Search

Your search keyword '"Zhu, Zhenyu"' showing total 1,640 results
Start Over Author "Zhu, Zhenyu"
1,640 results on '"Zhu, Zhenyu"'

55. PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block

Author

Li, Guoqing, Zhang, Meng, Zhang, Qianru, Chen, Ziyang, Liu, Wenzhao, Li, Jiaojie, Shen, Xuzhao, Li, Jianjun, Zhu, Zhenyu, and Yuen, Chau

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In many real-time applications, the deployment of deep neural networks is constrained by high computational cost and efficient lightweight neural networks are widely concerned. In this paper, we propose that depthwise convolution (DWC) is used to expand the number of channels in a bottleneck block, which is more efficient than 1 x 1 convolution. The proposed Pointwise-Standard-Depthwise network (PSDNet) based on channel expansion with DWC has fewer number of parameters, less computational cost and higher accuracy than corresponding ResNet on CIFAR datasets. To design more efficient lightweight concolutional neural netwok, Depthwise-Pointwise-Depthwise inverted bottleneck block (DPD block) is proposed and DPDNet is designed by stacking DPD block. Meanwhile, the number of parameters of DPDNet is only about 60% of that of MobileNetV2 for networks with the same number of layers, but can achieve approximated accuracy. Additionally, two hyperparameters of DPDNet can make the trade-off between accuracy and computational cost, which makes DPDNet suitable for diverse tasks. Furthermore, we find the networks with more DWC layers outperform the networks with more 1x1 convolution layers, which indicates that extracting spatial information is more important than combining channel information.

Published
2019

56. Sound velocity in dense stellar matter with strangeness and compact stars

Author

Xia, Chengjun, Zhu, Zhenyu, Zhou, Xia, and Li, Ang

Subjects
Nuclear Theory, Astrophysics - High Energy Astrophysical Phenomena, Astrophysics - Solar and Stellar Astrophysics, High Energy Physics - Phenomenology
Abstract

The phase state of dense matter in the intermediate density range ($\sim$1-10 times the nuclear saturation density) is both intriguing and unclear and could have important observable effects in the present gravitational wave era of neutron stars. As the matter density increases in compact stars, the sound velocity is expected to approach the conformal limit ($c_s/c=1/\sqrt{3}$) at high densities and should also fulfill the causality limit ($c_s/c<1$). However, its detailed behavior remains a hot topic of debate. It was suggested that the sound velocity of dense matter could be an important indicator for a deconfinement phase transition, where a particular shape might be expected for its density dependence. In this work, we explore the general properties of the sound velocity and the adiabatic index of dense matter in hybrid stars, as well as in neutron stars and quark stars. Various conditions are employed for hadron-quark phase transition with varying interface tension. We find that the expected behavior of the sound velocity can also be achieved by the nonperturbative properties of the quark phase, in addition to a deconfinement phase transition. And it leads to a more compact star with a similar mass. We then propose a new class of quark star equation of states, which could be tested by future high-precision radius measurements of pulsar-like objects., Comment: 10 pages, 5 figures, 1 table, review article to appear in Chinese Physics C

Published
2019
Full Text
View/download PDF

66. Weakly Supervised Liver Tumor Segmentation Based on Anchor Box and Adversarial Complementary Learning

Author

Fan, Mengyao, Liu, Haofeng, Zhu, Zhenyu, Jiao, Changzhe, Gou, Shuiping, Rannenberg, Kai, Editor-in-Chief, Soares Barbosa, Luís, Editorial Board Member, Goedicke, Michael, Editorial Board Member, Tatnall, Arthur, Editorial Board Member, Neuhold, Erich J., Editorial Board Member, Stiller, Burkhard, Editorial Board Member, Tröltzsch, Fredi, Editorial Board Member, Pries-Heje, Jan, Editorial Board Member, Kreps, David, Editorial Board Member, Reis, Ricardo, Editorial Board Member, Furnell, Steven, Editorial Board Member, Mercier-Laurent, Eunika, Editorial Board Member, Winckler, Marco, Editorial Board Member, Malaka, Rainer, Editorial Board Member, Shi, Zhongzhi, editor, Jin, Yaochu, editor, and Zhang, Xiangrong, editor

Published
2022
Full Text
View/download PDF

84. Electrical fire source simulation for igniting cable

Author

LIU Xuhui, ZHU Zhenyu, GUO Yue, JING Ziyang, WU Shuqun, and ZHANG Chaohai

Subjects
fault arc, fire source simulation, cable fire, induced voltage, ladder arc, arc ignition, Applications of electric power, TK4001-4102
Abstract

In cable fire test,a fire source is essential for the fire performance evaluation. Most of the existing fire sources for power cable are based on chemical fuel,which is unable to represent the cable fire caused by fault arc. Therefore,to simulate the ignition of power cable by fault arc,a fire source based on electrical arc is developed in this work. Firstly,the induced voltage on the metal armor layer is theoretically analyzed when the 110 kV cable has the ground wire stolen or the cross interconnection wires on both sides are stolen. Voltages can reach thousands of volts. Secondly,the pre-breakdown voltage and sustained voltage of the metal-to-ground arc in power cable and the Jacob's Ladder arc are compared. It is found that the breakdown characteristics of both arcs are similar for applied ac voltage with frequencies of 50 Hz and 20 kHz. Thirdly,a fire source based on Jacob's Ladder arc is proposed for the ignition of power cables. Experimental results show that the 110 kV cable can be successfully ignited by this fire source,and the flame is able to spread both vertically and horizontally. Finally,the conclusion is that the high frequency Jacob's Ladder arc can simulate the characteristics of the fault arc and effectively ignite the 110 kV cable.

Published
2022
Full Text
View/download PDF

87. Hierarchical multi-level dynamic hyperparameter deformable image registration with convolutional neural network.

Author

Zhu, Zhenyu, Li, Qianqian, Wei, Ying, and Song, Rui

Subjects
*CONVOLUTIONAL neural networks, *DEEP learning, *FEATURE extraction, *IMAGE registration, *RECORDING & registration, *LUNGS
Abstract

Objective. To enable the registration network to be trained only once, achieving fast regularization hyperparameter selection during the inference phase, and to improve registration accuracy and deformation field regularity. Approach. Hyperparameter tuning is an essential process for deep learning deformable image registration (DLDIR). Most DLDIR methods usually perform a large number of independent experiments to select the appropriate regularization hyperparameters, which are time-consuming and resource-consuming. To address this issue, we propose a novel dynamic hyperparameter block, which comprises a distributed mapping network, dynamic convolution, attention feature extraction layer, and instance normalization layer. The dynamic hyperparameter block encodes the input feature vectors and regularization hyperparameters into learnable feature variables and dynamic convolution parameters which changes the feature statistics of the high-dimensional features layer feature variables, respectively. In addition, the proposed method replaced the single-level structure residual blocks in LapIRN with a hierarchical multi-level architecture for the dynamic hyperparameter block in order to improve registration performance. Main results. On the OASIS dataset, the proposed method reduced the percentage of | J ϕ | ⩽ 0 by 28.01 % , 9.78 % and improved Dice similarity coefficient by 1.17 % , 1.17 % , compared with LapIRN and CIR, respectively. On the DIR-Lab dataset, the proposed method reduced the percentage of | J ϕ | ⩽ 0 by 10.00 % , 5.70 % and reduced target registration error by 10.84 % , 10.05 % , compared with LapIRN and CIR, respectively. Significance. The proposed method can fast achieve the corresponding registration deformation field for arbitrary hyperparameter value during the inference phase. Extensive experiments demonstrate that the proposed method reduces training time compared to DLDIR with fixed regularization hyperparameters while outperforming the state-of-the-art registration methods concerning registration accuracy and deformation smoothness on brain dataset OASIS and lung dataset DIR-Lab. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

100. Coupling life prediction of bending very high cycle fatigue of completion strings made of different materials using deep wise separable convolution

Author

Zhu, Zhenyu, Chen, Maolin, He, Mingge, Zhang, Junliang, Huang, Yanyan, Chen, Siqi, Du, Xuanyu, Chai, Guocai, Wang, Qingyuan, Zhu, Zhenyu, Chen, Maolin, He, Mingge, Zhang, Junliang, Huang, Yanyan, Chen, Siqi, Du, Xuanyu, Chai, Guocai, and Wang, Qingyuan

Abstract

This article predicts bending very high cycle fatigue (VHCF) life of three typical nickel-based alloys SM2550, BG2532, and G3 used for completion strings. Fatigue tests were conducted on the three alloys using an ultrasonic fatigue system at a frequency of 20 kHz. The results showed that the fatigue strength ranges of the three alloys were markedly different, reflecting their different sensitivities to fatigue loading. Scanning electron microscope observations revealed numerous fatigue crack origins with internal decohesion in the fatigue source region. To achieve unified prediction of the fatigue life for the three alloys, a prediction model based on deep learning was built with inputs including fatigue initiation quantity, cleavage facet size, and other fatigue fracture characteristics. It was found that single source feature was insufficient to obtain satisfactory prediction accuracy for all alloys, while multifeature coupling integration could significantly improve the prediction precision, enabling reliable prediction of alloy fatigue life. This study provides new insights into bending VHCF life prediction. This article predicts bending VHCF life for three completion strings. Bending VHCF life model utilizing deep wise separable convolution was established. Deep learning can effectively integrate with bending VHCF analyses., Funding Agencies|The 111 Center; Technology Development Project Foundation of PetroChina Southwest Oil and Gas Field CDB Operating Company; The 2023 Open Project of Failure Mechanics and Engineering Disaster Prevention, Key Lab of Sichuan Province [52205182]; National Natural Science Foundation of China [2023NSFSC0916]; Natural Science Foundation of Sichuan Province [20220303-16]; [FMEDP202303]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results