Search

Your search keyword '"Jiao, Yuhang"' showing total 46 results
Start Over Author "Jiao, Yuhang" Publication Year Range Last 50 years
46 results on '"Jiao, Yuhang"'

2. Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

Author

Bail, Lu, Cui, Lixin, Jiao, Yuhang, Rossi, Luca, and Hancock, Edwin R.

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model., Comment: This is an extension work for journals based on the previous work of arXiv:1904.04238v1

Published
2019
Full Text
View/download PDF

3. Learning Vertex Convolutional Networks for Graph Classification

Author

Bai, Lu, Cui, Lixin, Wu, Shu, Jiao, Yuhang, and Hancock, Edwin R.

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model., Comment: arXiv admin note: text overlap with arXiv:1809.01090

Published
2019

5. Graph Convolutional Neural Networks based on Quantum Vertex Saliency

Author

Bai, Lu, Jiao, Yuhang, Rossi, Luca, Cui, Lixin, Cheng, Jian, and Hancock, Edwin R.

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

Published
2018
Full Text
View/download PDF

6. Insights of mechanism and kinetics of acrylonitrile aqueous precipitation polymerization.

Author

Yan, Huijie, Jiao, Yuhang, Jin, Bingrui, Zhang, Huixuan, Fu, Zhongyu, Jia, Shiling, and Deng, Yunjiao

Subjects
*POLYMERIZATION kinetics, *PRECIPITATION (Chemistry) kinetics, *SCANNING electron microscopy, *ZETA potential, *ACRYLONITRILE
Abstract

Aqueous precipitation polymerization is commonly used in the industry due to its efficient heat dissipation, reaction stability and production flexibility. However, its mechanisms and kinetics are still partially unclear. The ammonium persulfate-ammonium sulfite monohydrate (APS-AS) initiated aqueous phase precipitation polymerization of acrylonitrile (AN) at low concentration was deeply investigated, with the APS initiation system as a control. The apparent kinetic equations for the APS and APS-AS initiation systems were determined to be Rp= K[AN]1.706[(NH4)2S2O8]0.704 and Rp= K[AN]3[(NH4)2S2O8]0.704[(NH4)2S2O3]−1.055, respectively. Monitoring AN distribution in the aqueous and polyacrylonitrile (PAN) phases revealed a rapid transition of the reaction site from the aqueous phase to the PAN phase following polymer precipitation. Zeta potential and primary particle number exposed that the nucleation site disparities between initiation systems led to different predominant factors affecting the polymerization rate. The change in molecular weight during polymerization had a maximum due to its dependence on the monomer concentration. The crystallinity of the product initially increased during polymerization, then decreased and eventually stabilized. Scanning electron microscopy (SEM) revealed that the diameter of the internal particles was larger, while the surface particles were smaller after coagulation. These findings offer crucial insights for optimizing aqueous precipitation polymerization and PAN particle property control. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

7. Learning Aligned-Spatial Graph Convolutional Networks for Graph Classification

Author

Bai, Lu, Jiao, Yuhang, Cui, Lixin, Hancock, Edwin R., Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Brefeld, Ulf, editor, Fromont, Elisa, editor, Hotho, Andreas, editor, Knobbe, Arno, editor, Maathuis, Marloes, editor, and Robardet, Céline, editor

Published
2020
Full Text
View/download PDF

9. An Attributed Graph Embedding Method Using the Tree-Index Algorithm

Author

Jiao, Yuhang, Yang, Yueting, Cui, Lixin, Bai, Lu, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Conte, Donatello, editor, Ramel, Jean-Yves, editor, and Foggia, Pasquale, editor

Published
2019
Full Text
View/download PDF

10. Analyzing Time Series from Chinese Financial Market Using a Linear-Time Graph Kernel

Author

Jiao, Yuhang, Cui, Lixin, Bai, Lu, Wang, Yue, 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, Weikum, Gerhard, Series Editor, Bai, Xiao, editor, Hancock, Edwin R., editor, Ho, Tin Kam, editor, Wilson, Richard C., editor, Biggio, Battista, editor, and Robles-Kelly, Antonio, editor

Published
2018
Full Text
View/download PDF

11. A Preliminary Survey of Analyzing Dynamic Time-Varying Financial Networks Using Graph Kernels

Author

Cui, Lixin, Bai, Lu, Rossi, Luca, Zhang, Zhihong, Jiao, Yuhang, Hancock, Edwin R., 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, Weikum, Gerhard, Series Editor, Bai, Xiao, editor, Hancock, Edwin R., editor, Ho, Tin Kam, editor, Wilson, Richard C., editor, Biggio, Battista, editor, and Robles-Kelly, Antonio, editor

Published
2018
Full Text
View/download PDF

13. Adaptive Feature Selection Based on the Most Informative Graph-Based Features

Author

Cui, Lixin, Jiao, Yuhang, Bai, Lu, Rossi, Luca, Hancock, Edwin R., Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Foggia, Pasquale, editor, Liu, Cheng-Lin, editor, and Vento, Mario, editor

Published
2017
Full Text
View/download PDF

23. 倾斜影像辅助的无人机载LiDAR高陡边坡形变监测

Author

杨耘 Yang Yun, 江万成 Jiang Wancheng, 任超锋 Ren Chaofeng, 马正龙 Ma Zhenglong, 蒲禹池 Pu Yuchi, and 焦宇航 Jiao Yuhang

Subjects
Space and Planetary Science, Aerospace Engineering, Electrical and Electronic Engineering, Atomic and Molecular Physics, and Optics
Published
2023

25. Learning Graph Convolutional Networks Based on Quantum Vertex Information Propagation

Author

Bai, Lu, Jiao, Yuhang, Cui, Lixin, Rossi, Luca, Wang, Yue, Yu, Philip S., and Hancock, Edwin R.

Abstract

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not alter the original spatial position of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We indicate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

Published
2023
Full Text
View/download PDF

26. Surge-Heading Guidance-Based Finite-Time Path Following of Underactuated Marine Vehicles

Author

Ning Wang, Zhuo Sun, Jiao Yuhang, and Guangjie Han

Subjects
Observer (quantum physics), Computer Networks and Communications, Computer science, Underactuation, Path following, Aerospace Engineering, 020302 automobile design & engineering, 02 engineering and technology, Observer (special relativity), Kinematics, Vehicle dynamics, 0203 mechanical engineering, Robustness (computer science), Control theory, Automotive Engineering, Electrical and Electronic Engineering, Surge, Finite time
Abstract

In this paper, a surge-heading guidance-based finite-time path-following control (SHG-FPC) scheme is created for an underactuated marine vehicle with complex unknowns. In lieu of line-of-sight guidance, both surge and heading can be guided by adapting to path-following errors and this can greatly enhance the decision-making autonomy pertaining to guidance of kinematics and dynamics, simultaneously. Complex unknowns can be exactly identified by virtue of the devised finite-time uncertainty observer (FUO), by which FUO-based nonsmooth control laws are able to achieve accurate guidance tracking, and thereby, contributing to entire finite-time path-following performance with strong robustness. Simulation results demonstrate the remarkable performance of the proposed SHG-FPC scheme.

Published
2019

29. 2‐undecanone protects against fine particles‐induced heart inflammation via modulating Nrf2/HO‐1 and NF‐κB pathways.

Author

Jiao, Yuhang, Wang, Shaopeng, Jiang, Liping, Sun, Xiance, Li, Jing, Liu, Xiaofang, Yao, Xiaofeng, Zhang, Cong, Wang, Ningning, Deng, Haoyuan, and Yang, Guang

Subjects
HEART, NUCLEAR factor E2 related factor, HEART injuries, PROTEIN expression, INFLAMMATION, AIR pollution
Abstract

Exposure to air pollution has been closely associated with some cardiovascular disease. One of the mechanisms of PM2.5‐mediated heart injury may be to promote inflammation. We aim to investigate whether the main extract of Houttuynia cordata, 2‐undecanone, can prevent the inflammation caused by PM2.5, and to reveal the underlying mechanisms. The results showed that PM2.5 increased the expression of certain inflammatory cytokines, and caused oxidative damage in BALB/c mice and H9C2 cells. Supplementation with 2‐undecanone attenuated this PM2.5‐induced inflammatory injury and oxidative damage. Further, we elucidated that the protective effect of 2‐undecanone may be associated with NF‐κB and Nrf2/HO‐1 pathways. The NF‐κB pathway was distinctly activated after treated by PM2.5, which can be blocked by 2‐undecanone, accompanied by increasing Nrf2 and HO‐1 levels. To figure out the relationship between NF‐κB and Nrf2/HO‐1 pathways, we knocked down Nrf2 gene. NF‐κB pathway proteins and downstream inflammatory cytokines were significantly increased after treatment with PM2.5, while 2‐undecanone could decrease expression of these proteins. In conclusion, it is possible that 2‐undecanone can induce the expression of the antioxidant enzyme HO‐1 by activating Nrf2, thereby reducing NF‐κB pathway and inflammatory damage of mouse myocardium caused by PM2.5 exposure. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

37. Hydroxyl‐terminated polybutadiene based waterborne polyurethane acrylate emulsions: Synthesis, characterization, and damping property.

Author

Li, Songsong, Deng, Yunjiao, Fu, Zhongyu, Zhang, Huixuan, Zhou, Chao, and Jiao, Yuhang

Subjects
METHYL methacrylate, POLYBUTADIENE, ACRYLATES, POLYURETHANES, DYNAMIC mechanical analysis, EMULSIONS, YTTRIUM iron garnet
Abstract

A new kinds of waterborne polyurethane acrylate (WPUA) dispersions were synthesized based on isophorone diisocyanate (IPDI), hydroxyl‐terminated polybutadiene (HTPB), 1, 4‐butanediol (1, 4‐BDO), polytetramethylene ether glycol (PTMG), dimethylolpropionic acid (DMPA), 2‐ethylhexyl acrylate (EHA), and methyl methacrylate (MMA) as main raw materials. The influence of the HTPB content on the particle size, storage stability of the WPUA dispersions and the damping property of cured films were studied by using dynamic light scattering (DLS), dynamic mechanical analysis (DMA), respectively. It can be found the WPUA dispersions have a good stability and the damping temperature range of loss tangent (tan δ) >0.3 reaches a maximum (−26.6–79.14°C) when the content of HTPB is 20%. The HTPB based WPUA could be applied to damping material. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

38. Gradient Boosting Decision Tree and Random Forest Based Partial Discharge Pattern Recognition of HV Cable

Author

Jiao Yuhang, Liu Taiwei, Wang Ganjun, Li Jinshu, Peng Xiaoasheng, and Wu Yijiang

Subjects
010302 applied physics, Computer science, business.industry, Feature extraction, Decision tree, Condition monitoring, 020206 networking & telecommunications, High voltage, Pattern recognition, 02 engineering and technology, 01 natural sciences, Random forest, 0103 physical sciences, Pattern recognition (psychology), Partial discharge, 0202 electrical engineering, electronic engineering, information engineering, Radio frequency, Artificial intelligence, business
Abstract

As a typical “white box” pattern recognition method, the traditional Decision Tree (DT) method, which is easy to be interpreted and trained, has been widely applied in the Partial Discharge (PD) pattern recognition of high voltage cables. However, the disadvantages of the DT method are significant, including the limited recognition accuracy, poor anti-interference ability and poor generalization ability, etc. In order to overcome the challenges, Gradient Boosting Decision Tree (GBDT) and Random Forest (RF) based PD pattern recognition methods are presented in the paper. Firstly, 3500 PD samples are obtained based on the PD testing of five types of artificial defects of ethylene-propylene (EPR) cables in the high voltage lab. Secondly, PD data pre-processing is carried out and 34 types of PD features are extracted from the raw data. Thirdly, the principles of GBDT and RF based PD pattern recognition are presented in details. Finally, the 3500 PD samples are applied to evaluate the GBDT and RF based PD pattern recognition methods, which are compared with the traditional DT method. The results show that the PD pattern recognition accuracies of RF, GBDT and DT are 89.7%, 90.4% and 84.3% respectively. GBDT and RF based PD pattern recognition methods show remarkable advantages, compared with the DT method, which are both applicable for industrial application of PD based condition monitoring of high voltage cables.

Published
2018

42. Adaptive feature selection based on the most informative graph-based features

Author

Foggia, Pasquale, Liu, Cheng-Lin, Vento, Mario, Bai, Lu, Cui, Lixin, Rossi, Luca, Hancock, Edwin R., Jiao, Yuhang, Foggia, Pasquale, Liu, Cheng-Lin, Vento, Mario, Bai, Lu, Cui, Lixin, Rossi, Luca, Hancock, Edwin R., and Jiao, Yuhang

Abstract

In this paper, we propose a novel method to adaptively select the most informative and least redundant feature subset, which has strong discriminating power with respect to the target label. Unlike most traditional methods using vectorial features, our proposed approach is based on graph-based features and thus incorporates the relationships between feature samples into the feature selection process. To efficiently encapsulate the main characteristics of the graph-based features, we probe each graph structure using the steady state random walk and compute a probability distribution of the walk visiting the vertices. Furthermore, we propose a new information theoretic criterion to measure the joint relevance of different pairwise feature combinations with respect to the target feature, through the Jensen-Shannon divergence measure between the probability distributions from the random walk on different graphs. By solving a quadratic programming problem, we use the new measure to automatically locate the subset of the most informative features, that have both low redundancy and strong discriminating power. Unlike most existing state-of-the-art feature selection methods, the proposed information theoretic feature selection method can accommodate both continuous and discrete target features. Experiments on the problem of P2P lending platforms in China demonstrate the effectiveness of the proposed method.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results