http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A robust approach in prediction of RCFST columns using machine learning algorithm
Van-Thanh Pham,Seung-Eock Kim 국제구조공학회 2023 Steel and Composite Structures, An International J Vol.46 No.2
Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.
Nano-porous Silicon Microcavity Sensors for Determination of Organic Fuel Mixtures
Van Hoi Pham,Huy Bui,Le Ha Hoang,Thuy Van Nguyen,The Anh Nguyen,Thanh Son Pham,Quang Minh Ngo 한국광학회 2013 Current Optics and Photonics Vol.17 No.5
We present the preparation and characteristics of liquid-phase sensors based on nano-porous silicon multilayer structures for determination of organic content in gasoline. The principle of the sensor is a determination of the cavity-resonant wavelength shift caused by refractive index change of the nano-porous silicon multilayer cavity due to the interaction with liquids. We use the transfer matrix method (TMM)for the design and prediction of characteristics of microcavity sensors based on nano-porous silicon multilayer structures. The preparation process of the nano-porous silicon microcavity is based on electrochemical etching of single-crystal silicon substrates, which can exactly control the porosity and thickness of the porous silicon layers. The basic characteristics of sensors obtained by experimental measurements of the different liquids with known refractive indices are in good agreement with simulation calculations. The reversibility of liquid-phase sensors is confirmed by fast complete evaporation of organic solvents using a low vacuum pump. The nano-porous silicon microcavity sensors can be used to determine different kinds of organic fuel mixtures such as bio-fuel (E5), A92 added ethanol and methanol of different concentrations up to 15%.
Thanh Van PHAM,Van Luan NGUYEN,Thi Lai NGUYEN,Thi Thu PHAN 한국유통과학회 2021 The Journal of Asian Finance, Economics and Busine Vol.8 No.9
This research was conducted to check the impact of factors related to the small and medium-sized enterprises (SME) on the economic growth in the Southeast region of Vietnam, over the years from 1996–2019. This paper applies a combination of FEM, DKSE, GMM, and RIDGE-FEM regression methods to estimate the influence of independent variables on the economic growth of the whole Southeast region with the panel data collected from GSO; and applying the OLS regression model for each province. The study finds that all variables have a statistically significant positive impact on the economic growth of the study area. Accordingly, the importance of the variables is in the following order: (1) the proportion of workers by professional and technical qualification (SMEH), (2) the number of vocational training schools (LnTSCH), and educational level of workers (LnSchool), (3) the number of SME enterprises (LnSME); (4) The average number of years in the schooling of employees in the enterprise (LnSchool); (5) Enterprise capital (LnCAP); and (6) the average number of employees of SME (LnSMER). The research results also show that factors related to the quality of labor resources have a more positive influence on growth than both the labor size and financial capital of SMEs.
A novel method for vehicle load detection in cable-stayed bridge using graph neural network
Van-Thanh Pham,Hyesook Son,Cheol-Ho Kim,Yun Jang,Seung-Eock Kim 국제구조공학회 2023 Steel and Composite Structures, An International J Vol.46 No.6
Vehicle load information is an important role in operating and ensuring the structural health of cable-stayed bridges. In this regard, an efficient and economic method is proposed for vehicle load detection based on the observed cable tension and vehicle position using a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), a robust program for modeling and considering both geometric and material nonlinearities of bridge structures subjected to vehicle load with low computational costs. With the superiority of GNN, the proposed model is demonstrated to precisely capture complex nonlinear correlations between the input features and vehicle load in the output. Four popular machine learning methods including artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machines (SVM) are refereed in a comparison. A case study of a cable-stayed bridge with the typical truck is considered to evaluate the model's performance. The results demonstrate that the GNN-based model provides high accuracy and efficiency in prediction with satisfactory correlation coefficients, efficient determination values, and very small errors; and is a novel approach for vehicle load detection with the input data of the existing monitoring system.
Pham, Thanh-Dong,Lee, Byeong-Kyu,Nguyen, Van Noi,Dao, Van-Duong Elsevier 2017 Journal of catalysis Vol.352 No.-
<P>This article has been retracted: please see Elsevier Policy on Article Withdrawal (<U>https://www.elsevier.com/about/our-business/policies/article-withdrawal</U>).</P><P>This article has been retracted at the request of the Editor, after consultation with the corresponding author Professor Byeong-Kyu Lee due to the methods described in the paper for the preparation of the catalysts being incomplete and the results not being reproduced. This was brought to the editors’ attention via a letter to the editor. Professor Lee agreed that the methods description was not complete and agreed with this course of action. <Journal of catalysis, 352 (2017) 13 – 21>, http://dx.doi.org/10.1016/j.jcat.2017.04.024.</P>
Van-Thanh Pham,Yun Jang,Jong-Woong Park,Dong Joo Kim,Seung-Eock Kim 국제구조공학회 2022 Steel and Composite Structures, An International J Vol.44 No.2
The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.
Thanh Khiem Nguyen,Ham Hoi Nguyen,Tuan Hiep Luong,Kim Khue Dang,Van Duy Le,Duc Dung Tran,Van Minh Do,Hong Quang Pham,Hoan My Pham,Thi Lan Tran,Cuong Thinh Nguyen,Hong Son Trinh,Yosuke Inoue 한국간담췌외과학회 2024 Annals of hepato-biliary-pancreatic surgery Vol.28 No.1
Backgrounds/Aims: Pancreaticoduodenectomy (PD) is the only radical treatment for periampullary malignancies. Superior mesenteric artery (SMA) first approach combined with total meso-pancreas (MP) excision was conducted to improve the oncological results. There has not been any previous research of a technique that combines the SMA first approach and total MP excision with a detailed description of the MP macroscopical shape. Methods: We prospectively assessed 77 patients with periampullary malignancies between October 2020 and March 2022 (18 months). All patients had undergone PD with SMA first approach combined total MP excision. The perioperative indications, clinical data, intra-operative index, R0 resection rate of postoperative pathological specimens (especially mesopancreatic margin), postoperative complications, and follow-up results were evaluated. Results: The median operative time was 289.6 min (178−540 min), the median intraoperative blood loss was 209 mL (30−1,600 mL). Microscopically, there were 19 (24.7%) cases with metastatic MP, and five cases (6.5%) with R1-resection of the MP. The number of lymph nodes (LNs) harvested and metastatic LNs were 27.2 (maximum was 74) and 1.8 (maximum was 16), respectively. Some (46.8%) patients had pancreatic fistula, but mostly in grade A, with 7 patients (9.1%) who required re-operations. Some 18.2% of cases developed postoperative refractory diarrhea. The rate of in-hospital mortality was 1.3%. Conclusions: The PD with SMA first approach combined TMpE for periampullary malignancies was effective in achieving superior oncological statistics (rate of MP R0-resection and number of total resected LNs) with non-inferior short-term outcomes. It is necessary to evaluate survival outcomes with long-term follow-up.
Dao, Van-Duong,Larina, Liudmila L.,Tran, Quoc Chinh,Bui, Van-Tien,Nguyen, Van-Toan,Pham, Thanh-Dong,Mohamed, Ibrahim M.A.,Barakat, Nasser A.M.,Huy, Bui The,Choi, Ho-Suk Elsevier 2017 Carbon Vol.116 No.-
<P>This work focuses on systematic studies of dissolution engineering for Pt0.9M0.1/graphene(M = Au, Co, Cu, Fe, Mo, Ni, Pd, Ru, and Sn) counter electrodes (CEs). The developed nanohybrid materials exhibit higher catalytic activity and electrical conductivity compared with those of Pt/graphene CEs. The results also indicate the improved stability of the developed CEs in iodide electrolyte. Furthermore, the trend in the variation of the reactivity of the PtM alloys agrees well with the concept of density functional theory (one-electron description). An enhancement in the catalytic activity of the developed nanohybrids results from the electronic effect that originates from an upward shift of the platinum d-band to the Fermi energy level upon alloying. Thus, the Pt(0.9)M(0.1)graphene nanohybrids are cost-effective alternative CE materials to the expensive Pt. The obtained results provide a foundation for enhancing the catalytic activities of CEs for dye-sensitized solar cells (DSCs). The implementation of the Pt0.9M0.1/graphene nanohybrids offers significant potential for increasing the efficiency of DSCs. (C) 2017 Elsevier Ltd. All rights reserved.</P>