检索结果-南通市图书馆

Privacy-preserving explainable AI: a survey

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(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

Prediction of BRIC Stock Price Using ARIMA,SutteARIMA,and Holt-Winters

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第1期70卷 523-534页

作者： Ansari Saleh Ahmar Pawan Kumar Singh nguyen Van thanh nguyen Viet Tinh Vo Minh hieu Department of Statistics Faculty of Mathematics and Natural ScienccesUniversitas Negeri MakassarMakassar90223Indonesia School of Humanities and Social Sciences Thapar Institute of Engineering and TechnologyPatiala147004India Faculty of Commerce Van Lang UniversityHo Chi Minh City70000Vietnam

The novel coronavirus has played a disastrous role in many countries *** outbreak became a major epidemic,engulfing the entire world in lockdown and it is now speculated that its economic impact might be worse than economic deceleration and *** paper identifies two different models to capture the trend of closing stock prices in Brazil(BVSP),Russia(***),India(BSESN),and China(SSE),i.e.,(BRIC)*** predict the stock prices for three daily time periods,so appropriate preparations can be undertaken to solve these ***,we compared the ARIMA,SutteARIMA and Holt-Winters(H-W)methods to determine the most effective model for predicting *** stock closing price of BRIC country data was obtained from Yahoo *** data dates from 01 November 2019 to 11 December 2020,then divided into two categories-training data and test *** data covers 01 November 2019 to 02 December *** days(03December 2020 to 11December 2020)of datawas tested to determine the accuracy of the models using training data as a *** measure the accuracy of the models,we obtained the means absolute percentage error(MAPE)and mean square error(MSE).Prediction model Holt-Winters was found to be the most suitable for forecasting the Brazil stock price(BVSP)while MAPE(0.50)and MSE(579272.65)with Holt-Winters(smaller than ARIMA and SutteARIMA),model SutteARIMA was found most appropriate to predict the stock prices of Russia(***),India(BSESN),and China(SSE)when compared to ARIMA and *** andMSE with SutteARIMA:Russia(MAPE:0.7;MSE:940.20),India(MAPE:0.90;MSE:207271.16),and China(MAPE:0.72;MSE:786.28).Finally,Holt-Winters predicted the daily forecast values for the Brazil stock price(BVSP)(12 December to 14 December 2020 i.e.,115757.6,116150.9 and 116544.1),while SutteARIMA predicted the daily forecast values of Russia stock prices(***)(12 December to 14 December 2020 i.e.,3238.06,3241.54 and 3245.01),India stock price(BSESN)(

关键词： SutteARIMA Holt-Winters ARIMA stock price COVID-19

Complexities and pitfalls in analyzing and interpreting mitochondrial DNA content in human cancer

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 Genetics and Genomics 2020年第7期47卷 349-359页

作者： hieu nguyen Thomas LaFramboise Vinmec Research Institute of Stem Cell and Gene Technology(VRSIG) 458 M inh KhaiVinh TuyHai Ba TrungHanoiViet Nam Department of Genetics and Genome Sciences Case Western Reserve University School of Medicine10900 Euclid AvenueClevelandOH44106USA

Mutations in the human mitochondrial genome have been observed in all types of human cancer,indicating that mutations might contribute to tumorigenesis,metastasis,recurrence,or drug *** possibility is appealing because of the known shift from oxidative metabolism to glycolysis,known as the Warburg effect,that occurs in *** DNA(mtDNA)mutations could either bematernally inherited and predispose to cancer(germ line mutations)or occur sporadically in the mtDNA of specific tissues(rissue-or tumor-specific somatic mutations)and contribute to the tumor initiation and progression ***-throughput sequencing technologies now enable comprehensive detection of mtDNA variation in tissues and bodily fluids,with the potential to be used as an early detectiontool that may impact the treatment of ***,we discuss insights into the roles of mtDNA mutations in carcinogenesis,highlighting the complexities involved in the analysis and interpretation of mitochondrial genomic *** challenges in studying their contribution to pathogenesis,and the value of mtDNA mutations in developing early detection,diagnosis,prognosis,and therapeuticstrategics for cancer.

关键词： Mitochondrial DNA Cancer Genetic variation

维普期刊数据库

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

在线全文

学校读者我要写书评

暂无评论

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).

维普期刊数据库

Graphene-driving novel strain relaxation towards AlN film and DUV photoelectronic devices

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2022年第7期11卷 1318-1319页

作者： hieu.P.T.nguyen New Jersey Institute of Technology Department of Electrical&Computer EngineeringNewarkNJ 07102USA

Graphene-driving strain-pre-store engineering enables the epitaxy of strain-free AlN film with low dislocation density for DUV-LED and the unique mechanism of strain-relaxation in QvdW epitaxy was demystified.

关键词： driving relaxation strain

Landslide Susceptibility Mapping Using RBFN-Based Ensemble Machine Learning Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

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)

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

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

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

维普期刊数据库

Mining fine-grained sequential travel patterns from social geo-tagged photos

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2018年第6期12卷 1255-1257页

作者： thanh-hieu BUI Seong-Bae PARK Institute of Research and Development Duy Tan UniversityDa Nang 550000Vietnam Department of Computer Science and Engineering Kyung Hee UniversityYongin 17104Korea

A huge amount of geo-tagged photos that contains broad knowledge about travel behaviors of human is generated and posted on social photo-sharing sites. In literature, many studies about mining travel patterns from geo-tagged social photos have been proposed. However, the existing studies lack of a comprehensive system to mine fine-grained travel patterns by utilizing extensions of sequential pattern mining. We consider the following questions for San Francisco City, CA, USA: 1) What are the popular travel routes for tourists if they have only four hours or eight hours for visiting? 2) Which POIs do international tourists prefer to visit after visiting Golden Gate Bridge? 3) Are there any differences in travel behavior between American tourists and international tourists, between male American tourists and female American tourists, between male international tourists and female international tourists? To address these questions, we define and implement a novel framework to mine fine-grained travel patterns from geo-tagged photos of a tourist destination.

关键词：

Electronic Band Structure of Carbon Nanotubes with Kekule Structure

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 Physics Letters 2013年第9期30卷 97-100页

作者： nguyen Ngoc hieu Le Cong Nhan Center of Research and Development Duy Tan UniversityK7/25 Quang TrungDa NangViet Nam Department of Environmental Science Saigon University273 An Duong VuongHo Chi Minh cityViet Nam

Electronic band structure of carbon nanotubes with the Kekule structure is studied by the tight-binding *** give a complete geometrical approach to structural properties of carbon nanotubes with bond alternation,including chiral and achiral *** the Kekule is introduced,all carbon nanotubes become semiconducting with a small band gap at the Fermi *** band gap of the carbon nanotubes depends only on the difference between C–C bond lengths or the resonance integrals.

关键词： carbon structure Fermi