检索结果-南通市图书馆

Meta Ordinal Regression Forest for Medical Image Classification With Ordinal Labels

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1233-1247页

作者： Yiming Lei Haiping Zhu junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200433China with Huawei Shanghai 200120China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China IEEE

The performance of medical image classification has been enhanced by deep convolutional neural networks(CNNs),which are typically trained with cross-entropy(CE)***,when the label presents an intrinsic ordinal property in nature,e.g.,the development from benign to malignant tumor,CE loss cannot take into account such ordinal information to allow for better *** improve model generalization with ordinal information,we propose a novel meta ordinal regression forest(MORF)method for medical image classification with ordinal labels,which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning *** merits of the proposed MORF come from the following two components:A tree-wise weighting net(TWW-Net)and a grouped feature selection(GFS)***,the TWW-Net assigns each tree in the forest with a specific weight that is mapped from the classification loss of the corresponding ***,all the trees possess varying weights,which is helpful for alleviating the tree-wise prediction ***,the GFS module enables a dynamic forest rather than a fixed one that was previously used,allowing for random feature *** training,we alternatively optimize the parameters of the CNN backbone and TWW-Net in the meta-learning framework through calculating the Hessian *** results on two medical image classification datasets with ordinal labels,i.e.,LIDC-IDRI and Breast Ultrasound datasets,demonstrate the superior performances of our MORF method over existing state-of-the-art methods.

关键词： Terms-Convolutional neural network(CNNs) medical image classification meta-learning ordinal regression random forest

General collision branching processes with two parameters

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2009年第7期52卷 1546-1568页

作者： CHEN AnYue LI junping Department of Mathematical Sciences the University of LiverpoolLiverpoolL69 7ZLUK Department of Statistics and Actuarial Science University of Hong KongPokfulam RoadHong Kong School of Mathematical Science and Computing Technology Central South UniversityChangsha 410075China

A new class of branching models,the general collision branching processes with two parameters,is considered in this *** such models,it is necessary to evaluate the absorbing probabilities and mean extinction times for both absorbing *** and uniqueness criteria are firstly *** expressions are then obtained for the extinction probability vector,the mean extinction times and the conditional mean extinction *** explosion behavior of these models is investigated and an explicit expression for mean explosion time is *** mean global holding time is also *** is revealed that these properties are substantially different between the super-explosive and sub-explosive cases.

关键词： Markov branching process general collision branching process uniqueness extinction probabilities mean extinction time mean explosion time 60J27 60J80

Crowd Density Field Estimation Based on Crowd Dynamics Theory and Social Force Model

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第3期28卷 521-528页

作者： WEI Xinlei DU junping LIANG Meiyu XUE Zhe Beijing Key Lab of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

The local crowd density and the crowd distribution estimation tasks are useful but *** are two main problems which limit the performance of existing algorithms. The first one is that there are not enough labeled training samples to build the highperformance estimation model. Another one is that existing methods lack the supports of physical theories of the crowd. To remedy them, a novel crowd density field model is proposed, which is deduced by jointing crowd dynamics theory and social force model. A crowd counting method based on the proposed crowd density field model is introduced to measure the proposed crowd density field model. Extensive experiments confirm the effectiveness of the proposed plan.

关键词： Social force model Crowd dynamics Crowd density field Computer vision

Engineered macrophage-biomimetic versatile nanoantidotes for inflammation-targeted therapy against Alzheimer’s disease by neurotoxin neutralization and immune recognition suppression

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Bioactive Materials 2023年第8期26卷 337-352页

作者： meng Cheng Caihua Ye Chunxiao Tian Dongju Zhao Haonan Li Zuhao Sun Yuyang Miao Qiang Zhang junping Wang Yan Dou Department of Radiology and Tianjin Key Laboratory of Functional Imaging Tianjin Medical University General HospitalTianjin300052PR China School of Biomedical Engineering and Technology Tianjin Medical UniversityTianjin300070PR China School of Life Sciences Tianjin UniversityTianjin300072PR China Department of Geriatrics Tianjin Medical University General HospitalTianjin Geriatrics InstituteTianjin300052PR China

Immune recognition of excessive neurotoxins by microglia is a trigger for the onset of neuroinflammation in the brain,leading to neurodegeneration in Alzheimer’s disease(AD).Blocking active recognition of microglia while removing neurotoxins holds promise for fundamentally alleviating neurotoxin-induced immune responses,but is very ***,an engineered macrophage-biomimetic versatile nanoantidote(OT-Lipo@M)is developed for inflammation-targeted therapy against AD by neurotoxin neutralization and immune recognition *** macrophage membranes can not only endow OT-Lipo@M with anti-phagocytic and inflammation-tropism capabilities to target inflammatory lesions in AD brain,but also efficiently reduce neurotoxin levels to prevent them from activating *** loaded oxytocin(OT)can be slowly released to downregulate the expression of immune recognition site Toll-like receptor 4(TLR4)on microglia,inhibiting TLR4-mediated pro-inflammatory signalling *** from this two-pronged immunosuppressive strategy,OT-Lipo@M exhibits outstanding therapeutic effects on ameliorating cognitive deficits,inhibiting neuronal apoptosis,and enhancing synaptic plasticity in AD mice,accompanied by the delayed hippocampal atrophy and brain microstructural disruption by in vivo 9.4T MR *** work provides new insights into potential AD therapeutics targeting microglia-mediated neuroinflammation at the source.

关键词： Alzheimer’s disease Biomimetic nanomedicine Biological neutralization Immune recognition and response Neuroinflammation-targeted therapy 9.4T MR imaging

Markov branching processes with immigration-migration and resurrection

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

Science China Mathematics 2011年第5期54卷 1043-1062页

作者： LI junping LIU ZaiMing School of Mathematical Science and Computing Technology Central South University Changsha 410075 China

We consider a modified Markov branching process incorporating with both state-independent immigration-migration and resurrection. The effect of state-independent immigration-migration is firstly in- vestigated in detail. The explicit expressions for the extinction probabilities and mean extinction times are presented. The ergodicity and stability properties of the process incorporating with resurrection structure are then investigated. The conditions for recurrence, ergodicity and exponential ergodicity are obtained. An explicit expression for the equilibrium distribution is also presented. As a preparation, the criteria for regularity and uniqueness for such structure are firstly established.

关键词： Markov branching process, immigration, migration, resurrection, regularity, extinction, recurrence, ergodicity收藏本站首页期刊全文库学位论文库会议论文库吾喜杂志注册|登录|我的账户基础科学|工程科技I辑|工程科技II辑|医药卫生科技|信息科技|农业科技|哲学与人文科学|社会科学I辑|社会科学II辑|经济管理高级搜索: 用" Markov branching process immigration "到知网平台检索,点击这里搜索更多...《Science China(Mathematics)》 2011年05期加入收藏获取最新 Markov branching processes with immigration-migration and resurrection【摘要】: We consider a modified Markov branching process incorporating with both state-independent immigration-migration and resurrection. The effect of state-independent immigration-migration is firstly in- vestigated in detail. The explicit expressions for the extinction probabilities and mean extinction times are presented. The ergodicity and stability properties of the process incorporating with resurrection structure are then investigated. The conditions for recurrence, ergodicity and exponential ergodicity are obtained. An explicit expression for the equilibrium distribution is also presented. As a preparation, the criteria for regularity and uniqueness for such structure are firstly established.【关键词】 : Markov branching process immigration migration resurrection regularity extinction recur- rence ergodicity Keywords Markov branching process, immigration, migration, resurrection, regularity, extinction, recur-rence, ergodicity

Self-adaptive spatial image denoising model based on scale correlation and SURE-LET in the nonsubsampled contourlet transform domain

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2014年第9期57卷 72-86页

作者： LIANG MeiYu DU junping LIU HongGang Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

A novel self-adaptive image denoising model based on scale correlation and Stein’s unbiased risk estimate-linear expansion of thresholds(SURE-LET)in the nonsubsampled contourlet transform domain is proposed in this *** we implement the multidimensional and translation invariant decomposition for spatial images by the nonsubsampled contourlet transform,and establish the image cross-scale description *** combining the scale correlation,we make improvements for the existing SURE-LET denoising idea and establish the self-adaptive denoising *** scale correlation calculation is needed for the coefficients at different scales and sub-bands to determine whether the coefficients are retained or processed with the adaptive SURE-LET threshold *** meanwhile a new local context self-adaptive threshold strategy is proposed in the process of scale correlation *** results both on spatial images and standard images demonstrate that the proposed algorithm performs significantly better in terms of both the visual subjective evaluation and the quantitative objective *** method can achieve better noise suppression,and effectively retain image edge details.

关键词： spatial images image denoising nonsubsampled contourlet transform SURE-LET scale correlation

Fast Blood Oxygenation through Hemocompatible Asymmetric Polymer of Intrinsic Microporosity Membranes

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Research 2024年第1期2023卷 261-270页

作者： Xinxi Huang junping Huang Pengcheng Su Wanbin Li Guangdong Key Laboratory of Environmental Pollution and Health School of EnvironmentJinan UniversityGuangzhou 511443China

Membrane technology has attracted considerable attention for chemical and medical applications,among *** organs play important roles in medical science.A membrane oxygenator,also known as artificial lung,can replenish O_(2) and remove CO_(2) of blood to maintain the metabolism of patients with cardiopulmonary ***,the membrane,a key component,is subjected to inferior gas transport property,leakage propensity,and insufficient *** this study,we report efficient blood oxygenation by using an asymmetric nanoporous membrane that is fabricated using the classic nonsolvent-induced phase separation method for polymer of intrinsic *** intrinsic superhydrophobic nanopores and asymmetric configuration endow the membrane with water impermeability and gas ultrapermeability,up to 3,500 and 1,100 gas permeation units for CO_(2) and O_(2),***,the rational hydrophobic–hydrophilic nature,electronegativity,and smoothness of the surface enable the substantially restricted protein adsorption,platelet adhesion and activation,hemolysis,and thrombosis for the ***,during blood oxygenation,the asymmetric nanoporous membrane shows no thrombus formation and plasma leakage and exhibits fast O_(2) and CO_(2) transport processes with exchange rates of 20 to 60 and 100 to 350 ml m^(−2) min^(−1),respectively,which are 2 to 6 times higher than those of conventional *** concepts reported here offer an alternative route to fabricate high-performance membranes and expand the possibilities of nanoporous materials for membrane-based artificial organs.

关键词： porosity asymmetric Oxygen

INVESTIGATION OF THE M-INTEGRAL IN CRACK-DAMAGED PIEZOELECTRIC CERAMICS

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

Acta Mechanica Solida Sinica 2006年第2期19卷 167-173页

作者： Wang Defa Ma Lifeng Shi junping Department of Civil Engineering Xi＇an University of Technology Xi＇an 710048. China Department of Civil Engineering Xi＇an Jiao Tong UniversityXian 710049China Department of Engineering Mechanics Xi＇an University of Technology Xi＇an 710048 China

The physical interpretation of the M-integral is investigated in the analysis of crackdamaged piezoelectric problems. The relation between the M-integral and the change of the total electric enthalpy （CTEE）, i.e., M = 2CTEE, is derived with a theoretical derivation procedure for two^dimensional piezoelectric problems. It is shown that the M-integral may provide a more natural description of electric enthalpy release due to the formation of the pre-existing microcracks associated with the damaged body, rather than the description of the total potential energy release rate as interpreted for conventional brittle solids. For crack-damaged piezoelectric ceramics, numerical calculation of the M-integral is discussed. Based on the pseudo-traction electric displacement method, M = 2CTEE has also been proved by the numerical results.

关键词： M-integral crack piezoelectric ceramics electric enthalpy damage

The first principles investigation of ferrite magnetic response with mismatch stress

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2014年第3期57卷 512-520页

作者： HUANG junping PENG XiangHe HU XianZhi Department of Engineering Mechanics Chongqing University School of Mechanical Engineering Chongqing Vocational Institute of Engineering Faculty of Science Kunming University of Science and Technology

The quasi-ferrite model is proposed and an appropriate PBE exchange functional with the spin density functional theory （SDFT） is selected for the calculation of the relation between magnetic moment and residual stress in ferrite using a quantum mechanics code. The relationship between ferrite magnetism and the carbon content is determined, and then a ferrite interstitial solid solution （ISS） model in a low carbon concentration state is replaced with an a-Fe model in the case of majority magnetic calculation. The band structure of the loaded α-Fe is compared with that of the unloaded a-Fe. The comparison shows that the energy of Fe atomic 3d orbital changes a little, while the energy of electron orbital of iron core below 3d almost keeps un- changed. The relationship between the magnetic moment and the stress appears intermittent due to the Bragg total reflection. The change in the magnetic moment due to lattice mismatch is much larger than that caused by mechanical loading.

关键词： the first-principles calculation SDFT quasi-ferrite lattice mismatch residual stress