检索结果-南通市图书馆

Depth perception on fundus images using a single-channel stereomicroscopy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2021年第3期4卷 68-76页

作者： Edalat Radfar Hyunseon Yu tien Son Ho Seung Ho Choi Byungjo Jung Department of Biomedical Engineering Yonsei University Wonju-siGangwon-do 26493 Republic of Korea Research Center for Science and Technology in Medicine Tehran University of Medical Sciences Tehran 14185-615Iran Institute of Metabolism and Systems Research University of Birmingham Edgbaston Birmingham B152TTUK

Typical fundus photography produces a two-dimensional *** makes it difficult to observe the microvascular and neural abnormalities,because the depth of the image is *** provide depth appreciation,we develop a single-channel stereoscopic fundus video imaging sys-tem based on a rotating *** respect to the pupil center,the rotating refractor laterally displaces the optical path and the *** allows standard monocular fundus cameras to generate stereo-parallax and image disparity through sequential image *** opti-mize our imaging system,characterize the stereo-base,and image an eyeball model and a rabbit *** virtual realities are considered,our imaging system can be a simple yet efficient technique to provide depth perception in a virtual space that allows users to perceive abnor-malities in the eye fundus.

关键词： Imaging systems ophthalmic optics and devices refraction vision-binocular and stereopsis

Using Informative Score for Instance Selection Strategy in Semi-Supervised Sentiment Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 4801-4818页

作者： Vivian Lee Lay Shan Gan Keng Hoon Tan tien Ping Rosni Abdullah School of Computer Sciences Universiti Sains MalaysiaPulau Pinang11800Malaysia

Sentiment classification is a useful tool to classify reviews about sentiments and attitudes towards a product or *** studies heavily rely on sentiment classification methods that require fully annotated ***,there is limited labelled text available,making the acquirement process of the fully annotated input costly and ***,semi-supervised methods emerge as they require only partially labelled input but perform comparably to supervised ***,some works reported that the performance of the semi-supervised model degraded after adding unlabelled instances into *** also shows that not all unlabelled instances are equally useful;thus identifying the informative unlabelled instances is beneficial in training a semi-supervised *** achieve this,an informative score is proposed and incorporated into semisupervised sentiment *** evaluation is performed on a semisupervised method without an informative score and with an informative *** using the informative score in the instance selection strategy to identify informative unlabelled instances,semi-supervised models perform better compared to models that do not incorporate informative scores into their *** the performance of semi-supervised models incorporated with an informative score is not able to surpass the supervised models,the results are still found promising as the differences in performance are subtle with a small difference of 2%to 5%,but the number of labelled instances used is greatly reduced from100%to 40%.The best finding of the proposed instance selection strategy is achieved when incorporating an informative score with a baseline confidence score at a 0.5:0.5 ratio using only 40%labelled data.

关键词： Document-level sentiment classification semi-supervised learning instance selection informative score

A novel semantic segmentation approach based on U-Net,WU-Net,and U-Net++deep learning for predicting areas sensitive to pluvial flood at tropical area

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2023年第1期16卷 3661-3679页

作者： Laura Melgar-García Francisco Martínez-álvarez Dieu tien Bui Alicia Troncoso Data Science&Big Data Lab Pablo de Olavide UniversitySevilleSpain GIS Group Department of Business and ITUniversity of South-Eastern NorwayGullbringvegen 36B?i Telemark3800Norway

Floods remain one of the most devastating weather-induced disastersworldwide, resulting in numerous fatalities each year and severelyimpacting socio-economic development and the ***, the ability to predict flood-prone areas in advance is crucialfor effective risk management. The objective of this research is to assessand compare three convolutional neural networks, U-Net, WU-Net, andU-Net++, for spatial prediction of pluvial flood with a case study at atropical area in the north of Vietnam. They are relative new convolutionalgorithms developed based on U-shaped architectures. For this task, ageospatial database with 796 historical flood locations and 12 floodindicators was prepared. For training the models, the binary crossentropywas employed as the loss function, while the Adaptive momentestimation (ADAM) algorithm was used for the optimization of themodel parameters, whereas, F1-score and classification accuracy (Acc)were used to assess the performance of the models. The results unequivocally highlight the high performance of the three models,achieving an impressive accuracy rate of 96.01%. The flood susceptibility maps derived from this research possess considerable utility for local authorities, providing valuable insights and informationto enhance decision-making processes and facilitate the implementation of effective risk management strategies.

关键词： Flash-flood assessment convolutional networks climate change GIS

Machine learning for molecular thermodynamics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2021年第3期34卷 227-239页

作者： Jiaqi Ding Nan Xu Manh tien Nguyen Qi Qiao Yao Shi Yi He Qing Shao College of Chemical and Biological Engineering Zhejiang UniversityHangzhou 310027China Chemical and Materials Engineering Department University of KentuckyLexingtonKY 40506USA Key Laboratory of Biomass Chemical Engineering of Ministry of Education Zhejiang UniversityHangzhou 310027China Department of Chemical Engineering University of WashingtonSeattleWA 98195USA

Thermodynamic properties of complex systems play an essential role in developing chemical engineering *** remains a challenge to predict the thermodynamic properties of complex systems in a wide range and describe the behavior of ions and molecules in complex *** learning emerges as a powerful tool to resolve this issue because it can describe complex relationships beyond the capacity of traditional mathematical *** minireview will summarize some fundamental concepts of machine learning methods and their applications in three aspects of the molecular thermodynamics using several *** first aspect is to apply machine learning methods to predict the thermodynamic properties of a broad spectrum of systems based on known *** second aspect is to integer machine learning and molecular simulations to accelerate the discovery of *** third aspect is to develop machine learning force field that can eliminate the barrier between quantum mechanics and all-atom molecular dynamics *** applications in these three aspects illustrate the potential of machine learning in molecular thermodynamics of chemical *** will also discuss the perspective of the broad applications of machine learning in chemical engineering.

关键词： Machine learning Thermodynamic properties Molecular engineering Molecular simulation Force field

Reappraisal of surgical decision-making in patients with splenic sclerosing angiomatoid nodular transformation:Case series and literature review

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

World Journal of Gastrointestinal Surgery 2021年第8期13卷 848-858页

作者： Hao Tseng Cheng-Maw Ho Yu-Wen tien School of Medicine National Taiwan University College of Medicine Department of Medical Education and Department of SurgeryNational Taiwan University Hospital Department of Surgery National Taiwan University Hospital and National Taiwan University College of Medicine

BACKGROUND Many clinicians and surgeons are unfamiliar with the sclerosing angiomatoid nodular transformation(SANT),which is gaining recognition as a benign splenic *** challenge that SANT is rare and whether surgical intervention could be avoided through critical imaging *** To evaluate the incidence of SANT among splenic tumors and the decisionmaking process of SANT *** Twenty hospitalized patients who underwent splenectomy in 2018 and 2019 in a tertiary university hospital were retrospectively reviewed,and their data on imaging,diagnosis,surgical indications,and courses were *** pathology results were confirmed by *** features differentiating SANT from other non-SANT splenic tumors were descriptively analyzed in this case *** Fourteen out of 20 patients who underwent splenectomy had splenic tumors,including 3 SANTs(21%splenic tumors),6 non-SANT benign lesions(43%),2 metastatic tumors,and 3 *** on T2-weighted magnetic resonance imaging(MRI),spoke wheel enhancing pattern in contrasted computed tomography or MRI,and cold spot(low fluorodeoxyglucose uptake)in positron emission tomography(PET)scan helped establish the diagnosis of ***,presenting with a hot spot on the PET scan were differentiated from *** indications were reformatted for splenic *** need not be performed in patients with typical imaging features of *** SANT is not a rare disease entity in clinical *** should not be routinely indicated as the only management option for SANT with typical imaging features.

关键词： Splenic tumor Diagnosis Surgical decision-making Sclerosing angiomatoid nodular transformation Retrospective study

Host movement,transmission hot spots,and vector-borne disease dynamics on spatial networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Infectious Disease Modelling 2022年第4期7卷 742-760页

作者： Omar Saucedo Joseph H.tien Department of Mathematics Virginia TechBlacksburgVAUSA Department of Mathematics The Ohio State UniversityColumbusOHUSA

We examine how spatial heterogeneity combines with mobility network structure to influence vector-borne disease ***,we consider a Ross-Macdonald-type disease model on n spatial locations that are coupled by host movement on a strongly connected,weighted,directed *** derive a closed form approximation to the domain reproduction number using a Laurent series expansion,and use this approximation to compute sensitivities of the basic reproduction number to model *** illustrate how these results can be used to help inform mitigation strategies,as a case study we apply these results to malaria dynamics in Namibia,using published cell phone data and estimates for local disease *** analytical results are particularly useful for understanding drivers of transmission when mobility sinks and transmission hot spots do not coincide.

关键词： Human movement Vector-borne disease Spatial networks Reproduction number Laurent series

Hepatitis B virus X protein suppresses virus-triggered IRF3 activation and IFN-β induction by disrupting the VISA-associated complex

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cellular & Molecular Immunology 2010年第5期7卷 341-348页

作者： Xianmiao Wang Ying Li Aiping Mao Chao Li Yongkui Li Po tien College of Life Sciences Modern Virology CenterWuhan UniversityWuhan 430072China

Viral RNAs produced during viral infection are recognized by the cytoplasmic RNA helicases retinoic acid-inducible gene-I(RIG-I)and melanoma differentiation-associated gene 5(MDA5).A central adapter protein downstream of RIG-I and MDA5 is the mitochondrial membrane protein virus-induced signaling adaptor(VISA),which mediates the induction of type I interferons(IFNs)through the activation of transcription factors such as nuclear factor-kappaB(NF-kB)and IFN-regulatory factor-3(IRF3).Here we found that hepatitis B virus(HBV)-encoded X protein(HBx)acts as an inhibitor of virus-triggered IRF3 activation and IFN-b *** and plaque assays indicate that HBx inhibits signaling by components upstream but not downstream of *** experiments indicate that HBx interacts with VISA and disrupts the association of VISA with its upstream and downstream *** findings suggest that HBx acts as a suppressor of virus-triggered induction of type I IFNs,which explains the observation that HBV causes transient and chronic infection in hepatocytes but fails to activate the pattern recognition receptor-mediated IFN induction pathways.

关键词： HBx innate immunity signal transduction type I interferons VISA

Spatial prediction of rainfall-induced shallow landslides using hybrid integration approach of Least-Squares Support Vector Machines and differential evolution optimization:a case study in Central Vietnam

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2016年第11期9卷 1077-1097页

作者： Dieu tien Bui Binh Thai Pham Quoc Phi Nguyen Nhat-Duc Hoang Geographic Information System Group Department of Business Administration and Computer ScienceUniversity College of Southeast NorwayBøi TelemarkNorway Faculty of Geomatics and Land Administration Hanoi University of Mining and GeologyHanoiVietnam Department of Civil Engineering Gujarat Technological UniversityAhmedabadGujaratIndia Department of Geotechnical Engineering University of Transport TechnologyHa NoiVietNam Department of Environmental Sciences Hanoi University of Mining and GeologyHanoiVietnam Faculty of Civil Engineering Institute of Research and DevelopmentDuy Tan UniversityDanangVietnam

This study represents a hybrid intelligence approach based on the differential evolution optimization and Least-Squares Support Vector Machines for shallow landslide prediction,named as *** LSSVM is used to establish a landslide prediction model whereas the DE is adopted to search the optimal tuning parameters of the LSSVM *** this research,a GIS database with 129 historical landslide records in the Quy Hop area(Central Vietnam)has been collected to establish the hybrid *** receiver operating characteristic(ROC)curve and area under the curve(AUC)were used to assess the performance of the newly constructed *** results show that the proposed model has high performances with approximately 82%of AUCs on both training and validating *** model’s results were compared with those obtained from other methods,Support Vector Machines,Multilayer Perceptron Neural Networks,and J48 Decision *** result comparison demonstrates that the DE-LSSVMSLP deems best suited for the dataset at hand;therefore,the proposed model can be a promising tool for spatial prediction of rainfall-induced shallow landslides for the study area.

关键词： Shallow landslide Least-Squares Support Vector Machines differential evolution GIS Vietnam

TOWARDS REAL-TIME CUSTOMIZED MANAGEMENT OF SUPPLY AND DEMAND CHAINS

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Systems Science and Systems Engineering 2004年第3期13卷 257-278页

作者： JamesM.tien AnanthKRISHNAMURTHY AliYASAR DepartmentofDecisionSciencesandEngineeringSystemsRensselaerPolytechnicinstitute 110EighthSt.TroyNewYork12180USA

Our focus herein is on developing an effective taxonomy for the simultaneous and real-timemanagement of supply and demand *** specifically,the taxonomy is developed in terms ofits underpinning components and its research *** a components perspective,we first considerthe value chain of supplier,manufacturer,assembler,retailer,and customer,and then develop aconsistent set of definitions for supply and demand chains based on the location of the customer orderpenetration *** a research perspective,we classify the methods that are employed in themanagement of these chains,based on whether supply and/or demand are flexible or ***,our taxonomy highlights a very critical research area at which both supply and demandare flexible,thus *** management of supply and demand chains sets the stagefor mass customization which is concerned with meeting the needs of an individualized *** and real-time management of supply and demand chains set the stage forreal-time mass customization(e.g.,wherein a tailor first laser scans an individual's upper torso andthen delivers a uniquely fitted jacket within a reasonable period,while the individual is waiting).Thebenefits of real-time mass customization can not be over-stated as products and services becomeindistinguishable and are co-produced in real-time,resulting in an overwhelming economicadvantage.

关键词： Value chain supply chain demand chain taxonomy real-time management mass customization information and decision technologies services