检索结果-南通市图书馆

Inner Cascaded U^(2)-Net:An Improvement to Plain Cascaded U-Net

Computer Modeling in Engineering & Sciences 2023年第2期134卷 1323-1335页

作者： Wenbin Wu guanjun liu Kaiyi Liang Hui Zhou Tongji University Shanghai201804China Jiading District Central Hospital Affiliated to Shanghai University of Medicine and Health Sciences Shanghai201800China

Deep neural networks are now widely used in the medical image segmentation field for their performance superiority and no need of manual feature extraction.U-Net has been the baseline model since the very beginning due to a symmetricalU-structure for better feature extraction and fusing and suitable for small datasets.To enhance the segmentation performance of U-Net,cascaded U-Net proposes to put two U-Nets successively to segment targets from coarse to fine.However,the plain cascaded U-Net faces the problem of too less between connections so the contextual information learned by the former U-Net cannot be fully used by the latter one.In this article,we devise novel Inner Cascaded U-Net and Inner Cascaded U^(2)-Net as improvements to plain cascaded U-Net for medical image segmentation.The proposed Inner Cascaded U-Net adds inner nested connections between two U-Nets to share more contextual information.To further boost segmentation performance,we propose Inner Cascaded U^(2)-Net,which applies residual U-block to capture more global contextual information from different scales.The proposed models can be trained from scratch in an end-to-end fashion and have been evaluated on Multimodal Brain Tumor Segmentation Challenge(BraTS)2013 and ISBI Liver Tumor Segmentation Challenge(LiTS)dataset in comparison to related U-Net,cascaded U-Net,U-Net++,U^(2)-Net and state-of-the-art methods.Our experiments demonstrate that our proposed Inner Cascaded U-Net and Inner Cascaded U^(2)-Net achieve better segmentation performance in terms of dice similarity coefficient and hausdorff distance as well as get finer outline segmentation.

关键词： Deep neural networks medical image segmentation U-Net cascaded convolution block

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

Effects of different nitrogen forms and concentrations on seedling growth traits and physiological characteristics of Populus simonii × P. nigra

引用

Journal of Forestry Research 2022年第5期33卷 1593-1606页

作者： Zhongye liu Wei Li Zhiru Xu Huihui Zhang Guangyu Sun Heng Zhang Chuanping Yang guanjun liu State Key Laboratory of Tree Genetics and Breeding Northeast Forestry UniversityHarbin 150040People’s Republic of China College of Life Science Northeast Forestry UniversityHarbin 150040People’s Republic of China

Numerous growth and physiological variables of 3-week-old Populus simonii × P.nigra seedlings were assessed after treatment with either nitrate nitrogen(NO_(3)^(−)--N)(0.1,0.5,1,5,or 10 mmol·L^(−1)) or ammonium nitrogen(NH_(4)^(+)+-N)(0.1,0.5,1,5,or 10 mmol·L^(−1)) to determine the best nitrogen form and concentration to optimize growth,biomass allocation,pigment content,and photosynthetic capacity.The results of combining membership function and an evaluation index suggested that,5 mmol·L^(−1) nitrogen,regardless of the form,yielded the highest comprehensive evaluation index and good growth.In addition,a Pearson correlation analysis and network visualization revealed that the total mass,shoot mass,root mass,leaf dry mass,plant height,leaf area,chlorophyll a and total chlorophyll had a physiological index connectivity degree≥15 for both nitrogen *** photosynthetic rate,stomatal conductance,transpiration rate,maximum photochemical efficiency of PSII,total nitrogen content,ground diameter,chlorophyll b,and carotenoid were unique indices for evaluating NH_(4)^(+)+-N-based nutrition,which could provide a theoretical basis for evaluating the effects of nitrogen fertilizer on seedlings,cultivation periods,and stress tolerance in P.simonii× P.nigra.

关键词： Nitrogen form Nitrogen concentration Growth traits Physiological characteristics

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

Detecting and Repairing Data-Flow Errors in WFD-net Systems

引用

Computer Modeling in Engineering & Sciences 2022年第6期131卷 1337-1363页

作者： Fang Zhao Dongming Xiang guanjun liu Changjun Jiang Honghao Zhu School of Electronics and Information Engineering Tongji UniversityShanghai201804China School of Information Science and Technology Zhejiang Sci-Tech UniversityHangzhou310018China School of Computer Engineering Bengbu UniversityBengbu233030China

Workflow system has become a standard solution for managing a complex business process.How to guarantee its correctness is a key requirement.Many methods only focus on the control-flow verification,while they neglect the modeling and checking of data-flows.Although some studies are presented to repair the data-flow errors,they do not consider the effect of delete operations or weak circulation relations on the repairing results.What’s more,repairing some data-flow errors may bring in new errors.In order to solve these problems,we use workflow net with data(WFD-net)systems to model and analyze a workflow system.Based on weak behavioral relations and order relations in a WFD-net system,we formalize four kinds of data-flow errors.After then,we reveal the relations between these errors and organize them into a hierarchy.Furthermore,we propose some new methods to repair data-flow errors in a WFD-net system based on system requirements and repair strategies.Finally,a case study of campus-card recharging shows the applicability of our methods,and a group of experiments show their advantages and effectiveness.

关键词： Data-flow errors WFD-net weak behavioral relations system requirements

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

Observable liveness of Petri nets with controllable and observable transitions

引用

Science China(Information Sciences) 2017年第11期60卷 256-264页

作者： guanjun liu Changjun JIANG Department of Computer Science Tongji University Key Laboratory of Embedded System and Service Computing of Ministry of Education Tongji University E-commerce Transactions and Information Services Collaborative Innovation Center of Shanghai University Knowledge Service Platform Tongji University

Observability and/or controllability are paid much attention to by researchers not only from the control science field[1–3]but also from the computer science field[4–9].Recently,Desel and Kilinc[4]proposed the notion of observable liveness for Petri nets with(un-)observable and(un-)controllable transitions.The purpose of defining observable liveness is to represent that"a user can always enforce the occurrence of any observable transition only by stimulating the net by choosing appropriate enabled controllable transition"[4].An important assumption of

关键词： net cot PN Observable liveness of Petri nets with controllable and observable transitions

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

Genome-Wide Analysis of the KANADI Gene Family and Its Expression Patterns under Different Nitrogen Concentrations Treatments in Populus trichocarpa

引用

Phyton-International Journal of Experimental Botany 2023年第7期92卷 2001-2015页

作者： Minghui Niu Heng Zhang Xiangyang Li Zhibao Hu Hongjiao Zhang Zhiru Xu Chunpu Qu guanjun liu State Key Laboratory of Tree Genetics and Breeding(Northeast Forestry University) School of ForestryNortheast Forestry UniversityHarbin150040China Key Laboratory of Saline-Alkali Vegetation Ecology Restoration(Northeast Forestry University) Ministry of EducationHarbin150040China College of Life Science Northeast Forestry UniversityHarbin150040China College of Forestry Guizhou UniversityGuiyang550025China

KANADI(KAN)is a plant-specific gene that controlled the polarity development of lateral organs.It mainly acted on the abaxial characteristics of plants to make the lateral organs asymmetrical.However,it had been less identified in woody plants.In this study,the members of the KAN gene family in Populus trichocarpa were identified and analyzed using the bioinformatics method.The results showed that a total of 8 KAN family members were screened out,and each member contained the unique GARP domain and conserved region of the family proteins.Phylogenetic analysis and their gene structures revealed that all KAN genes from P.trichocarpa,Arabidopsis thaliana,and Nicotiana benthamiana could be divided into four subgroups,while the eight genes in P.trichocarpa were classified into three subgroups,respectively.The analysis of tissue-specific expression indicated that PtKAN1 was highly expressed in young leaves,PtKAN6 was highly expressed in young leaves and mature leaves,PtKAN2,PtKAN5,and PtKAN7 were highly expressed in nodes and internodes,PtKAN8 was highly expressed in roots,and PtKAN3 and PtKAN4 showed low expression levels in all tissues.Among them,PtKAN2 and PtKAN6,and PtKAN4 and PtKAN5 might have functional redundancy.Under high nitrogen concentrations,PtKAN2 and PtKAN8 were highly expressed in mature stems and leaves,respectively,while PtKAN4,PtKAN5,and PtKAN7 were highly expressed in roots.This study laid a theoretical foundation for further study of the KAN genemediated nitrogen effect on root development.

关键词： Bioinformatics analysis KANADI gene family nitrogen Populus trichocarpa

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

Partition-based Collaborative Tensor Factorization for POI Recommendation

引用

IEEE/CAA Journal of Automatica Sinica 2017年第3期4卷 437-446页

作者： Wenjing Luan guanjun liu Changjun Jiang Liang Qi Department of Computer Science and Technology Tongji University IEEE Key Laboratory of Embedded System and Service Computing Tongji University

The rapid development of location-based social networks(LBSNs) provides people with an opportunity of better understanding their mobility behavior which enables them to decide their next location.For example,it can help travelers to choose where to go next,or recommend salesmen the most potential places to deliver advertisements or sell products.In this paper,a method for recommending points of interest(POIs)is proposed based on a collaborative tensor factorization(CTF)technique.Firstly,a generalized objective function is constructed for collaboratively factorizing a tensor with several feature matrices.Secondly,a 3-mode tensor is used to model all users' check-in behaviors,and three feature matrices are extracted to characterize the time distribution,category distribution and POI correlation,respectively.Thirdly,each user's preference to a POI at a specific time can be estimated by using CTF.In order to further improve the recommendation accuracy,PCTF(Partitionbased CTF) is proposed to fill the missing entries of a tensor after clustering its every mode.Experiments on a real checkin database show that the proposed method can provide more accurate location recommendation.

关键词： Clustering context feature extraction point of interest(POI) recommendation tensor factorization

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

Detecting Data-flow Errors Based on Petri Nets With Data Operations

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 251-260页

作者： Dongming Xiang guanjun liu Chungang Yan Changjun Jiang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China IEEE

In order to guarantee the correctness of business processes, not only control-flow errors but also data-flow errors should be considered. The control-flow errors mainly focus on deadlock, livelock, soundness, and so on. However, there are not too many methods for detecting data-flow errors. This paper defines Petri nets with data operations(PN-DO) that can model the operations on data such as read, write and delete. Based on PN-DO, we define some data-flow errors in this paper. We construct a reachability graph with data operations for each PN-DO, and then propose a method to reduce the reachability graph. Based on the reduced reachability graph, data-flow errors can be detected rapidly. A case study is given to illustrate the effectiveness of our methods.

关键词： Business process modeling data-flow errors Petri nets reachability graph

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

A clustering-based flexible weighting method in AdaBoost and its application to transaction fraud detection

引用

Science China(Information Sciences) 2021年第12期64卷 69-79页

作者： Chaofan YANG guanjun liu Chungang YAN Changjun JIANG Department of Computer Science Tongji University Shanghai Electronic Transactions and Information Service Collaborative Innovation Center Tongji University

AdaBoost is a famous ensemble learning method and has achieved successful applications in many fields. The existing studies illustrate that AdaBoost easily suffers from noisy points, resulting in a decline of classification performance. The main reason is that it increases the weights of all misclassified samples(especially noisy points) in the same way so that the influence of noisy points can hardly be weakened. In this paper, the clustering algorithm is used to dynamically decide noisy points in the process of iterations.More precisely, we compute a misclassification degree for every cluster in every iteration that is used to decide if a misclassified sample is a noisy point or not in the current iteration. Furthermore, we propose a flexible method to update the weights of the misclassified samples. The experimental results on 22 public datasets show that our method achieves better results than the state-of-the-art methods including AdaBoost,AdaCoast, LogitBoost, and SPLBoost. We also apply our method to the transactions fraud detection, and the experiments on our real big dataset of transactions also illustrate its good performance.

关键词： ensemble learning AdaBoost clustering misclassification degree transaction fraud detection

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

Test selection and optimization for PHM based on failure evolution mechanism model

引用

Journal of Systems Engineering and Electronics 2013年第5期24卷 780-792页

作者： Jing Qiu Xiaodong Tan guanjun liu Kehong L Laboratory of Science and Technology on Integrated Logistics Support College of Mechatronics and AutomationNational University of Defense Technology

The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuses on fault detection and isolation, but they cannot provide an effective guide for the design for testability （DFT） to improve the PHM performance level. To solve the problem, a model of TSO for PHM systems is proposed. Firstly, through integrating the characteristics of fault severity and propa- gation time, and analyzing the test timing and sensitivity, a testability model based on failure evolution mechanism model （FEMM） for PHM systems is built up. This model describes the fault evolution- test dependency using the fault-symptom parameter matrix and symptom parameter-test matrix. Secondly, a novel method of in- herent testability analysis for PHM systems is developed based on the above information. Having completed the analysis, a TSO model, whose objective is to maximize fault trackability and mini- mize the test cost, is proposed through inherent testability analysis results, and an adaptive simulated annealing genetic algorithm （ASAGA） is introduced to solve the TSO problem. Finally, a case of a centrifugal pump system is used to verify the feasibility and effectiveness of the proposed models and methods. The results show that the proposed technology is important for PHM systems to select and optimize the test set in order to improve their performance level.

关键词： test selection and optimization （TSO） prognostics and health management （PHM） failure evolution mechanism model （FEMM） adaptive simulated annealing genetic algorithm （ASAGA）.

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

Behavior Consistency Computation for Workflow Nets With Unknown Correspondence

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 281-291页

作者： Mimi Wang guanjun liu Peihai Zhao Chungang Yan Changjun Jiang Department of Computer Science and Technology the Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China IEEE

Consistency degree calculation is established on the basis of known correspondence, but in real life, the correspondence is generally unknown, so how to calculate consistency of two models under unknown correspondence has become a problem. For this condition, we should analyze unknown correspondence due to the influence of different correspondences.In this paper we obtain the relations of transitions based on event relations using branching processes, and build a behavioral matrix of relations. Based on the permutation of behavioral matrix, we express different correspondences, and define a new formula to compute the maximal consistency degree of two workflow nets. Additionally, this paper utilizes an example to show these definitions, computation as well as the advantages.

关键词： Behavioral matrix branching process consistency degree unknown correspondence workflow net(WF-nets)

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

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：