检索结果-南通市图书馆

Predicting 3D Radiotherapy Dose-Volume Based on Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2024年第2期39卷 319-335页

作者： Do Nang Toan Lam Thanh Hien Ha Manh Toan Nguyen Trong Vinh Pham trung hieu Institute of Information Technology Vietnam Academy of Science and TechnologyHanoi10072Vietnam Faculty of Information Technology Lac Hong UniversityBien HoaDong Nai76120Vietnam

Cancer is one of the most dangerous diseaseswith *** of the principal treatments is radiotherapy by using radiation beams to destroy cancer cells and this workflow requires a lot of experience and skill from doctors and *** our study,we focused on the 3D dose prediction problem in radiotherapy by applying the deeplearning approach to computed tomography(CT)images of cancer *** image data has more complex characteristics than normal image data,and this research aims to explore the effectiveness of data preprocessing and augmentation in the context of the 3D dose prediction *** proposed four strategies to clarify our hypothesis in different aspects of applying data preprocessing and *** strategies,we trained our custom convolutional neural network model which has a structure inspired by the U-net,and residual blocks were also applied to the *** output of the network is added with a rectified linear unit(Re-Lu)function for each pixel to ensure there are no negative values,which are absurd with radiation *** experiments were conducted on the dataset of the Open Knowledge-Based Planning Challenge which was collected from head and neck cancer patients treatedwith radiation *** results of four strategies showthat our hypothesis is rational by evaluating metrics in terms of the Dose-score and the Dose-volume histogram score(DVH-score).In the best training cases,the Dose-score is 3.08 and the DVH-score is *** addition,we also conducted a comparison with the results of another study in the same context of using the loss function.

关键词： CT image 3D dose prediction data preprocessing augmentation

越南昆嵩地体早古生代花岗岩地球化学特征及对三岐–福山洋俯冲的响应

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

大地构造与成矿学 2024年

作者：赖宗婷张玉芝余小清钱鑫 PHAM trung hieu 徐畅王岳军中山大学地球科学与工程学院广东省地球动力作用与地质灾害重点实验室南方海洋科学与工程广东省实验室(珠海) University of Science VNU-HCM 227Nguyen Van Cu Street

昆嵩地体位于印支陆块东部,广泛发育早古生代岩浆作用,是了解东南亚原特提斯洋演化的关键地区。但长久以来此地区原特提斯洋的俯冲极性与时间争议较大。本文对该地体的一套早古生代花岗岩进行了岩相学、锆石U-Pb年代学、锆石原位Hf同位... 详细信息

昆嵩地体位于印支陆块东部,广泛发育早古生代岩浆作用,是了解东南亚原特提斯洋演化的关键地区。但长久以来此地区原特提斯洋的俯冲极性与时间争议较大。本文对该地体的一套早古生代花岗岩进行了岩相学、锆石U-Pb年代学、锆石原位Hf同位素以及全岩主微量和Sr-Nd-Pb同位素研究。年代学结果显示该套花岗岩的结晶年龄为446～440Ma。花岗岩样品的K2O为2.14%～5.92%, Na2O+K2O为5.49%～8.25%,显示高钾钙碱性特征。其A/CNK值为1.03～1.18,为过铝质S型花岗岩。样品均显示明显的大离子亲石元素（如Rb、Th和U等）富集以及高场强元素（如Nb、Ta、Sr和Ti等）亏损,并具有强烈的Eu负异常（Eu/Eu*=0.23～0.69）。样品呈现变化范围较大的锆石原位Hf同位素组成(εHf（t）=-19.84～+1.99)以及新太古代-中元古代的Hf二阶模式年龄(tDM2=2.70～1.28 Ga),且具有富集的全岩Nd同位素组成(εNd（t）=-10.3～-6.5)。本文研究显示该套早古生代花岗岩是古老变沉积岩和基性变火成岩部分熔融的产物。结合区域地质研究表明,越南中部昆嵩地块早古生代花岗岩形成于俯冲作用下的岛弧背景,响应于区域上印支陆块内部原特提斯三岐–福山洋的南向俯冲过程。

关键词：昆嵩地体早古生代 S型花岗岩原特提斯洋三岐–福山洋俯冲作用

3D modeling of transformation of gaseous pollutants in the high-pressure turbine of an aircraft engine

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Propulsion and Power Research 2020年第1期9卷 1-14页

作者： trung hieu Nguyen Phuong Nguyen-Tri Francois Garnier Department of Mechanical Engineering École de Technologie Supérieure(ETS)MontrealQuebecH3C 1K3Canada Institute of Research and Development Duy Tan UniversityDa Nang550000Viet Nam Department of Chemistry Biochemistry and PhysicsUniversitédu QuébecàTrois-RivièresUniversity of QuebecTrois-Rivières(Québec)G9A 5H7Canada

Aircraft emissions contribute to global climate change and regional air pollution near *** the formation and the transformation of emissions in the aircraft engine is essential to properly quantify the environmental impact and air ***,precise investigation of chemical process in the turbine is challenging because of the complexity of the transformation process in the complex flow relating to the moving blade at high temperature and high *** present here,the first published model study of 3D chemical formations inside a high-pressure turbine and first time to compare three numerical solutions(1D,2D and 3D calculations)of transformation of trace species inside an aircraft *** model has simulated the evolution of principal precursor pollutant gases(NOx and SOx)and other species(hydrogen,oxygen species and carbon oxides).Our results also indicated strong dissimilarities in chemical transformations of 3D *** comparing the three solutions,the results obtained showed that the difference of mole fractions of species can be under predicted by 75%between 1D and 2D calculations and in the comparison of 2D and 3D calculation,the under predicted difference may be 90%.

关键词： Gaseous pollutants High-pressure turbine Aircraft engine 3D modeling

A review of the formulation and application of the spatial equilibrium models to analyze policy

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 Forestry Research 2011年第4期22卷 671-679页

作者： phan Sy hieu Steve Harrison The Centre for Informatics and Statistics Ministry of Agriculture and Rural Development in Vietnam No. 2 Ngoc Ha Street Ba Dinh district Hanoi Vietnam Associate Professor the School of Economics the University of Queensland Australia.

This paper reviews alternative market equilibrium models for policy analysis. The origin of spatial equilibrium models and their application to wood and wood-processing industries are described. Three mathematical programming models commonly applied to solve spatial problems - namely linear programming, non-linear programming and mixed complementary programming - are reviewed in terms of forms of objective functions and constraint equalities and inequalities. These programming are illustrated with numerical examples. Linear programming is only applied in transportation problems to solve quantities trans, ported between regions when quantities supplied and demanded in each region are already known. It is argued that linear programming can be applied in broader context to transportation problems where supply and demand quantities are unknown and are linear. In this context, linear programming is seen as a more convenient method for modelers because it has a simpler objective function and does not require as strict conditions, for instance the equal numbers of variables and equations required in mixed complementary programming. Finally, some critical insights are provided on the interpretation of optimal solutions generated by solving spatial equilibrium models.

关键词： simplex method reduced-gradient linear programming non-linear programming mixed complementary programming

A hierarchical system to predict behavior of soil and cantilever sheet wall by data-driven models

在线全文

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2022年第6期16卷 667-684页

作者： Nang Duc BUI hieu Chi phan Tiep Duc PHAM Ashutosh Sutra DHAR Institute of Techniques for Special Engineering Le Quy Don Technical UniversityHanoi 100000Vietnam Faculty of Engineering and Applied Science Memorial University of NewfoundlandSt.John’sNL A1B 3X5Canada

The study proposes a framework combining machine learning(ML)models into a logical hierarchical system which evaluates the stability of the sheet wall before other *** study uses the hardening soil(HS)model to develop a 200-sample finite element analysis(FEA)database,to develop the ML ***,a system containing three trained ML models is proposed to first predict the stability status(random forest classification,RFC)followed by 1)the cantilever top horizontal displacement of sheet wall(artificial neural network regression models,RANN1)and 2)vertical settlement of soil(RANN2).The uncertainty of this data-driven system is partially investigated by developing 1000 RFC models,based on the application of random sampling technique in the data splitting *** on the distribution of the evaluation metrics reveals negative skewed data toward the 1.0000 *** implies a high performance of RFC on the database with medians of accuracy,precision,and recall,on test set are 1.0000,1.0000,and 0.92857,*** regression ANN models have coefficient of determinations on test set,as high as 0.9521 for RANN1,and 0.9988 for RANN2,*** parametric study for these regressions is also provided to evaluate the relative insight influence of inputs to output.

关键词： finite element analysis cantilever sheet wall machine learning artificial neural network random forest

Apply neural network for improving production planning at Samarang petrol mine

在线全文

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2016年第2期9卷 126-143页

作者： Quoc trung Pham Thi Kim Dung phan School of Industrial Management HCMC University of TechnologyHo Chi Minh CityVietnam Schlumberger Information Solution Schlumberger Malaysia ServicesKuala LumpurMalaysia

Purpose-Artificial neural network(ANN)is considered a good solution for building non-linear relationship between input and output parameters,which is suitable for solving production back allocation,which is the most important step for production planning of petroleum *** purpose of this paper is to suggest a solution for solving production back allocation problem at Samarang petrol mine based on ANN ***/methodology/approach-In this study,well operational parameters’surveillance was conducted and ANN was used to build relationships between operation parameters and production *** method is used for testing and evaluating the possibility of using ANN for supporting production planning at Samarang ***-Consequently,the proposed ANN solution can increase the accuracy of predicted values and could be used for supporting production planning at Samarang *** ANN uses well test data for training and predicting(without adding new devices),it could be a feasible and cheap *** limitations/implications-There is a need for applying other methods,such as:support machine vector,non-linear autoregressive models,*** better evaluation of ANN *** implications-The ANN models helped operation engineers to understand well production performance and make decision to improve production plan in timely *** solution could be generalized for the whole mine or to similar petroleum mines in ***/value-This paper aims to propose a solution based on ANN for solving production back allocation problem of petroleum *** solution is tested at Samarang mine.

关键词： Malaysia Artificial neural network Petroleum industry Production back allocation Production plan Samarang mine

Cloning, Overexpression and Characterization of the Phytase Gene （PhyA）from Aspergillus Fumigatus Sp.

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cloning, Overexpression and Characterization of the Phytase ...

作者： phan trung hieu 华东理工大学

学位级别：硕士

Phytate, myo-inositol1,2,3,4,5,6-hexakisphosphate, is the primary source of inosi-tol and the major storage form phosphorus in agricultural feedstuffs, such as cereals, leg-umes, and oilseeds. Phytase, myo-inositol hexakisphosphate hydrolase （EC3.***.3.8for3-phytase and3.***.8.26for6-phytase）, catalyzes the hydrolysis of phytate into myo-inositol and inorganic phosphates. Monogastric animals such as pigs and chickens are incapable of digesting phytate phosphorus due to the lack of, or low levels of, phytase activity in their digestive systems. Supplementation of phytase in these animals’feedstuffs enhances not only the nutritional quality of phytate-rich feed, but also the growth performance of the animals, thus decreasing phosphorus pollution in areas of intensive animal agriculture. The potential industrial applications of phytase increase the interest of isolation of new bacte-rial strains producing novel and efficient phytases is increasing. In this thesis, a phytase producing Aspergillus fumigatus sp （A. fumigatus sp） specie, was isolated and identified, the gene phyA encoding its thermostable phytase was cloned and heterologously expressed in ***, active recombinant phytase was purified from in-clusion bodies and then its thennostability and the pH dependence were assayed in detail. Firstly, isolation of A. fumigatus phytase producing was selected by size of clear zone on the plate with modified phytase screening medium. Secondly, total RNA was extracted from A. fumigatus grown on modified phytase screening medium, the cDNA libraries were generated by RevertAidTM First Strand cDNA Synthesis kit. The gene encoding phytase of A. fumigatus without signal peptide and intron, PhyA, which comprises1,329bp and encodes443amino-acid residues, was PCR amplified and sequenced. The nucleotide sequence of A. fumigatus phytase gene showed99%identities to that of A. fumigatus Af293phytase and67%homology to that of A. niger phytase. The deduced amino acid sequence of

关键词：植酸酶基因基因克隆包涵体重折叠霉菌

Sorting by Restricted-Length-Weighted Reversals

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2005年第2期3卷 120-127页

作者： Thach Cam Nguyen hieu trung Ngo Nguyen Bao Nguyen Department of Mathematics Singapore 117543. School of Computing National University of Singapore Singapore 117543.

Classical sorting by reversals uses the unit-cost model, that is, each reversal consumes an equal cost. This model limits the biological meaning of sorting by reversal. Bender and his colleagues extended it by assigning a cost function f（1） = l^a for all a≥ 0, where l is the length of the reversed subsequence. In this paper, we extend their results by considering a model in which long reversals are prohibited. Using the same cost function above for permitted reversals, we present tight or nearly tight bounds for the worst-case cost of sorting by reversals. Then we develop algorithms to approximate the optimal cost to sort a given 0/1 sequence as well as a given permutation. Our proposed problems are more biologically meaningful and more algorithmically general and challenging than the problem considered by Bender et al. Furthermore, our bounds are tight and nearly tight, whereas our algorithms provide good approximation ratios compared to the optimal cost to sort 0/1 sequences or permutations by reversals.

关键词： reversal sorting length-weighted permutation

越南西北部phan Si Pan地区新生代埃达克质侵入岩时代、成因及构造意义——U-Pb锆石年龄、元素地球化学和Hf同位素证据

在线全文

学校读者我要写书评

暂无评论

岩石学报 2012年第9期28卷 3031-3041页

作者： hieu Pham trung 王涛童英 Faculty of Geology University of Sciences VNU-HCM227-Nguyen Van Cu StrHo Chi MinhVietnam Department of Geology Hanoi University of Mining and GeologyHanoiVietnam 中国地质科学院地质研究所北京100037

越南西北部phanSiPan地区新生代花岗岩,高SiO2(69.95%～70.52%)、A12O3(15.77%～17.11%)、K2O(4.97%～5.63%)、Na2O(4.29%～4.98%),K2O/Na2O=1.02～1.31、Sr(744×10-6～1316×10-6),贫Y(6.93×10-6～8.06×10-6),低MgO和CaO,富集LILE元素及LREE,亏损HREE具有典型的埃达克岩特征。采用LA-ICPMS方法对该岩体进行了U-Pb同位素定年和Hf同位素分析,结果表明该岩体为始新世(38Ma)岩浆活动的产物。锆石Hf同位素研究结果显示,εHf(t)变化范围为-5.5至+7.3,二阶段Hf模式年龄(tDM2)为652Ma至1466Ma、集中在1.1～1.3Ga,说明花岗岩岩体主要由中-(新)元古代地壳物质部分熔融形成。部分锆石具有正的εHf(t)值,可能指示花岗岩岩浆形成的过程中存在壳-幔混合相互作用。越南西北部phan Si Pan地区新生代花岗岩和扬子地块-(哀牢山-金沙江-红河带)高钾富碱的岩石形成的时代和机制具有密切的关系,可能与印度-亚洲大陆的碰撞导致红河带区域性走滑断裂系统的形成有关。

关键词：埃达克质岩锆石U-Pb年龄 Hf同位素越南西北部