Search

Your search keyword '"DAI Haoran"' showing total 155 results
Start Over Author "DAI Haoran"
155 results on '"DAI Haoran"'

2. Registration-Free Hybrid Learning Empowers Simple Multimodal Imaging System for High-quality Fusion Detection

Author

Guan, Yinghan, Dai, Haoran, Yu, Zekuan, Wang, Shouyu, and Gu, Yuanjie

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Multimodal fusion detection always places high demands on the imaging system and image pre-processing, while either a high-quality pre-registration system or image registration processing is costly. Unfortunately, the existing fusion methods are designed for registered source images, and the fusion of inhomogeneous features, which denotes a pair of features at the same spatial location that expresses different semantic information, cannot achieve satisfactory performance via these methods. As a result, we propose IA-VFDnet, a CNN-Transformer hybrid learning framework with a unified high-quality multimodal feature matching module (AKM) and a fusion module (WDAF), in which AKM and DWDAF work in synergy to perform high-quality infrared-aware visible fusion detection, which can be applied to smoke and wildfire detection. Furthermore, experiments on the M3FD dataset validate the superiority of the proposed method, with IA-VFDnet achieving the best detection performance than other state-of-the-art methods under conventional registered conditions. In addition, the first unregistered multimodal smoke and wildfire detection benchmark is openly available in this letter.

Published
2023

3. voxel2vec: A Natural Language Processing Approach to Learning Distributed Representations for Scientific Data

Author

He, Xiangyang, Tao, Yubo, Yang, Shuoliu, Dai, Haoran, and Lin, Hai

Subjects
Computer Science - Machine Learning, Computer Science - Human-Computer Interaction, I.6.9, I.2.7
Abstract

Relationships in scientific data, such as the numerical and spatial distribution relations of features in univariate data, the scalar-value combinations' relations in multivariate data, and the association of volumes in time-varying and ensemble data, are intricate and complex. This paper presents voxel2vec, a novel unsupervised representation learning model, which is used to learn distributed representations of scalar values/scalar-value combinations in a low-dimensional vector space. Its basic assumption is that if two scalar values/scalar-value combinations have similar contexts, they usually have high similarity in terms of features. By representing scalar values/scalar-value combinations as symbols, voxel2vec learns the similarity between them in the context of spatial distribution and then allows us to explore the overall association between volumes by transfer prediction. We demonstrate the usefulness and effectiveness of voxel2vec by comparing it with the isosurface similarity map of univariate data and applying the learned distributed representations to feature classification for multivariate data and to association analysis for time-varying and ensemble data., Comment: Accepted by IEEE Transaction on Visualization and Computer Graphics (TVCG)

Published
2022

5. Physics Driven Deep Retinex Fusion for Adaptive Infrared and Visible Image Fusion

Author

Gu, Yuanjie, Xiao, Zhibo, Guan, Yinghan, Dai, Haoran, Liu, Cheng, Xue, Liang, and Wang, Shouyu

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

Convolutional neural networks have turned into an illustrious tool for image fusion and super-resolution. However, their excellent performance cannot work without large fixed-paired datasets; and additionally, these high-demanded ground truth data always cannot be obtained easily in fusion tasks. In this study, we show that, the structures of generative networks capture a great deal of image feature priors, and then these priors are sufficient to reconstruct high-quality fused super-resolution result using only low-resolution inputs. By this way, we propose a novel self-supervised dataset-free method for adaptive infrared (IR) and visible (VIS) image super-resolution fusion named Deep Retinex Fusion (DRF). The key idea of DRF is first generating component priors which are disentangled from physical model using our designed generative networks ZipperNet, LightingNet and AdjustingNet, then combining these priors which captured by networks via adaptive fusion loss functions based on Retinex theory, and finally reconstructing the super-resolution fusion results. Furthermore, in order to verify the effectiveness of our reported DRF, both qualitative and quantitative experiments via comparing with other state-of-the-art methods are performed using different test sets. These results prove that, comparing with large datasets trained methods, DRF which works without any dataset achieves the best super-resolution fusion performance; and more importantly, DRF can adaptively balance IR and VIS information and has good noise immunity. DRF codes are open source available at https://github.com/GuYuanjie/Deep-Retinex-fusion., Comment: 20 pages, 9 figures

Published
2021

6. Deep Fusion Prior for Plenoptic Super-Resolution All-in-Focus Imaging

Author

Gu, Yuanjie, Guan, Yinghan, Xiao, Zhibo, Dai, Haoran, Liu, Cheng, and Wang, Shouyu

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

Multi-focus image fusion (MFIF) and super-resolution (SR) are the inverse problem of imaging model, purposes of MFIF and SR are obtaining all-in-focus and high-resolution 2D mapping of targets. Though various MFIF and SR methods have been designed; almost all the them deal with MFIF and SR separately. This paper unifies MFIF and SR problems in the physical perspective as the multi-focus image super resolution fusion (MFISRF), and we propose a novel unified dataset-free unsupervised framework named deep fusion prior (DFP) based-on deep image prior (DIP) to address such MFISRF with single model. Experiments have proved that our proposed DFP approaches or even outperforms those state-of-art MFIF and SR method combinations. To our best knowledge, our proposed work is a dataset-free unsupervised method to simultaneously implement the multi-focus fusion and super-resolution task for the first time. Additionally, DFP is a general framework, thus its networks and focus measurement tactics can be continuously updated to further improve the MFISRF performance. DFP codes are open source available at http://github.com/GuYuanjie/DeepFusionPrior., Comment: 24 pages

Published
2021
Full Text
View/download PDF

13. Efficacy and safety of Mahuang Fuzi and Shenzhuo Decoction for treatment of primary membranous nephropathy: a multicenter prospective trial.

Author

Zhang, Naiqian, Jiang, Hanxue, Dai, Haoran, Huang, Shuxian, Zhao, Qihan, Zhang, Na, Liu, Wenbin, Dong, Zhaocheng, Gao, Yu, Dong, Xuan, Hu, Yuehong, Hou, Fanyu, Rui, Hongliang, Liu, Qingquan, and Liu, Baoli

Subjects
KIDNEY diseases, TREATMENT duration, NEPHROTIC syndrome, DISEASE remission, REGRESSION analysis
Abstract

This study aims to undertake a comprehensive assessment of the effectiveness and safety profile of Mahuang Fuzi and Shenzhuo Decoction (MFSD) in the management of primary membranous nephropathy (PMN), within the context of a prospective clinical investigation. A multicenter, open-label clinical trial was executed on patients diagnosed with PMN. These individuals were subjected to MFSD therapy for a duration of at least 24 months, with primary outcome of clinical remission rates. The Cox regression analysis was employed to discern the pertinent risk factors exerting influence on the efficacy of MFSD treatment, with scrupulous monitoring of any adverse events. The study comprised 198 participants in total. Following 24 months of treatment, the remission rate was 58.6% (116/198). Among the subgroup of 130 participants subjected to a 36-month follow-up, the remission rate reached 70% (91/130). Subgroup analysis revealed that neither a history of immunosuppressive therapy (HIST) nor an age threshold of ≥60 years exhibited a statistically significant impact on the remission rate at the 24-month mark (p >.05). Multivariate Cox regression analyses elucidated HIST, nephrotic syndrome, or mass proteinuria, and a high-risk classification as noteworthy risk factors in the context of MFSD treatment. Remarkably, no fatalities resulting from side effects were documented throughout the study's duration. This trial establishes the efficacy of MFSD as a treatment modality for membranous nephropathy. MFSD demonstrates a favorable side effect profile, and remission rates are consistent across patients, irrespective of HIST and age categories. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

18. Cluster analysis to identify long COVID phenotypes using129Xe magnetic resonance imaging: a multicentre evaluation

Author

Eddy, Rachel L., primary, Mummy, David, additional, Zhang, Shuo, additional, Dai, Haoran, additional, Bechtel, Aryil, additional, Schmidt, Alexandra, additional, Frizzell, Bradie, additional, Gerayeli, Firoozeh V., additional, Leipsic, Jonathon A., additional, Leung, Janice M., additional, Driehuys, Bastiaan, additional, Que, Loretta G., additional, Castro, Mario, additional, Sin, Don D., additional, and Niedbalski, Peter J., additional

Published
2024
Full Text
View/download PDF

23. Corrigendum: MicroRNAs: Potential mediators between particulate matter 2.5 and Th17/Treg immune disorder in primary membranous nephropathy

Author

Zhou, Xiaoshan, primary, Dai, Haoran, additional, Jiang, Hanxue, additional, Rui, Hongliang, additional, Liu, Wenbin, additional, Dong, Zhaocheng, additional, Zhang, Na, additional, Zhao, Qihan, additional, Feng, Zhendong, additional, Hu, Yuehong, additional, Hou, Fanyu, additional, Zheng, Yang, additional, and Liu, Baoli, additional

Published
2023
Full Text
View/download PDF

31. A color mapping method based on global statistical and local spacial characteristics.

Author

LIU Huan, MA Hao, DAI Haoran, TAO Yubo, and LIN Hai

Subjects
SCALAR field theory
Abstract

To give a better assistance to users in the understanding and analyzing of data, this paper proposes a new color mapping method based on global statistical and focal spacial characteristics, aiming at emphasis of both the global patterns and the boundary information of data. Our method employs Jenks natural break method to minimize control points in the color map and maximizes the color differences between boundary points and its neighbors to obtain the color napping. The effectiveness of our method Is verified via qualitative experiments and user researches on the 2D scalar field data. [ABSTRACT FROM AUTHOR]

Published
2023

32. voxel2vec: A Natural Language Processing Approach to Learning Distributed Representations for Scientific Data

Author

He, Xiangyang, Tao, Yubo, Yang, Shuoliu, Dai, Haoran, and Lin, Hai

Abstract

Relationships in scientific data, such as the numerical and spatial distribution relations of features in univariate data, the scalar-value combinations’ relations in multivariate data, and the association of volumes in time-varying and ensemble data, are intricate and complex. This paper presents voxel2vec, a novel unsupervised representation learning model, which is used to learn distributed representations of scalar values/scalar-value combinations in a low-dimensional vector space. Its basic assumption is that if two scalar values/scalar-value combinations have similar contexts, they usually have high similarity in terms of features. By representing scalar values/scalar-value combinations as symbols, voxel2vec learns the similarity between them in the context of spatial distribution and then allows us to explore the overall association between volumes by transfer prediction. We demonstrate the usefulness and effectiveness of voxel2vec by comparing it with the isosurface similarity map of univariate data and applying the learned distributed representations to feature classification for multivariate data and to association analysis for time-varying and ensemble data.

Published
2023
Full Text
View/download PDF

33. MicroRNAs: Potential mediators between particulate matter 2.5 and Th17/Treg immune disorder in primary membranous nephropathy

Author

Zhou, Xiaoshan, primary, Dai, Haoran, additional, Jiang, Hanxue, additional, Rui, Hongliang, additional, Liu, Wenbin, additional, Dong, Zhaocheng, additional, Zhang, Na, additional, Zhao, Qihan, additional, Feng, Zhendong, additional, Hu, Yuehong, additional, Hou, Fanyu, additional, Zheng, Yang, additional, and Liu, Baoli, additional

Published
2022
Full Text
View/download PDF

34. Level of interleukin-35 in patients with idiopathic membranous nephropathy and its predictive value for remission time

Author

Zhang, Na, primary, Dai, Haoran, additional, Dong, Xuan, additional, Liu, Wenbin, additional, Jiang, Hanxue, additional, Zhao, Qihan, additional, Gao, Yu, additional, Feng, Zhendong, additional, Dong, Zhaocheng, additional, Hu, Yuehong, additional, Huang, Guangrui, additional, Rui, Hongliang, additional, and Liu, Baoli, additional

Published
2022
Full Text
View/download PDF

37. The Ameliorative Effect of Mahuang Fuzi and Shenzhuo Decoction on Membranous Nephropathy of Rodent Model is Associated With Autophagy and Wnt/β-Catenin Pathway

Author

Gao, Yu, primary, Dai, Haoran, additional, Zhang, Na, additional, Jiang, Hanxue, additional, Zhang, Zihan, additional, Feng, Zhendong, additional, Dong, Zhaocheng, additional, Liu, Wenbin, additional, Liu, Fei, additional, Dong, Xuan, additional, Zhao, Qihan, additional, Zhou, Xiaoshan, additional, Du, Jieli, additional, Zhang, Naiqian, additional, Rui, Hongliang, additional, and Liu, Baoli, additional

Published
2022
Full Text
View/download PDF

43. Effect of Mahuang Fuzi and Shenzhuo Decoction on Idiopathic Membranous Nephropathy: A Multicenter, Nonrandomized, Single-Arm Clinical Trial

Author

Dong, Zhaocheng, primary, Dai, Haoran, additional, Gao, Yu, additional, Jiang, Hanxue, additional, Liu, Meiqi, additional, Liu, Fei, additional, Liu, Wenbin, additional, Feng, Zhendong, additional, Zhang, Xiaoyan, additional, Ren, Aijie, additional, Li, Xiaolan, additional, Rui, Hongliang, additional, Tian, Xuefei, additional, Li, Guiming, additional, and Liu, Baoli, additional

Published
2021
Full Text
View/download PDF

44. Calibration and Testing of Small High-Resolution Transition Edge Sensor Microcalorimeters With Optical Photons

Author

Jaeckel, Felix T., primary, Ambarish, C. V., additional, Dai, Haoran, additional, Liu, Shukai, additional, McCammon, Dan, additional, McPheron, Mari, additional, Nelms, Kari L., additional, Roy, Avirup, additional, Stueber, Haley R., additional, Bandler, Simon R., additional, Chervenak, James A., additional, Sakai, Kazuhiro, additional, and Smith, Stephen J., additional

Published
2021
Full Text
View/download PDF

47. Helper T Cells in Idiopathic Membranous Nephropathy

Author

Zhao, Qihan, primary, Dai, Haoran, additional, Liu, Xianli, additional, Jiang, Hanxue, additional, Liu, Wenbin, additional, Feng, Zhendong, additional, Zhang, Na, additional, Gao, Yu, additional, Dong, Zhaocheng, additional, Zhou, Xiaoshan, additional, Du, Jieli, additional, Zhang, Naiqian, additional, Rui, Hongliang, additional, Yuan, Li, additional, and Liu, Baoli, additional

Published
2021
Full Text
View/download PDF

49. The Potential Role of Regulatory B Cells in Idiopathic Membranous Nephropathy

Author

Dong, Zhaocheng, Liu, Zhiyuan, Dai, Haoran, Liu, Wenbin, Feng, Zhendong, Zhao, Qihan, Gao, Yu, Liu, Fei, Zhang, Na, Dong, Xuan, Zhou, Xiaoshan, Du, Jieli, Huang, Guangrui, Tian, Xuefei, and Liu, Baoli

Subjects
Article Subject
Abstract

Regulatory B cells (Breg) are widely regarded as immunomodulatory cells which play an immunosuppressive role. Breg inhibits pathological autoimmune response by secreting interleukin-10 (IL-10), transforming growth factor-β (TGF-β), and adenosine and through other ways to prevent T cells and other immune cells from expanding. Recent studies have shown that different inflammatory environments induce different types of Breg cells, and these different Breg cells have different functions. For example, Br1 cells can secrete IgG4 to block autoantigens. Idiopathic membranous nephropathy (IMN) is an autoimmune disease in which the humoral immune response is dominant and the cellular immune response is impaired. However, only a handful of studies have been done on the role of Bregs in this regard. In this review, we provide a brief overview of the types and functions of Breg found in human body, as well as the abnormal pathological and immunological phenomena in IMN, and propose the hypothesis that Breg is activated in IMN patients and the proportion of Br1 can be increased. Our review aims at highlighting the correlation between Breg and IMN and proposes potential mechanisms, which can provide a new direction for the discovery of the pathogenesis of IMN, thus providing a new strategy for the prevention and early treatment of IMN.

Published
2020
Full Text
View/download PDF

50. Mechanism of herbal medicine on hypertensive nephropathy (Review)

Author

Dong, Zhaocheng, primary, Dai, Haoran, additional, Feng, Zhandong, additional, Liu, Wenbin, additional, Gao, Yu, additional, Liu, Fei, additional, Zhang, Zihan, additional, Zhang, Na, additional, Dong, Xuan, additional, Zhao, Qihan, additional, Zhou, Xiaoshan, additional, Du, Jieli, additional, and Liu, Baoli, additional

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results