检索结果-南通市图书馆

维普期刊数据库

Deep learning long short-term memory combined with discrete element method for porosity prediction in gravel-bed rivers

在线全文

学校读者我要写书评

暂无评论

International Journal of Sediment Research 2023年第1期38卷 128-140页

作者： Duong tran Anh Ahad Hasan Tanim Daniel Prakash Kushwaha Quoc bao Pham Van Hieu Bui HUTECH University Center for River Harbor and Landslide Research Chittagong University of Engineering & Technology Govind Ballabh Pant University of Agriculture and Technology Institute of Applied Technology Thu Dau Mot University Faculty of Mechanical Engineering Thuyloi University

The porosity of gravel riverbed material often is an essential parameter to estimate the sediment transport rate, groundwater-river flow interaction, river ecosystem, and fluvial geomorphology. Current methods of porosity estimation are time-consuming in simulation. To evaluate the relation between porosity and grain size distribution(GSD), this study proposed a hybrid model of deep learning Long Short-Term Memory(LSTM) combined with the Discrete Element Method(DEM). The DEM is applied to model the packing pattern of gravel-bed structure and fine sediment infiltration processes in threedimensional(3D) space. The combined approaches for porosity calculation enable the porosity to be determined through real time images, fast labeling to be applied, and validation to be done. DEM outputs based on the porosity dataset were utilized to develop the deep learning LSTM model for predicting bed porosity based on the GSD. The simulation results validated with the experimental data then segregated into 800 cross sections along the vertical direction of gravel pack. Two DEM packing cases, i.e., clogging and penetration are tested to predict the porosity. The LSTM model performance measures for porosity estimation along the z-direction are the coefficient of determination(R~2), root mean squared error(RMSE), and mean absolute error(MAE) with values of 0.99, 0.01, and 0.01 respectively, which is better than the values obtained for the Clogging case which are 0.71, 0.14, and 0.03, respectively. The use of the LSTM in combination with the DEM model yields satisfactory results in a less complex gravel pack DEM setup, suggesting that it could be a viable alternative to minimize the simulation time and provide a robust tool for gravel riverbed porosity prediction. The simulated results showed that the hybrid model of the LSTM combined with the DEM is reliable and accurate in porosity prediction in gravel-bed river test samples.

关键词： Numerical modeling Discrete element method LSTM Bed porosity Gravel-bed river

Building 3-D Human Data Based on Handed Measurement and CNN

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 2023年第2期74卷 2431-2441页

作者： Bich Nguyen Binh Nguyen Hai tran Vuong Pham Le Nhi Lam Thuy Pham The bao Faculty of Information Science Sai Gon UniversityHo Chi Minh70000Vietnam Faculty of Information Technology University of EducationHo Chi Minh70000Vietnam

3-dimension(3-D)printing technology is growing strongly with many applications,one of which is the garment *** application of human body models to the garment industry is necessary to respond to the increasing personalization demand and still guarantee *** paper proposes amethod to construct 3-D human models by applying deep *** calculate the location of the main slices of the human body,including the neck,chest,belly,buttocks,and the rings of the extremities,using pre-existing ***,on the positioning frame,we find the key points(fixed and unaltered)of these key slices and update these points tomatch the current *** add points to a star slice,we use a deep learning model tomimic the form of the human body at that slice *** use interpolation to produce sub-slices of different body sections based on the main slices to create complete body parts *** combine all slices to construct a full 3-D representation of the human body.

关键词： 3-D human model deep learning interpolation

Assessing geological uncertainty of a cement raw material deposit,southern Vietnam,based on hierarchical simulation

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 Mining Science and Technology 2020年第6期30卷 819-837页

作者： Trong Vu Carsten Drebenstedt tran bao TU Bergakademie Freiberg 09599 FreibergGermany Hanoi University of Mining and Geology Hanoi 10000Viet Nam

Resource modeling plays a crucial role in raw material quality management for cement *** has shown that geological uncertainty in resource modeling is inevitable and results in risk to future extraction planning and operations of the cement *** study aims to assess the geological uncertainty and associated risk in modeling a cement raw material deposit in southern *** this deposit,soil,clay,laterite,and limestone are the four primary rock types,controlling the occurrence and spatial distribution of chemical *** this study,hierarchical simulation method was used to evaluate the *** types were first simulated,and the chemical grades conditioning to the rock types were then *** results demonstrated the capability of the hierarchical simulation approach to incorporate the uncertainty of rock types in resource modeling and to allow evaluating the risks in providing the desired raw material for the cement plant in the form of grade-tonnage curves.

关键词： Cement raw material Geological uncertainty Rock types Grades Hierarchical simulation

维普期刊数据库

Intelligent acupuncture:data-driven revolution of traditional Chinese medicine

在线全文

学校读者我要写书评

暂无评论

Acupuncture and Herbal Medicine 2023年第4期3卷 271-284页

作者： Yunfan bao Haokang Ding Zhihan Zhang Kunhuan Yang Queena tran Qi Sun Tiancheng Xu Key Laboratory of Acupuncture and Medicine Research of Ministry of Education Nanjing University of Chinese MedicineNanjingChina Jiangsu Key Laboratory for Pharmacology and Safety Evaluation of Chinese Materia Medica Nanjing University of Chinese MedicineNanjingChina School of Life Science and Chemistry and Chemical Engineering Jiangsu Second Normal UniversityNanjingChina College of Letters&Science University of CaliforniaBerkeleyUSA School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjingChina Zhimei Kangmin(Zhuhai)Health Technology Co. LTDZhuhaiChina

Acupuncture,a form of traditional Chinese medicine with a history of 2,000 years in China,has gained wider acceptance worldwide as a complementary *** have examined its effectiveness in various health conditions and it is commonly used alongside conventional medical *** the development of artificial intelligence(AI)technology,new possibilities for improving the efficacy and precision of acupuncture have *** study explored the combination of traditional acupuncture and AI technology from three perspectives:acupuncture diagnosis,prescription,and treatment *** study aimed to provide cutting-edge direction and theoretical assistance for the development of an acupuncture robot.

关键词： Acupuncture Artificial intelligence Knowledge graph Graphical abstract:http://***/AHM/A68

Predicting soil erosion hazard in Lattakia Governorate(W Syria)

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 Sediment Research 2021年第2期36卷 207-220页

作者： Mohammed Safwan Khallouf Alaa Alshiehabi Omran bao Pham Quoc Thi Thuy Linh Nguyen Nam thai Van tran Anh Duong Harsányi Endre Institution of Land Utilization Technology and Regional Planning Faculty of Agricultural and Food Sciences and Environmental Management University of Debrecen Administration of Natural Resources Management General Commission for Scientific Agricultural Research (GCSAR) 3. Department of Soil Sciences and Land Reclamation Faculty of Agriculture Al-Baath University Department of Soil and Environment Swedish University of Agricultural Sciences (SLU) Institute of Research and Development Duy Tan University Faculty of Environmental and Chemical Engineering Duy Tan University Faculty of Water Resource Engineering Thuyloi University Ho Chi Minh City University of Technology (HUTECH) Sustainable Management of Natural Resources and Environment Research Group Faculty of Environment and Labour Safety Ton Duc Thang University

The main objective of this study is to predict soil erosion in the Lattakia Governorate(W Syria) using the Water Erosion Prediction Project model(WEPP) and to compare the result with that of the RUSLE. Field survey and data collection were carried out, and 44 soil samples were analyzed. In addition, all the necessary input files were prepared for use in the WEPP model and RUSLE. Results show that more than of 80% of the locations studied experience slight to moderate erosion(less than 5 t/ha/y), whereas the rest of the locations experience severe soil erosion hazard. Moreover, the volume of runoff estimated by the WEPP model is in the range of 51 e321 mm, and the R~2 between the simulated soil erosion and the predicted runoff reached 0.68. Interestingly, the R~2 between the WEPP model and RUSLE is 0.56, which indicates a good correlation between the two models.

关键词： Soil erosion Run-off WEPP RUSLE Syria

An improved CRNN for Vietnamese Identity Card Information Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第2期40卷 539-555页

作者： Trinh Tan Dat Le tran Anh Dang Nguyen Nhat Truong Pham Cung Le Thien Vu Vu Ngoc Thanh Sang Pham Thi Vuong Pham The bao Information Science Faculty Sai Gon UniversityHCM City700000Vietnam Faculty of Electrical&Electronics Engineering University of TechnologyHCM City700000Vietnam

This paper proposes an enhancement of an automatic text recognition system for extracting information from the front side of the Vietnamese citizen identity(CID)***,we apply Mask-RCNN to segment and align the CID card from the ***,we present two approaches to detect the CID card’s text lines using traditional image processing techniques compared to the EAST ***,we introduce a new end-to-end Convolutional Recurrent Neural Network(CRNN)model based on a combination of Connectionist Temporal Classification(CTC)and attention mechanism for Vietnamese text recognition by jointly train the CTC and attention objective functions *** length of the CTC’s output label sequence is applied to the attention-based decoder prediction to make the final label *** process helps to decrease irregular alignments and speed up the label sequence estimation during training and inference,instead of only relying on a data-driven attention-based encoder-decoder to estimate the label sequence in long *** may directly learn the proposed model from a sequence of words without detailed *** evaluate the proposed system using a real collected Vietnamese CID card dataset and find that our method provides a 4.28%in WER and outperforms the common techniques.

关键词： Vietnamese text recognition OCR CRNN BLSTM attention mechanism joint CTC-Attention

Application of the AERMOD Model to Evaluate the Health Benefits Due to Air Pollution from the Public transport Sector in Ha Noi, Viet Nam

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 Geoscience and Environment Protection 2022年第3期10卷 13-33页

作者： tran Do bao Trung Doan Quang Tri Department of Climate Change Ministry of Natural Resources and Environment Ha Noi Viet Nam Vietnam Journal of Hydrometeorology Viet Nam Meteorological and Hydrological Administration Ha Noi Viet Nam

Fine particulate matter (PM2.5) mainly originates from combustion emissions on-road transportation. Exposure to PM2.5 could be considered one of the primary causes of diseases such as heart attack, stroke, lung cancer, and chronic respiratory, which made it one of the most important co-benefits when evaluating the impact of GHG mitigation measures. This study quantifies the co-benefit of Ha Noi’s modal shift from private to public means of transport, which are reduced air pollution and extended life expectancy, combining AERMOD model and benefit transfer method. Analytical results show that shifting from motorbike to electric train could be the most beneficial option in term of health co-benefit, compared to the usage of standard buses and BRTs.

关键词： AERMOD Model Air Pollution Health Co-Benefit Ha Noi

Quantifying E2F1 protein dynamics in single cells

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Quantitative Biology 2020年第1期8卷 20-30页

作者： Bernard Mathey-Prevot bao-tran Parker Carolyn Im Cierra Hong Peng Dong Guang Yao Lingchong You Department of Pharmacology and Cancer Biology Duke University School of MedicineDurhamNC 27710USA Duke University School of Medicine DurhamNC 27710USA Molecular and Cellular Biology University of ArizonaTucsonAZ 85721USA Department of Biomedical Engineering Duke UniversityDurhamNC 27705USA Center for Genomic and Computational Biology Duke UniversityDurhamNC 27705USA Department of Molecular Genetics and Microbiology Duke University School of MedicineDurhamNC 27708USA Department of Pediatrics Duke University School of MedicineDurhamNC 27708USA University of North Carolina School of Medicine Chapel HillNC 27516USA Janelia Research Campus Howard Hughes Medical InstituteAshburnVA 20147USA

Background:E2F1 protein,a major effector of the Rb/E2F pathway plays a central role in regulating cell-fate decisions involved in proliferation,apoptosis,and *** expression is highly dynamic and tightly modulated through a combination of transcriptional,translational and posttranslational ***,the mechanisms by which its expression and activity can promote different cellular outcomes remain to be fully *** better document E2F1 expression in live cells,we have engineered a series of fluorescent E2F1 protein reporters that quantitatively capture E2F1 protein ***:Reporter constructs,under the control of the mouse or human E2F1 proximal promoter,were designed to express an E2F1-Venus fusion protein incapable of binding *** addition,constructs either included or excluded the y untranslated region(3fUTR)of the E2F1 *** constructs were introduced into fibroblasts and epithelial cells,and expression of the fusion reporter protein was validated and quantified in single cells using live ***:In all cases,expression of the reporter protein effectively recapitulated the behavior of E2F1 under various conditions,including cell cycle progression and genotoxic *** or little fluorescent signal of the reporter was detected in G〇,but as the cycle progressed,expression of the reporter protein steadily increased in the nucleus,peaking a few hours before cell division,but declining to baseline 2-3 h prior to the onset of *** absence of the E2F13 fUTR in the constructs led to considerably higher steady-state levels of the fusion protein,which although normally regulated,exhibited a slightly less complex dynamic profile during the cell cycle or genotoxic ***,the presence or absence of Rb failed to impact the overall detection and levels of the reporter ***:Our validated E2F1 protein reporters complement nicely other reporters of the Rb/E2F pathway and provide a unique tool to f

关键词： protein E2F1 reporter cell cycle

Research on Effects of Comorbidities Disease on Anticoagulation and Bleeding Disorders Risk in Patients with Overdosage of Vitamin K Antagonist Anticoagulant

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Open Journal of Emergency Medicine 2023年第3期11卷 68-79页

作者： Si Dung Chu Minh Thi tran Hai Phong-Vinh bao International General Hospital Haiphong Vietnam Department of Internal Medicine Vietnam University of Traditional Medicine and Pharmacy Hanoi Vietnam

Objectives: Research on effects of comorbidities disease on anticoagulation overdose in patients receiving anticoagulant therapy with vitamin K antagonists anticoagulant (VKAs) drugs at HaiPhong-Vinhbao International General Hospital. Methods: Description and Prospective study. Research on 79 patients receiving anticoagulant therapy with VKAs who have an INR testing index of more than anticoagulation dose with VKAs and check INR every 4 weeks. Results: The average research age is 65.65 ± 12.17 years [33: 85], most of the elderly group. The Male group is lower than the female group (p > 0.05). Patients with hemorrhage signs account for 22.8%. The INR testing index has an average value is 5.88 ± 3.0 [3.02 - 23.95];The group of INR > 5 level is a higher risk of bleeding than the group of INR ≤ 5 levels, there is statistical difference (p Conclusion: All most patients with anticoagulation overdose are in the elderly group. The group with INR > 5 levels has a higher risk of bleeding than the group with INR ≤ 5 levels, it’s the statistical significance (p 1 but p > 0.05);Patients used VKAs drugs on the background of kidney failure or arthritis pathology are the cause of the increased risk of bleeding, it’s statistical significance (p < 0.05).

关键词： Comorbidities Disease INR VKAs Bleeding Disorders