检索结果-南通市图书馆

Transfer Learning for Disease Diagnosis from Myocardial Perfusion SPECT Imaging

Computers, Materials & Continua 2022年第12期73卷 5925-5941页

作者： Phung Nhu Hai nguyen chi thanh nguyen thanh Trung Tran Trung Kien Institute of Information Technology AMSTHanoi11307Vietnam Department of Medical Equipment 108 Military Central HospitalHanoi11610Vietnam

Coronary artery disease(CAD)is one of the most common pathological conditions and the major global cause of *** perfusion imaging(MPI)using single-photon emission computed tomography(SPECT)is a non-invasive method and plays an essential role in diagnosing ***,there is currently a shortage of doctors who can diagnose using SPECT-MPI in developing countries,especially *** on deploying machine learning and deep learning in supporting CAD diagnosis has been noticed for a long ***,these methods require a large dataset and are therefore time-consuming and *** study aims to develop a cost-effective and high-performance CAD classification model to support doctors in these *** this paper,we propose a transfer learning framework for a multi-stage training process with different learning *** process consists of two training stages:a warming up stage in which all layers of a pre-trained model(on ImageNet dataset)are frozen;and a finetuning stage in which a small amount of the top layers are unfrozen and then retrained with a lower learning *** dataset for this study consists of the polar maps from 218 *** popular CNN-based pre-trained models have been investigated,and ResNet152V2-based model has obtained the highest performances with an accuracy of 95.5%,area under the receiver operating characteristic curve(AUC)score 0.932,sensitivity 94.4%,precision 96.4%,and F1-score 95.2%.These performances are competitive or even better than all state-of-the-art approaches in terms of classification accuracy and *** also apply the class activation mapping technique to help explain the model’s predictions and increase the model’s reliability,proving capable of assisting the SPECT image readers in the CAD diagnosis.

关键词： Coronary artery disease deep learning transfer learning SPECTMPI polar maps

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

Privacy-preserving explainable AI: a survey

引用

Science china(Information Sciences) 2025年第1期68卷 23-56页

作者： thanh Tam nguyen thanh Trung HUYNH Zhao REN thanh Toan nguyen Phi Le nguyen Hongzhi YIN Quoc Viet Hung nguyen School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

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

Effect of Melt Mixing Time in Internal Mixer on Mechanical Properties and Crystallization Behavior of Glycidyl Methacrylate Grafted Poly (Lactic Acid)

引用

Journal of Materials Science and Chemical Engineering 2015年第7期3卷 102-107页

作者： nguyen chi thanh Chaiwat Ruksakulpiwat Yupaporn Ruksakulpiwat School of Polymer Engineering Institute of Engineering Suranaree University of Technology Nakhon Ratchasima Thailand Department of Chemistry Faculty of Science Khon Kaen University Khon Kaen Thailand

Glycidyl methacrylate (GMA) was grafted onto poly (lactic acid) (PLA) by melt mixing in internal mixer using dicumyl peroxide (DCP) as an initiator. The results from proton nuclear magnetic resonance (1H-NMR) and Fourier transform infrared (FTIR) spectroscopy indicated that the grafting reaction of GMA onto PLA took place successfully. The impact strength of PLA-g-GMA was significantly higher than that of pure PLA. The crystallinity of PLA, obtained from differential scanning calorimetry (DSC), decreased after grafting. In order to obtain the optimal mixing conditions, the mixing time was varied into 7, 10 and 14 min. The optimum mixing time of 10 min was found to give the optimum mechanical properties of glycidyl methacrylate grafted poly (lactic acid) (PLA-g- GMA). However, the mixing time played no important role in impact behavior of PLA-g-GMA. In addition, the highest crystallinity was obtained with the PLA-g-GMA prepared with the mixing time of 7 min.

关键词： PLA Grafting PLA-g-GMA Mixing Time Crystallization

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

Hyperstatic reaction method for calculations of tunnels with horseshoe-shaped cross-section under the impact of earthquakes

引用

Earthquake Engineering and Engineering Vibration 2020年第1期19卷 179-188页

作者： thanh nguyen chi Gospodarikov Alexandr Saint Petersburg Mining University Saint PetersburgRussia Federation Hanoi University of Mining and Geology HanoiVietnam

Tunnels are now an integral part of the infrastructure in major cities around the world. For many reasons, these tunnels have horseshoe-shaped cross-sections with round top and flat bottom. This paper presents some improvements to the use of the Hyperstatic Reaction Method-HRM for analysing tunnels with horseshoe-shaped cross-sections when these tunnels operate under the influence of earthquakes, particularly in cases when the tunnel lining is a continuous lining. The analysis used parameters of a tunnel from the Hanoi metro system, as well as parameters of the strongest earthquake that may occur in the central Hanoi area in the improved HRM and 2 D numerical methods using the ABAQUS software. On the basis of the results obtained, the paper gives conclusions about the HRM methodology when it is used to calculate tunnels that have horseshoe cross-sections operating under the influence of earthquakes.

关键词： hyperstatic reaction method earthquake horseshoe cross-section impact tunnel

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 Chemical Reactor Network for Oxides of Nitrogen Emission Prediction in Gas Turbine Combustor

引用

Journal of Thermal Science 2014年第3期23卷 279-284页

作者： nguyen thanh Hao Industrial University of HochiMinh City

This study presents the use of a new chemical reactor network(CRN) model and non-uniform injectors to predict the NOx emission pollutant in gas turbine combustor. The CRN uses information from Computational Fluid Dynamics(CFD) combustion analysis with two injectors of CH4-air mixture. The injectors of CH4-air mixture have different lean equivalence ratio, and they control fuel flow to stabilize combustion and adjust combustor's equivalence ratio. Non-uniform injector is applied to improve the burning process of the turbine combustor. The results of the new CRN for NOx prediction in the gas turbine combustor show very good agreement with the experimental data from Korea Electric Power Research Institute.

关键词： Chemical Reactor Networks (CRN) Computational Fluid Dynamics (CFD) Perfectly Stirred Reactor (PSR) Plug Flow Reactor (PFR) Gas Turbine Combustor Oxides of Nitrogen Emission (NOx).

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

Landslide Susceptibility Mapping Using RBFN-Based Ensemble Machine Learning Models

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 467-500页

作者： Landslide Susceptibility Mapping Using RBFN-Based Ensemble Machine Learning Models Duc-Dam nguyen nguyen Viet Tiep Quynh-Anh Thi Bui Hiep Van Le Indra Prakash Romulus Costache Manish Pandey Binh Thai Pham Faculty of Civil Engineering University of Transport TechnologyThanh XuanHa Noi100000Vietnam Faculty of Hydraulic Engineering Hanoi University of Civil EngineeringHa Noi100000Vietnam DDG(R)Geological Survey of India Gandhinagar382010India Research Institute of the University of Bucharest Bucharest050663Romania National Institute of Hydrology and Water Management Bucharest013686Romania Department of Civil Engineering Transilvania University of BrasovBrasov500152Romania Danube Delta National Institute for Research and Development Tulcea820112Romania Marwadi University Research Center(MURC) Marwadi UniversityRajkotGujaratBharat360003India Department of Civil Engineering Faculty of Engineering&TechnologyMarwadi UniversityRajkotGujaratBharat360003India

This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and ***,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and *** models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to *** factors were instrumental in predicting the output variable,which was the probability of landslide *** analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other *** AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of *** results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.

关键词： Landslide susceptibility map spatial analysis ensemble modelling information values(IV)

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

Multilevel Threshold Based Image Denoising in Curvelet Domain

引用

Journal of Computer Science & Technology 2010年第3期25卷 632-640页

作者： nguyen thanh Binh Ashish Khare Department of Electronics and Communication University of Allahabad

In this paper, we propose a multilevel thresholding technique for noise removal in curvelet transform domain which uses cycle-spinning. Most of uncorrelated noise gets removed by thresholding curvelet coefficients at lowest level, while correlated noise gets removed by only a fraction at lower levels, so we used multilevel thresholding on curvelet coefficients. The threshold in the proposed method depends on the variance of curvelet coefficients, the mean and the median of absolute curvelet coefficients at a particular level which makes it adaptive in nature. Results obtained for 2-D images demonstrate an improved performance over other recent related methods available in literature.

关键词： curvelet transform denoising multilevel thresholding cycle-spinning

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

Schistosomal appendicitis:A serious and often misdiagnosed condition

引用

World Journal of Clinical Cases 2025年第10期13卷 62-64页

作者： Phi Duong nguyen thanh Kien Lam Orthopaedic-Burn-Plastic Surgery City Children’s HospitalHo Chi Minh City 71815Viet Nam The Faculty of Medical Technology Van Lang UniversityHo Chi Minh City 700000Viet Nam

Schistosomal appendicitis(SA)is a rare but serious complication of schistosomiasis,a parasitic disease affecting over 250 million people worldwide.A recent retrospective study by Wang et al provides important insights into the clinicopathological characteristics of *** study compared 136 cases of SA to 5418 cases of non-SA over a ten-year *** findings include a higher average age of SA patients(61.73 years vs 35.8 years for non-SA),a higher proportion of acute on chronic appendicitis(33.1%vs 16%),and a significantly higher incidence of colorectal cancer(11.7%vs 2.2%).Despite these differences,SA remains a diagnostic challenge due to its nonspecific clinical presentation and lack of specific laboratory *** study also highlights the persistent prevalence of SA,accounting for 1.6%-3.4%of all appendicitis cases each year from 2013 to *** findings underscore the need for enhanced awareness,early detection,and prompt treatment of SA in endemic *** the association with colorectal cancer,patients with SA require thorough screening and *** research into the pathogenesis and diagnostic markers of SA is *** the global battle against schistosomiasis continues,targeted efforts to diagnose and manage SA can significantly improve patient outcomes.

关键词： Schistosomal appendicitis Schistosomiasis Colorectal cancer Misdiagnosis Clinicopathological characteristics

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

Prediction of Shear Bond Strength of Asphalt Concrete Pavement Using Machine Learning Models and Grid Search Optimization Technique

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 691-712页

作者： Quynh-Anh Thi Bui Dam Duc nguyen Hiep Van Le Indra Prakash Binh Thai Pham Civil Engineering Department University of Transport Technology54 Trieu KhucThanh XuanHanoi100000Vietnam DDG(R)Geological Survey of India Gandhinagar382010India

Determination of Shear Bond strength(SBS)at interlayer of double-layer asphalt concrete is crucial in flexible pavement *** study used three Machine Learning(ML)models,including K-Nearest Neighbors(KNN),Extra Trees(ET),and Light Gradient Boosting Machine(LGBM),to predict SBS based on easily determinable input ***,the Grid Search technique was employed for hyper-parameter tuning of the ML models,and cross-validation and learning curve analysis were used for training the *** models were built on a database of 240 experimental results and three input variables:temperature,normal pressure,and tack coat *** validation was performed using three statistical criteria:the coefficient of determination(R2),the Root Mean Square Error(RMSE),and the mean absolute error(MAE).Additionally,SHAP analysis was also used to validate the importance of the input variables in the prediction of the *** show that these models accurately predict SBS,with LGBM providing outstanding ***(Shapley Additive explanation)analysis for LGBM indicates that temperature is the most influential factor on ***,the proposed ML models can quickly and accurately predict SBS between two layers of asphalt concrete,serving practical applications in flexible pavement structure design.

关键词： Shear bond asphalt pavement grid search optimization machine learning

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

Bubble entrapment during the recoil of an impacting droplet

引用

Microsystems & Nanoengineering 2020年第1期6卷 768-774页

作者： thanh-Vinh nguyen Masaaki Ichiki Sensing System Research Center National Institute of Advanced Industrial Science and Technology(AIST)Japan1-2-1 NamikiTsukuba-shiIbaraki 305-8564Japan

When a droplet impacts a(super-)hydrophobic surface,there is a range of Weber numbers within which bubble entrapment will occur during droplet recoil due to closure of the air cavity developed when the droplet spreads out during the *** this study,we studied bubble entrapment using a microelectromechanical system(MEMS)-based acoustic sensor fabricated on a *** found that bubble entrapment is followed by an acoustic vibration that can be detected by the ***,the frequency of the vibration is inversely proportional to the radius of the droplet,which indicates that this vibration is the resonant oscillation of the ***,the MEMS-based acoustic sensor can be used not only to detect but also to measure the size of the entrapped ***,we demonstrated that it is possible to prevent bubble formation by allowing the air to escape to the underside of the droplet contact *** can be done by creating through-holes on the substrate or decorating the substrate with sufficiently large textures.

关键词： bubble radius resonant

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

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：