检索结果-南通市图书馆

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 965-981页

作者： yong-Chao Li Rui-Sheng Jia Ying-xiang Hu Hong-Mei sun the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590 the Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266000China the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China the College of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210000China

In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation *** this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised *** this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the ***,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd *** addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density *** experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.

关键词： Crowd density estimation linear feature calibration vision transformer weakly-supervision learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Temperature prediction model in multiphase flow considering phase transition in the drilling operations

引用

Petroleum Science 2024年第3期21卷 1969-1979页

作者： Yang Zhang yong-An Li xiang-Wei Kong Hao Liu Teng-Fei sun College of Mechanical and Electrical Engineering Beijing University of Chemical TechnologyBeijing 100027China School of Petroleum Engineering Yangtze UniversityWuhan430000HubeiChina

The study considers gas compression properties,gas slippage,back pressure(BP),phase transition(PT),well depth,and differences in gas-liquid physical properties.A new temperature model for multiphase flow is proposed by considering phase transition in the drilling *** mathematical model of multiphase flow is solved using the finite difference method with annulus mesh division for grid nodes,and a module for multiphase flow calculation and analysis is *** results indicate that the temperature varies along the annulus with the variation of gas influx at the bottom of the *** the process of controlled pressure drilling,as gas slips along the annulus to the wellhead,its volume continuously expands,leading to an increase in the gas content within the annulus,and consequently,an increase in the pressure drop caused by gas *** temperature increases with the increase in BP and decreases in gas influx rate and wellbore *** gas influx,the thermal conductivity coefficient for the gas-drilling mud two phases is significantly weakened,resulting in a considerable change in temperature along the *** the context of MPD,the method of slightly changing the temperature along the annulus by controlling the back pressure is feasible.

关键词： Managed pressure drilling Phase transition Temperature Gas-drilling mud two phase

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Acyclic Total Colorings of Planar Graphs without l Cycles

引用

Acta Mathematica Sinica,English Series 2011年第7期27卷 1315-1322页

作者： xiang yong sun Jian Liang WU School of Statistics and Mathematics Shandong Economic University Ji'nan 250014 P. R. China School of Mathematics and Systems Science Shandong University Ji'nan 250100 P. R. China

A proper total coloring of a graph G such that there are at least 4 colors on those vertices and edges incident with a cycle of G, is called acyclic total coloring. The acyclic total chromatic number of G is the least number of colors in an acyclic total coloring of G. In this paper, it is proved that the acyclic total chromatic number of a planar graph G of maximum degree at least k and without 1 cycles is at most △（G）＋ 2 if （k, l） ∈ {（6, 3）, （7, 4）, （6, 5）, （7, 6）}.

关键词： Acyclic total coloring cycle planar graph

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Miniaturized power detection module operating in millimeter wave band

引用

Journal of Electronic Science and Technology 2024年第2期22卷 69-76页

作者： xiang Zhou Zhi-yong Zhong School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

The miniaturized broadband detection module can be embedded into the microwave application system such as the front end of the transmitter to detect the power or other parameters in real *** is highly prospective in military and scientific *** this paper,a broadband power detection module operating at 26.5 GHz-40.0 GHz is designed by using low-barrier Schottky diode as the detector and a comparator for threshold *** module can dynamically detect the power range between-10 dBm and 10 dBm with the detection accuracy of 0.1 ***,the temperature compensation circuit is also applied to improve the measurement *** a result,the resulted error low to±1 dB in the temperature range of -55℃ to +85℃ is *** designed module is encapsulated by a Kovar alloy with a small volume of 9 mm×6 mm×3 *** endows the designed module the advantages of small size,easy integration,and low cost,and even it is applicable to high-reliability environments such as satellites.

关键词： Diode Miniaturization Power detection Temperature compensation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

miR-124 is upregulated in diabetic mice and inhibits proliferation and promotes apoptosis of high-glucose-inducedβ-cells by targeting EZH2

引用

World Journal of Diabetes 2023年第3期14卷 209-221页

作者： Xiao-Kai Duan yong-xiang sun Hong-Yun Wang Yan-Yan Xu Shi-Zhen Fan Jin-Ya Tian yong Yu Yan-YunZhao Yan-Li Jiang Department of General Practice Zhengzhou First People’s HospitalZhengzhou 450000Henan ProvinceChina

BACKGROUND Diabetes is a chronic metabolic disease,and a variety of miRNA are involved in the occurrence and development of *** clinical studies,miR-124 is highly expressed in the serum of patients with diabetes and in pancreatic isletβ-***,few reports exist concerning the role and mechanism of action of miR-124 in *** To investigate the expression of miR-124 in diabetic mice and the potential mechanism of action in isletβ-*** The expression levels of miR-124 and enhancer of zeste homolog 2(EZH2)in pancreatic tissues of diabetic mice were *** targeted relationship between miR-124 and EZH2 was predicted by Targetscan software and verified by a double luciferase reporter *** isletβ-cells Min6 were grown in a high glucose(HG)medium to mimic a diabetes *** insulin secretion,proliferation,cell cycle and apoptosis of HG-induced Min6 cells were detected after interference of miR-124a and/or *** The expression of miR-124 was upregulated and EZH2 was downregulated in the pancreatic tissue of diabetic mice compared with control mice,and the expression of miR-124 was negatively correlated with that of ***-124 was highly expressed in HG-induced Min6 *** of miR-124 promoted insulin secretion and cell proliferation,induced the transition from the G0/G1 phase to the S phase of the cell cycle,and inhibited cell apoptosis in HG-induced Min6 ***2 was one of the targets of ***-transfection of miR-124 inhibitor and siRNA-EZH2 could reverse the effects of the miR-124 inhibitor in HG-induced Min6 *** miR-124 is highly expressed in diabetic mice and HG-induced Min6 cells and regulates insulin secretion,proliferation and apoptosis of isletβ-cells by targeting EZH2.

关键词： miR-124 Enhancer of zeste homolog 2 Diabetes Insulin secretion Proliferation Apoptosis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A New Method for Solving Nonlinear Partial Differential Equations Based on Liquid Time-Constant Networks

引用

Journal of Systems Science & Complexity 2024年第2期37卷 480-493页

作者： sun Jiuyun DONG Huanhe FANG yong College of Mathematics and Systems Science Shandong University of Science and TechnologyQingdao 266590China

In this paper,physics-informed liquid networks(PILNs)are proposed based on liquid time-constant networks(LTC)for solving nonlinear partial differential equations(PDEs).In this approach,the network state is controlled via ordinary differential equations(ODEs).The significant advantage is that neurons controlled by ODEs are more expressive compared to simple activation *** addition,the PILNs use difference schemes instead of automatic differentiation to construct the residuals of PDEs,which avoid information loss in the neighborhood of sampling *** this method draws on both the traveling wave method and physics-informed neural networks(PINNs),it has a better physical ***,the KdV equation and the nonlinear Schr¨odinger equation are solved to test the generalization ability of the *** the best of the authors’knowledge,this is the first deep learning method that uses ODEs to simulate the numerical solutions of PDEs.

关键词： Nonlinear partial differential equations numerical solutions physics-informed liquid networks physics-informed neural networks

来源：

维普期刊数据库

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks with Two Weighted Loss Function Methods for Interactions of Two-Dimensional Oceanic Internal Solitary Waves

引用

Journal of Systems Science & Complexity 2024年第2期37卷 545-566页

作者： sun Junchao CHEN yong TANG Xiaoyan School of Mathematical Sciences Key Laboratory of Mathematics and Engineering Applications(Ministry of Education)&Shanghai Key Laboratory of PMMPEast China Normal UniversityShanghai 200241China College of Mathematics and Systems Science Shandong University of Science and TechnologyQingdao 266590China

The multiple patterns of internal solitary wave interactions(ISWI)are a complex oceanic *** remote sensing techniques indirectly detect these ISWI,but do not provide information on their detailed structure and ***,the authors considered a three-layer fluid with shear flow and developed a(2+1)Kadomtsev-Petviashvili(KP)model that is capable of describing five types of oceanic ISWI,including O-type,P-type,TO-type,TP-type,and *** learning models,particularly physics-informed neural networks(PINN),are widely used in the field of fluids and internal solitary ***,the authors find that the amplitude of internal solitary waves is much smaller than the wavelength and the ISWI occur at relatively large spatial scales,and these characteristics lead to an imbalance in the loss function of the PINN *** solve this problem,the authors introduce two weighted loss function methods,the fixed weighing and the adaptive weighting methods,to improve the PINN *** successfully simulated the detailed structure and dynamics of ISWI,with simulation results corresponding to the satellite *** particular,the adaptive weighting method can automatically update the weights of different terms in the loss function and outperforms the fixed weighting method in terms of generalization ability.

关键词： Internal solitary wave interactions KP equation PINN method weighted loss function method

来源：

维普期刊数据库

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Biomimetic Gland Models with Engineered Stratagems

引用

Research 2024年第2期2023卷 583-612页

作者： xiang Lin Lingyu sun Minhui Lu Yuanjin Zhao Department of Rheumatology and Immunology Nanjng Drum Tower HospitalSchool of Biological Science and Medical EngineeringSoutheast UniversityNanjing 210096China Oujiang Laboratory(Zhejiang Lab for Regenerative Medicine Vision and Brain Health)Wenzhou InstituteUniversity of Chinese Academy of SciencesWenzhouZhejiang 325001China Southeast University Shenzhen Research Institute Shenzhen 518071China

As extensively distributed tissues throughout the human body,glands play a critical role in various physiological ***,the construction of biomimetic gland models in vitro has aroused great interest in multiple *** the biological field,the researchers focus on optimizing the cell sources and culture techniques to reconstruct the specific structures and functions of glands,such as the emergence of organoid *** the perspective of biomedical engineering,the generation of biomimetic gland models depends on the combination of engineered scaffolds and microfluidics,to mimic the in vivo environment of glandular *** engineered stratagems endowed gland models with more biomimetic features,as well as a wide range of application *** this review,we first describe the biomimetic strategies for constructing different in vitro gland models,focusing on the role of microfluidics in promoting the structure and function development of biomimetic *** summarizing several common in vitro models of endocrine and exocrine glands,the applications of gland models in disease modelling,drug screening,regenerative medicine,and personalized medicine are ***,we conclude the current challenges and our perspective of these biomimetic gland models.

关键词： endowed constructing strata

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Subnatural-linewidth fluorescent single photons

引用

Photonics Research 2024年第4期12卷 625-637页

作者： HE-BIN ZHANG GAO-xiang LI yong-CHUN LIU State Key Laboratory of Low-Dimensional Quantum Physics Department of PhysicsTsinghua UniversityBeijing 100084China Department of Physics Huazhong Normal UniversityWuhan 430079China Frontier Science Center for Quantum Information Beijing 100084China

Subnatural-linewidth single photons are of vital importance in quantum optics and quantum information *** to previous research, it appears difficult to utilize resonance fluorescence to generate single photons with subnatural linewidth. Here we propose a universally applicable approach to generate fluorescent single photons with subnatural linewidth, which can be implemented based on Λ-shape and similar energy ***, the general condition to obtain fluorescent single photons with subnatural linewidth is *** single-photon linewidth can be easily manipulated over a broad range by external fields, which can be several orders of magnitude smaller than the natural linewidth. Our study can be easily implemented in various physical platforms with current experimental techniques and will significantly facilitate the research on the quantum nature of resonance fluorescence and the technologies in quantum information science.

关键词： quantum utilize optics

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Adversarial data splitting for domain generalization

引用

Science China(Information Sciences) 2024年第5期67卷 28-42页

作者： xiang GU Jian sun Zongben XU School of Mathematics and Statistics Xi'an Jiaotong University

Domain generalization aims to learn a model that is generalizable to an unseen target domain,which is a fundamental and challenging task in machine learning for out-of-distribution generalization. This paper proposes a novel domain generalization approach that enforces the learned model to be able to generalize well over the train/val subset splitting of the training dataset. This idea is modeled herein as an adversarial data splitting framework, formulated as a min-max optimization problem inspired by the metalearning approach. The min-max optimization problem is solved by iteratively splitting the training dataset into the training and val subsets to maximize the domain shift measured by the objective function and updating the model parameters to enable the model to generalize well from the training subset to the val subset by minimizing the objective function. This adversarial training approach does not assume the known domain labels of the training data; instead, it automatically investigates the “hard” splitting of the train/val subsets to learn the generalizable model. Extensive experimental results using three benchmark datasets demonstrate the superiority of this approach. In addition, we derive a generalization error bound for the theoretical understanding of our proposed approach.

关键词： domain generalization adversarial learning data splitting meta-learning out of distribution

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：