ye, Wenbin, Chen, Huifen, Shi, Qing, Li, Yao, Zhao, Shi-Min, Hou, Xiaonan, Weroha, Saravut, Wang, Yuzhuo, Zhang, Jun, Karnes, R, He, Housheng, Wang, Liguo, Wang, Chenji, and Huang, Haojie

Subjects
Animals, Antineoplastic Combined Chemotherapy Protocols, Azacitidine, Cell Line, Tumor, DNA (Cytosine-5-)-Methyltransferases, DNA Methylation, Docetaxel, Down-Regulation, Drug Resistance, Neoplasm, Drug Synergism, Epigenesis, Genetic, Gene Expression Regulation, Neoplastic, Genes, Tumor Suppressor, Histocompatibility Antigens, Histone-Lysine N-Methyltransferase, Humans, Male, Mice, Mutation, Nuclear Proteins, Prostatic Neoplasms, Protein Stability, Proteolysis, Repressor Proteins, Xenograft Model Antitumor Assays
Abstract

Mutations in SPOP E3 ligase gene are reportedly associated with genome-wide DNA hypermethylation in prostate cancer (PCa) although the underlying mechanisms remain elusive. Here, we demonstrate that SPOP binds and promotes polyubiquitination and degradation of histone methyltransferase and DNMT interactor GLP. SPOP mutation induces stabilization of GLP and its partner protein G9a and aberrant upregulation of global DNA hypermethylation in cultured PCa cells and primary PCa specimens. Genome-wide DNA methylome analysis shows that a subset of tumor suppressor genes (TSGs) including FOXO3, GATA5, and NDRG1, are hypermethylated and downregulated in SPOP-mutated PCa cells. DNA methylation inhibitor 5-azacytidine effectively reverses expression of the TSGs examined, inhibits SPOP-mutated PCa cell growth in vitro and in mice, and enhances docetaxel anti-cancer efficacy. Our findings reveal the GLP/G9a-DNMT module as a mediator of DNA hypermethylation in SPOP-mutated PCa. They suggest that SPOP mutation could be a biomarker for effective treatment of PCa with DNA methylation inhibitor alone or in combination with taxane chemotherapeutics.

Published
2021

29. Behavioral Changes During COVID-19 Omicron Variant Infection on Children with Autism Spectrum Disorder in China.

Author

Ye, Fang, Hou, Xiaonan, Chen, Jie, Qin, Hui, Xu, Xiaojing, Liu, Die, Liu, Jing, Sun, Qi, Liu, Haiyan, Hu, Fang, Zhou, Yuwan, Xu, Pengfei, and Zhang, Qi

Abstract

Objective of this study was to investigate the behavioral changes in the core features and challenging behaviors of children with Autism Spectrum Disorder (ASD) during the COVID-19 Omicron wave (from December 2022 to January 2023) in China. Patients and Methods: A total of 515 caregivers of children with ASD completed an online survey. This survey was designed to assess the sociodemographic characteristics of the children and their caregivers, the clinical features of COVID-19, the manifestation of core ASD features and challenging behaviors, and the alterations in daily life following the COVID-19 Omicron variant wave. Results: The children with ASD had an average age of 5.4 years, with 79.6% being male. After the Omicron wave, the proportions of participants with worsening core ASD features and challenging behaviors were 22.9% and 37.1%, respectively. Sleep disorders (20.0%), eating problems (18.6%), and inattentive symptoms (17.5%) were the most frequently reported worsening behaviors. The factors associated with the worsening of core ASD features included infection with the Omicron variant of COVID-19, reduced outdoor activity, and a lower score of caregiver health-related quality of life (HRQoL). The worsening of challenging behaviors was associated with infection with the Omicron variant of COVID-19, a lower frequency of rehabilitation training, and a lower score of HRQoL. Conclusion: The outbreak of the COVID-19 Omicron variant had an impact on the behaviors of autistic children. The behavior changes in core ASD features and challenging behaviors differed and were associated with COVID-19 infection and other factors. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

33. Lestaurtinib′s antineoplastic activity converges on JAK/STAT signaling to inhibit advanced forms of therapy resistant ovarian cancer

Author

Rodman, Esther P B, primary, Emch, Michael J, additional, Hou, Xiaonan, additional, Bajaj, Archit, additional, Pearson, Nicole A, additional, John, August, additional, Ortiz, Yamillie, additional, Bass, Adam D, additional, Baldassarre, Gustavo, additional, Kaufmann, Scott H, additional, Weroha, Saravut John, additional, and Hawse, John R, additional

Published
2024
Full Text
View/download PDF

40. Salicylates enhance CRM1 inhibitor antitumor activity by induction of S-phase arrest and impairment of DNA-damage repair

Author

Abeykoon, Jithma P., Wu, Xiaosheng, Nowakowski, Kevin E., Dasari, Surendra, Paludo, Jonas, Weroha, S. John, Hu, Chunling, Hou, Xiaonan, Sarkaria, Jann N., Mladek, Ann C., Phillips, Jessica L., Feldman, Andrew L., Ravindran, Aishwarya, King, Rebecca L., Boysen, Justin, Stenson, Mary J., Carr, Ryan M., Manske, Michelle K., Molina, Julian R., Kapoor, Prashant, Parikh, Sameer A., Kumar, Shaji, Robinson, Steven I., Yu, Jia, Boughey, Judy C., Wang, Liewei, Goetz, Matthew P., Couch, Fergus J., Patnaik, Mrinal M., and Witzig, Thomas E.

Published
2021
Full Text
View/download PDF

42. Element-wise Multiplication Based Physics-informed Neural Networks

Author

Jiang, Feilong, Hou, Xiaonan, Xia, Min, Jiang, Feilong, Hou, Xiaonan, and Xia, Min

Abstract

As a promising framework for resolving partial differential equations (PDEs), physics-informed neural networks (PINNs) have received widespread attention from industrial and scientific fields. However, lack of expressive ability and initialization pathology issues are found to prevent the application of PINNs in complex PDEs. In this work, we propose Element-wise Multiplication Based Physics-informed Neural Networks (EM-PINNs) to resolve these issues. The element-wise multiplication operation is adopted to transform features into high-dimensional, non-linear spaces, which effectively enhance the expressive capability of PINNs. Benefiting from element-wise multiplication operation, EM-PINNs can eliminate the initialization pathologies of PINNs. The proposed structure is verified on various benchmarks. The results show that EM-PINNs have strong expressive ability.

Published
2024

43. Building a Research-Quality Copy Number Variation Data Repository for Translational Research

Author

Wang, Chen, Moore, Raymond M., Evans, Jared M., Hou, Xiaonan, John Weroha, S., Jiang, Guoqian, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Gadepally, Vijay, editor, Mattson, Timothy, editor, Stonebraker, Michael, editor, Wang, Fusheng, editor, Luo, Gang, editor, and Teodoro, George, editor

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results