Vietnam Academy of Science and Technology: Journals Online
Vietnam Academy of Science and Technology: Journals OnlineNot a member yet
7064 research outputs found
Sort by
Prediction of soil unconfined compressive strength using Artificial Neural Network Model
No full textThe main objective of the present study is to apply Artificial Neural Network (ANN), which is one of the most popular machine learning models, to accurately predict the soil unconfined compressive strength (qu) for the use in designing of foundations of civil engineering structures. For the development of model, data of 118 soil samples were collected from Long Phu 1 power plant project, Soc Trang Province, Vietnam. The database of physicomechanical properties of soils was prepared for the model study, where 70% data was used for the training and 30% for the testing of the model. Standard statistical indices, namely Root Mean Squared Error (RMSE) and Pearson Correlation Coefficient (R) were used in the validation of the model’s performance. In addition, Partial Dependence Plots (PDP) was used to evaluate the importance of the input variables used for modeling. Results showed that the ANN model performed well for the prediction of the qu (RMSE = 0.442 and R = 0.861). The PDP analysis showed that the liquid limit is the most important input factor for modeling of the qu. The present study demonstrated that the ANN is a promising tool that can be used for quick and accurate prediction of the qu, which can be used in designing the civil engineering structures like bridges, buildings, and powerhouses
DESIGNING HEDGE ALGEBRAIC CONTROLLER AND OPTIMIZING BY GENETIC ALGORITHM FOR SERIAL ROBOTS ADHERING TRAJECTORIES
Get PDFIn recent years, the application of hedge algebras in the field of control has been studied. The results show that this approach has many advantages. In additions, industrial robots are being well-developed and extensively used, especially in the industrial revolution 4.0. Accurate control of industrial robots is a class of problems that many scientists are interested in. In this paper, we design a controller based on hedge algebra for serial robots. The control rule is given by linguistic rule base system. The goal is to accurately control the moving robot arm which adheres given trajectories. Optimization of fuzzy parameters for the controller is done by genetic algorithms. The system has been simulated on the Matlab-Simulink software. The simulation results show that the orbital deviation is very small. Moreover, the controller worked well with correct control quality. This result once presents the simplicity and efficiency of the hedge algebras approach to control
SOME TECHNIQUES IN MICROPROPAGATION AND BREEDING OF Paphiopedilum spp.
No full textPaphiopedilum orchids are one of the most popular and rare orchid genera sold and exhibited as pot plants and cut flowers. Their wild populations are under the threat of extinction as a result of over-collection and loss of suitable habitats. Reduction in their commercial value through large-scale propagation in vitro is a preferable option to reduce pressure from illegal collection, to attempt at meeting commercial needs and to re-establish these threatened orchid species back into the wild. Although they are commercially propagated via seed germination in vitro, Paphiopedilum are considered to be difficult to propagate in vitro, especially by plant regeneration from tissue culture. This paper aims to provide the most important techniques on Paphiopedilum propagation mainly including plant, cell, tissue and organ culture techniques applied to in vitro propagation of Paphiopedilum and to emphasize the importance of further improving tissue culture protocols from ex vitro-derived explants of mature plants
Study on structure of the Earth’s crust in Thua Thien-Hue province and adjacent areas by using gravity and magnetic data in combination
Get PDFThis paper presents the structural characteristics of the Earth’s crust in Thua Thien-Hue province and adjacent area based on interpretation of gravity and magnetic data in combination. Research results have shown that: The depth of crystalline basement varies complicatedly, in the range of 0–11 km. The depth of Conrad surface increases from Northeast (12 km) to Southwest (18 km) and the depth of Moho surface is 23–34 km; The density of sedimentary layer changes from 2.61 g/cm3 to 2.65 g/cm3. Meanwhile, the density of granitic layer is in the range of 2.68–2.73 g/cm3. The basaltic layer has the density value of 2.88–2.93 g/cm3 and the average density of lower layer of the Earth’s crust is about 3.30 g/cm3; The depth of second-order faults, Red River and A Luoi - Rao Quan, is through the Earth’s crust. Meanwhile, the depth of influence of third-order faults, Chay river, Dong Ha - Phu Vang, Vinh Linh, Hue - Son Tra and Tam Ky - Phuoc Son, is within the thickness of the Earth’s crust
Quy trình gia công và phân tích hóa thạch Tảo vôi, áp dụng cho các trầm tích ven biển tỉnh Sóc Trăng
Get PDFCalcareous nannofossils are very small microfossils composed of calcium carbonate. They are very good biostratigraphic markers within marine sediments by covering the Jurassic to present. The standard preparation of a sample for nannofossil analysis requires the collection of the largest quantity and the best fossils. Sample preparation accords to the following steps: i. Pounding sample; ii. Eliminating organic matter; iii. Washing sample; iv. Filter sample through the sieve; v. Eliminating clay; vi. Drying sample in an incubator; vii. Packing sample. Sample analysis accords to the following steps: i. Preparation of smear - slide; ii. Observation of morphology; iii. Determination; iv. Taking photo; v. Evaluating overall preservation and abundance of fossils; vi. Making analysis result sheet. This process is applied to study calcareous nannofossils within marine sediments in Soc Trang province. It makes much clear to understand middle Pleistocene-early Holocene ecosystem of calcareous nannofossil. In conclusion, this assemblage belongs to NN21 zone by the present of Emiliania huxleyi and Gephyrocapsa oceanica.Hóa thạch Tảo vôi có kích thước rất nhỏ, thành phần chính là canxi carbonat. Chúng là hóa thạch định tầng rất tốt cho các trầm tích biển có tuổi từ Jura đến nay. Để nghiên cứu hóa thạch Tảo vôi, cần tiến hành gia công và phân tích mẫu theo đúng quy trình để thu được lượng hóa thạch nhiều nhất và bảo tồn tốt nhất. Quy trình gia công gồm các bước sau: i. giã mẫu; ii. tẩy keo hữu cơ; iii. rửa mẫu; iv. lọc mẫu; v. tẩy sét; vi. sấy mẫu; vii. đóng gói. Quy trình phân tích tiến hành theo những bước sau: i. chuẩn bị tiêu bản; ii. nghiên cứu đặc điểm hình thái của hóa thạch; iii. xác định hóa thạch; iv. chụp ảnh hóa thạch; v. đánh giá mức độ bảo tồn và phong phú của hóa thạch; vi. lập phiếu kết quả phân tích. Kết quả áp dụng quy trình cho các trầm tích ven biển tỉnh Sóc Trăng đã góp phần làm sáng tỏ hệ sinh thái Tảo vôi ở khu vực nghiên cứu trong Pleistocen giữa - Holocen sớm. Tập hợp hóa thạch ở khu vực ven biển Sóc Trăng thuộc sinh đới NN21 với bằng chứng là sự xuất hiện của Emiliania huxleyi và Gephyrocapsa oceanica
A DOUBLE-SHRINK AUTOENCODER FOR NETWORK ANOMALY DETECTION
Get PDFThe rapid development of the Internet and the wide spread of its applications has affected many aspects of our life. However, this development also makes the cyberspace more vulnerable to various attacks. Thus, detecting and preventing these attacks are crucial for the next development of the Internet and its services. Recently, machine learning methods have been widely adopted in detecting network attacks. Among many machine learning methods, AutoEncoders (AEs) are known as the state-of-the-art techniques for network anomaly detection. Although, AEs have been successfully applied to detect many types of attacks, it is often unable to detect some difficult attacks that attempt to mimic the normal network traffic. In order to handle this issue, we propose a new model based on AutoEncoder called Double-Shrink AutoEncoder (DSAE). DSAE put more shrinkage on the normal data in the middle hidden layer. This helps to pull out some anomalies that are very similar to normal data. DSAE are evaluated on six well-known network attacks datasets. The experimental results show that our model performs competitively to the state-of-the-art model, and often out-performs this model on the attacks group that is difficult for the previous methods
Prediction of soil loss due to erosion using support vector machine model
No full textSoil erosion refers to the detachment and removal of soil particles from land (topsoil), by the natural physical forces (water, glacier and wind). Soil erosion causes soil loss in the catchment or any land areas severely impacting agriculture activity, sedimentation in the dam reservoirs, and hampering developmental activities. Therefore, it is desirable to accurately measure soil loss due to erosion for the development and management of an area. With this objective, a well-known machine learning algorithm Support Vector Machine (SVM) has been used in the development of the soil loss prediction model. Eight erosion affecting variable inputs: ambient temperature Tair, rainfall, Antecedent Moisture Conditions (AMC), rainfall intensity, slope, vegetation cover, soil temperature Tsoil and moisture of the soil. Data on published literature was used in the model study. The accuracy of the proposed SVM was assessed by using three statistical performance evaluation indicators namely Person correlation coefficient (R), Root Mean Squared Error (RMSE), Mean Squared Error (MAE). Partial Dependence Plots (PDP) was used to investigate the dependence of prediction results of eight input variables used in the model study. Model validation results showed that SVM model performed well for the prediction of soil loss for testing (R = 0.8993) and also for training (R=0.9123). Rainfall intensity and vegetation cover were found to be the two most important affecting input parameters for the soil loss prediction
The controlling of paleo-riverbed migration on Arsenic mobilization in groundwater in the Red River Delta, Vietnam
No full textIn the Red River Delta, the concentrations of Arsenic in groundwater of alluvial dominated systems are very high, exceeding the WHO’s permissible. The correlation between the Arsenic concentrations in groundwater and the age of Holocene sediment as a key controlling groundwater Arsenic concentration in the Red River delta has been investigated. The evolution of sediments in the Holocene is closely related to paleo-riverbed migration in the past. A combination of methods is implemented including remote sensing, multi-electrode profiling (MEP), gamma-logging, drilling, soil sample and groundwater modeling. The resul has identified the shape, sediment compositions and location of the six paleo-riverbed periods. The age of the paleo-riverbed is determined by drilling, soil sampling and optically stimulated luminescence (OSL) in the laboratory. The oldest sediments is 5.9±0.4 ka BP in Phung Thuong near the mountain, the youngest one is from 0.4÷0.6 ka BP in H-transect near the Red River and the rest of the other is around 3.5 ka BP. The modeling results by using MODFLOW and MT3D show that the dynamics of paleo-riverbeds controlling Arsenic mobilization in groundwater in the Red River Delta. When the river moved to another position, the current river position at that time was filled with younger sediments and became paleo-riverbed formation with reducing conditions, Arsenic content which was adsorbed in the previous stage then released into groundwater. Therefore, Arsenic concentration in groundwater of young Holocene sediments is higher than in older ones which elucidates that paleo-riverbed migration controls on Arsenic mobilization in groundwater in the study area
Experiments and optimization for the WEDM process: A trade-off analysis between surface quality and production rate
Get PDFThis work addressed a parameter optimization to simultaneously decrease the root mean square roughness (Rq) as well as the thickness of the white layer (TW) and improve the material removal rate (MRR) for the wire electro-discharge machining (WEDM) of a stainless steel 304 (SS304). The factors considered are the discharge current (C), the gap voltage (VO), the pulse on time (POT), and the wire drum speed (SP). The interpolative radius basic function (RBF) is applied to show the correlation between the varied factors and WEDM performances measured. The optimal selection is chosen using the multi-objective particle swarm optimization (MOPSO). Moreover, a traditional one using the response surface method (RSM) and desirability approach (DA) is adopted to compare the working efficiency of two optimization techniques. The results showed that the optimal findings of the C, POT, VO, and SP are 5.0 A, 1.0 µs, 61.0 V, and 8.0 m/min, respectively. The values of the Rq and TW are decreased by approximately 33.33% and 23.53%, respectively, while the MRR enhances 47.42% at the optimal selection, as compared to the common values used. The BRF-MOPSO can provide better performance than the RSM-DA
Identification of p.His119Leu mutation in the G6PC gene of a Vietnamese patient with glycogen storage disease type Ia
Get PDFGlycogen storage disease type Ia (GSD Ia), a rare autosomal inherited disorder, is characterized by accumulation of excessive glycogen and fat in the liver. Primary symptoms of GSD Ia include hypoglycemia; metabolic acidosis; elevated levels of lactate, uric acid and lipids; hepatomagaly and growth retardation. Glycogen storage disease type Ia was caused by mutations in the G6PC gene. In this study, mutations in a Vietnamese patient with glycogen storage disease type Ia were analyzed using the whole exome sequencing method. A missense mutation c.356AT (p.His119Leu) in the G6PC gene of the patient was identified in exon 3. Genetic analysis confirmed that this mutation was present under homozygous form In-silico analyses using SIFT and Mutation Taster confirmed the damaging effects of this mutations on the function of the proteins. This result enriches knowledge of the G6PC gene mutation spectrum and provides genetic data for further studies on glycogen storage disease type Ia in Viet Nam.