Journal Articles - Engineering - 2023
Permanent URI for this collection
Browse
Browsing Journal Articles - Engineering - 2023 by Issue Date
Results Per Page
Sort Options
-
PublicationEffect of Gradient Descent Optimizers and Dropout Technique on Deep Learning LSTM Performance in Rainfall‑runoff Modeling( 2023)"Duong Tran Anh, Dat Vi Thanh, Hoang Minh Le, Bang Tran Sy, Ahad Hasan Tanim, Quoc Bao Pham, Thanh Duc Dang, Son T. Mai, Nguyen Mai Dang."Machine learning and deep learning (ML-DL) based models are widely used for rainfall runof prediction and they have potential to substitute process-oriented physics based numerical models. However, developing an ML model has also performance uncertainty because of inaccurate choices of hyperparameters and neural networks architectures. Thus, this study aims to search for best optimization algorithms to be used in ML-DL models namely, RMSprop, Adagrad, Adadelta, and Adam optimizers, as well as dropout tech niques to be integrated into the Long Short Term Memory (LSTM) model to improve forecasting accuracy of rainfall-runof modeling. A deep learning LSTMs were developed using 480 model architectures at two hydro-meteorological stations of the Mekong Delta, Vietnam, namely Chau Doc and Can Tho. The model performance is tested with the most ideally suited LSTM optimizers utilizing combinations of four dropout percentages respec tively, 0%, 10%, 20%, and 30%. The Adagrad optimizer shows the best model performance in the model testing. Deep learning LSTM models with 10% dropout made the best predic tion results while signifcantly reducing overftting tendency of the forecasted time series. The fndings of this study are valuable for ML-based hydrological models set up by identi fying a suitable gradient descent (GD) optimizer and optimal dropout ratio to enhance the performance and forecasting accuracy of the ML model.
-
Publication"Data‑driven prediction of the shear capacity of ETS‑FRP‑strengthened beams in the hybrid 2PKT–ML approach"( 2023)Thai SonTran, Boonchai Stitmannaithum, LinhVan Hong Bui, Thanh‑Truong Nguyen.A new approach that combines analytical two-parameter kinematic theory (2PKT) with machine learning (ML) models for estimating the shear capacity of embedded through-section (ETS)-strengthened reinforced concrete (RC) beams is proposed. The 2PKT was first developed to validate its representativeness and confidence against the available experimental data of ETS-retrofitted RC beams. Given the deficiency of the test data, the developed 2PKT was utilized to generate a large data pool with 2643 samples. The aim was to optimize the ML algorithms, namely, the random forest, extreme gradient boosting (XGBoost), light gradient boosting machine, and artificial neural network (ANN) algorithm. The optimized ANN model exhibited the highest accuracy in predicting the total shear strength of ETS-strengthened beams and ETS shear contribution. In terms of predicting the total shear strength of ETS-strengthened beams, the ANN model achieved R2 values of 0.99, 0.98, and 0.96 for the training, validation, and testing data, respectively. By contrast, the ANN model could predict ETS shear contribution with high accuracy, with R2 values of 0.99, 0.99, and 0.97 for the training, validation, and testing data, respectively. Then, the effects of all design variables on the shear capacity of the ETS-strengthened beams were investigated using the hybrid 2PKT–ML. The obtained trends could well appraise the reasonability of the proposed approach.
-
PublicationA NURBS-based IGA using zig-zag plate theory for nonlinear passive/semi-active damping analysis of laminated FG-CNTRC plates( 2023)T. Nguyen-Thoi, Duy-Khuong Ly, Sy-Ngoc Nguyen, Vinyas Mahesh, Chanachai Thongchom"In this article, a novel numerical approach based on electromechanical coupling isogeometric analysis employing a piecewise linear zig-zag function is proposed for modeling and analysis of smart constrained layer damping (SCLD) treatment in multilayer porous functionally graded graphene platelets-reinforced composite (PFG-GPRC) plates. The approach efficiently approximates the geometric, mechanical, and electric displacement fields by utilizing non-uniform rational B-splines (NURBS) basis functions. These basis functions are subsequently integrated with the zig-zag formulation to characterize the system dynamic and help handle both continuous/discontinuous material properties at all interfaces, as well as improve the effectiveness of global–local numerical solutions for the analysis of current structures. The multilayer PFG-GPRC plate model is designed to incorporate porous, uniformly, or non-uniformly distributed layers based on three different graphene platelet patterns. The analysis of the SCLD treatment encompasses an examination of the frequency response function of the damped structure under passive/hybrid mechanisms, taking into account"
-
PublicationResearch, Direct Construction form Optical Characteristics – OCR using Department Technology( 2023)Ly Hai Son, Nguyen Thu Nguyet Minh, Tra Van DongOptical character recognition – using a deep learning technique that describes an overview of optical character recognition, the basic steps in the optical character recognition problem. At the same time, the thesis introduces in detail the Long short term memory (LSTM) deep learning method and its application in optical character recognition. Through testing on a dataset of 10,000 license plate photos, the thesis showed that the application of the LSTM method is quite effective in optical character recognition.
-
PublicationTermite life cycle optimizer( 2023)Hoang-Le Minh, Thanh Sang-To, Guy Theraulaz, Magd Abdel Wahab, Thanh Cuong-Le"This paper introduces a novel bio-inspired meta-heuristic optimization algorithm, named termite life cycle optimizer (TLCO), which is based on both the life cycle of a termite colony and the modulation of movement strategies used by many animal species in nature. Termite colonies are comprised of three distinct castes: the workers, the soldiers and the reproductive termites. Each caste undertakes a set of specific tasks that ensure the growth and survival of the colony. TLCO mimics the activities of these three castes that are implemented in a mathematical model. The model is then used to find the global optimum in classic optimization problems. First, the behaviors of the workers, soldiers and reproductive termites are used to simulate a balance between the tasks of exploration and exploitation. Second, the initial population securely records the information obtained at each iteration and transmits it to workers and soldiers at the next iteration. This process is repeated until the global optimum is found with the smallest error. Besides, a new proposed function combined with L´evy flight is used to modulate the movement of termites that increases its flexibility. Thus, TLCO can cover both long distances during the first iterations to improve the convergence rate and shorter distances during the last iterations to enhance the level of accuracy. We then compare the performances of TLCO with other well-known nature-inspired algorithms using 23 classical benchmark functions, CEC2005 benchmark functions, and five real engineering design problems. The results demonstrate the effectiveness and reliability of TLCO in solving these optimization problems. Source codes of TLCO is publicly available at http://goldensolutionrs.com/termite-life-cycle-optimizer.html"
-
PublicationImpact of Ownership Structure and Business Diversifications on the Risk-Taking Behaviors of Insurance Companies in Vietnam( 2023)"Khoa Dang Duong, AiNhan Ngoc Le, Diep Van Nguyen, and Hoa Thanh Phan Le""This study analyzes the impacts of ownership structure and business diversifications on the risk-taking behaviors of insurance companies in Vietnam. Foreign ownership and institutional ownership in the insurance sector are increasing significantly due to the privatization trend in Vietnam. Besides, business diversification allows insurance firms to maximize profits and reduce insolvency. Therefore, this study enriches the current literature because it is the first to examine how ownership and diversifications affect the risk-taking behaviors of insurance companies in Vietnam. We employ the Ordinary Least Squares, Fixed Effect Models, Random Effect Models, Generalized Least Squares, and dynamic system Generalized Methods of Moments to analyze 42 insurance companies from 2005 to 2020. Our findings indicate that business diversification increases the risktaking behaviors of insurance firms. We also figure out a U-shaped relationship between institutional ownership and risktaking behavior, with a turning point of 9.8%. This study also indicates an inverse U-shaped relationship between foreign ownership and insurers’ risk-taking behaviors, with a turning point of 20%. Thirdly, the interaction terms between ownership and diversification suggest the moderate role of business diversification in increasing the risk of insurance firms. Our findings align with agency theory, stakeholder theory, monitoring hypothesis, expropriation hypothesis, and prior literature. This study contributes practical implications for managers and policymakers to develop the insurance sector sustainably"
-
PublicationLand cover and crop types mapping using different spatial resolution imagery in a Mediterranean irrigated area( 2023)"Siham Acharki, Pierre‑Louis Frison, Bijeesh Kozhikkodan Veettil, Quoc Bao Pham, Sudhir Kumar Singh, Mina Amharref, Abdes Samed Bernoussi""Crop type identification is critical for agricultural sustainability policy development and environmental assessments. Therefore, it is important to obtain their spatial distribution via different approaches. Medium-, high- and very high-resolution optical satellite sensors are efficient tools for acquiring this information, particularly for challenging studies such as those conducted in heterogeneous agricultural fields. This research examined the ability of four multitemporal datasets (Sentinel-1-SAR (S1), Sentinel- 2-MSI (S2), RapidEye (RE), and PlanetScope (PS)) to identify land cover and crop types (LCCT) in a Mediterranean irrigated area. To map LCCT distribution, a supervised pixel-based classification is adopted using Support Vector Machine with a radial basis function kernel (SVMRB) and Random Forest (RF). Thus, LCCT maps were generated into three levels, including six (Level I), ten (Level II), and fourteen (Level III) classes. Overall, the findings revealed high overall accuracies of >92%, >83%, and > 81% for Level I, Level II, and Level III, respectively, except for Sentinel- 1. It was found that accuracy improves considerably when the number of classes decreases, especially when cropland or non-cropland classes are grouped into one. Furthermore, there was a similarity in performance between S2 alone and S1S2. PlanetScope LCCT classifications outperform other sensors. In addition, the present study demonstrated that SVM achieved better performances against RF and can thereby effectively extract LCCT information from high-resolution imagery as PlanetScope."
-
PublicationBuilding the classification model based on the genetic algorithm and the improved Bayesianmethod( 2023)Dinh Pham-Toan, Tai Vo-Van"This study presents a classification model that incorporates significant enhancements based on the Bayesian method and genetic algorithm (BGA). Firstly, the prior probabilities in each iteration are determined using the ratio of the number of elements in each group, obtained through clustering techniques, to the total number of elements in the training set. Secondly, an automatic selection process optimizes the training set to minimize classification errors. Finally, the traditional genetic algorithm operators are improved by utilizing the Bayes error as the objective function. These improvements combine to create an effective classification model. Additionally, the BGA demonstrates effective performance on real data using the established MATLAB procedure. A numerical example illustrates the superiority of the proposed algorithm compared to existing methods. The study also applies the BGA for image classification using the Gabor filter, which extracts essential image features. The proposed model outperforms popular methods in classifying various numerical and image datasets. These applications highlight the potential of this study in real-world scenarios."
-
PublicationImproving the genetic algorithm in fuzzy cluster analysis for numerical data and its applications( 2023)Dinh Pham-Toan, Tai Vo-Van"This study proposes an automatic genetic algorithm in fuzzy cluster analysis for numerical data. In this algorithm, a new measure called the FB index is used as the objective function of the genetic algorithm. In addition, the algorithm not only determines the appropriate number of groups but also improves the steps of traditional genetic algorithm as crossover, mutation and selection operators. The proposed algorithm is shown the step by step throughout the numerical example, and can perform fast by the established Matlab procedure. The result from experiments show the superiority of the proposed algorithm when it overcomes the existing algorithms. Moreover, it has been applied in recognizing the image data, and building the fuzzy time series model. These show the potential of this study for many real applications of the di erent elds."
-
PublicationOne-loop contributions to decays eb→eaγand (g−2)eaanomalies, and Ward identity( 2023)L.T.Hue, H.N.Long, V.H.Binh, H.L.T.Mai, T.PhongNguyenIn this paper, we will present analytic formulas to express one-loop contributions to lepton flavor violating decays eb→eaγ, which are also relevant to the anomalous dipole magnetic moments of charged leptons ea. These formulas were computed in the unitary gauge, using the well-known Passarino-Veltman notations. We also show that our results are consistent with those calculated previously in the ’t Hooft-Veltman gauge, or in the limit of zero lepton masses. At the one-loop level, we show that the appearance of fermion-scalar-vector type diagrams in the unitary gauge will violate the Ward Identity relating to an external photon. As a result, the validation of the Ward Identity guarantees that the photon always couples with two identical particles in an arbitrary triple coupling vertex containing a photon
-
PublicationTowards Sustainable Composting of Source-Separated Biodegradable Municipal Solid Waste—Insights from Long An Province, Vietnam( 2023)Tan Loi Huynh, Thi Kim Oanh Le, Yong JieWong, Chi Tuong Phan and Thi Long Trinh"Inadequate municipal solid waste (MSW) management has become a pressing concern, resulting in significant environmental contamination, particularly in developing countries. Composting has demonstrated its practicality and feasibility for addressing this issue; however, the lack of at-source solid waste separation remains a major challenge. As a result, in this study, the first sustainable MSW separation at source was conducted in Tan An City, Long An Province. The objective of this study was to evaluate the compost process and quality using Tan An City’s separated biodegradable organic solid waste as the raw material, through a windrow composting process with active aeration. Biodegradable organic waste, slow-biodegradable organic waste and plastic waste accounted for 84.5%, 15.1% and 0.4%, respectively, of the total waste. The pH, moisture, volatile solid percentage, total nitrogen, total organic carbon and carbon-to-nitrogen ratio of the separated solid waste were 8.7 0.4, 76.8 1.9%, 68.3 1.3%, 2.1 0.1%, 35.7 2.2% and 17 0.8, respectively. Rice straw was mixed with solid waste as a bulking material in a 31%:69% ratio to achieve a moisture content of 55% in the mixture. After 10 weeks, an evaluation of the compost’s quality revealed its potential suitability for agricultural applications. Notably, Salmonella was not detected in the compost, and the heavy metal levels were below standard limits, indicating the safety of the compost. To ensure optimal nutrient levels for effective plant growth, a slight nitrogen and phosphorus supplement was recommended. Aligned with the C/N ratio of 12.1 and a consistent temperature of approximately 29 C, this indicates a high degree of maturity and stability in the composting process. The framework of this study demonstrates the effectiveness of at-source MSW separation in paving a sustainable path for MSW management."
-
PublicationAir emission inventory and air quality modelling for developing countries: A case of Vinh Phuc province, Vietnam( 2023)
-
PublicationOn Cauchy problem for pseudo-parabolic equation with Caputo-Fabrizio operator( 2023)Bui Dai Nghia, Van Tien Nguyen, and Le Dinh Long"In this article, we considered the pseudo-parabolic equation with Caputo-Fabrizio fractional derivative. This equation has many applications in different fields, such as science, technology, and so on. In this article, we gave the formula of mild solution, which is represented in the form of Fourier series by some operators . In the linear case, we investigated the continuity of the mild solution with respect to the fractional order. For the nonlinear case, we investigated the existence and uniqueness of a global solution. The main proof technique is based on the Banach fixed point theorem combined with some Sobolev embeddings. For more detailed, we obtained two other interesting results: the continuity of mild solution with respect to the derivative order and the convergence of solution as the coefficient k approaches to zero."
-
PublicationInvestigation of the Product of Random Matrices and Related Evolution Models( 2023)Hirobumi Mineo, Vladimir Suvorov and David B. Saakian"In this paper, we study the phase structure of the product of D * D order matrices. In each round, we randomly choose a matrix from a finite set of d matrices and multiply it with the product from the previous round. Initially, we derived a functional equation for the case of matrices with real eigenvalues and correlated choice of matrices, which led to the identification of several phases. Subsequently, we explored the case of uncorrelated choice of matrices and derived a simpler functional equation, again identifying multiple phases. In our investigation, we observed a phase with a smooth distribution in steady-state and phases with singularities. For the general case of D-dimensional matrices, we derived a formula for the phase transition point. Additionally, we solved a related evolution model. Moreover, we examined the relaxation dynamics of the considered models. In both the smooth phase and the phase with singularities, the relaxation is exponential. The superiority of relaxation in the smooth phase depends on the specific case"
-
PublicationIdentifying of Unknown Source Term for the Rayleigh-Stokes Problem( 2023)Tran Thanh PHONG, Devendra KUMAR, and Le Dinh LONGIn this paper, we would like to briefly introduce some applications of fractional derivatives in the fields of heat and fluid-flows. However, our main focus is on study an inverse source problem for the Rayleigh-Stokes problem. The problem is severely ill-posed. We verify the ill-posedness of Problem 1, applying the modified Lavrentiev to construct a regularization from the exact data. After that, we established the convergent rate between the exact solution and its approximation. Furthermore, we have the estimate in Lq space
-
PublicationOn the Fractional Diffusion Equation Associated With Exponential Source and Operator With Exponential Kernel( 2023)
-
PublicationEvaluation of structural, optical, and magnetic properties of Gd doped MnFe2O4 nanoparticles( 2023)
-
PublicationAngle dependence of the electrical conductivity in high Tc superconductor( 2023)"Luu Huu Nguyen, Tran Cong Minh , Nguyen Chinh Cuong, Bui Duc Tinh""We use the time-dependent Ginzburg{Landau Lawrence{Doniach model with thermal noise to study angle dependence of electrical conductivity in high Tc superconductor. The electrical conductivity is calculated as temper- ature and magnetic eld in the homogeneous phase. When the magnetic eld is rotated in the plane indicated by the c axis and the direction of the electric current, the theoretical caculation based on the self-consistent Gaussian ap- proximation is used to compare with the experimental data of HgBa2CaCu2O6. Our caculations are in good agreement with the experimental data for temper- atures below Tc and above Tc. In terms of quality, the increase in resistivity brought on by a developing magnetic eld at constant strength is comparable to that brought on by a growing magnetic eld applied orthogonally to the layers. However, as the magnetic eld approaches an orientation parallel to the layers, the e ects of a perpendicular eld obviously di er from those of a tilted eld with the same normal component."
-
PublicationOne-loop expressions for h → l l̅γ in Higgs extensions of the Standard Model( 2023)
-
PublicationDependence of hole’s effective mass on the spin polarization and temperature in quantum well( 2023)Le Van Tan"The effective mass of holes (𝑚∗) in GaAs quantum wells is investigated as a function of spin polarization, temperature, and carrier density using the Hartree–Fock approximation. The results reveal 𝑚∗ initially decreases at low carrier densities before increasing with density. Additionally, as the interaction parameter increases, 𝑚∗ decreases rapidly. Especially, as the temperature rises to 200 K, 𝑚∗ asymptotically approaches a value of 0.45𝑚0, where 𝑚0 is the electron mass. These findings provide insights into the influence of Coulomb interaction and exchange energy on the effective mass of semiconductors across a wide range of temperatures, spin polarizations, and densities"