The main objective of this study is to evaluate and compare the performance different machine learning (ML) algorithms, namely, Artificial Neural Network (ANN), Extreme Learning Machine (ELM), Boosting Trees (Boosted) considering influence various training testing ratios in predicting soil shear strength, one most critical geotechnical engineering properties civil design construction. For aim, a database 538 samples collected from Long Phu 1 power plant project, Vietnam, was utilized...

This work emphasizes the use of silver decorative method to enhance antibacterial activity TiO2 and ZnO nanoparticles. These silver-decorated nanoparticles (hybrid nanoparticles) were synthesized using sodium borohydride as a reducing agent, with weight ratio Ag precursors/oxide = 1:30. The morphology optical properties these hybrid investigated transmission electron microscopy (TEM), X-ray diffraction (XRD) patterns, UV-Vis spectroscopy. agar-well diffusion was used evaluate their against...

Axial bearing capacity of piles is the most important parameter in pile foundation design. In this paper, artificial neural network (ANN) and random forest (RF) algorithms were utilized to predict ultimate axial driven piles. An unprecedented database containing 2314 static load test reports gathered, including diameter, length segments, natural ground elevation, top guide segment stop driving tip average standard penetration (SPT) value along embedded pile, SPT blow counts at as input...

Concrete filled steel tubes (CFSTs) show advantageous applications in the field of construction, especially for a high axial load capacity. The challenge using such structure lies selection many parameters constituting CFST, which necessitates defining complex relationships between components and corresponding properties. capacity (Pu) CFST is among most important mechanical In this study, possibility feedforward neural network (FNN) to predict Pu was investigated. Furthermore, an...

Gas multisensor devices offer an effective approach to monitor air pollution, which has become a pandemic in many cities, especially because of transport emissions. To be reliable, properly trained models need developed that combine output from sensors with weather data; however, factors can affect the accuracy models. The main objective this study was explore impact several input variables training different quality indexes using fuzzy logic combined two metaheuristic optimizations:...

Understanding shear behavior is crucial for the design of reinforced concrete beams and sustainability in construction civil engineering. Although numerous studies have been proposed, predicting such still needs further improvement. This study proposes a soft-computing tool to predict ultimate capacities (USCs) with steel fiber, one most important factors structural design. Two hybrid machine learning (ML) algorithms were created that combine neural networks (NNs) two distinct optimization...

Improvement of compressive strength prediction accuracy for concrete is crucial and considered a challenging task to reduce costly experiments time. Particularly, the determination using ground granulated blast furnace slag (GGBFS) more difficult due complexity composition mix design. In this paper, an approach random forest (RF), which one powerful machine learning algorithms, proposed predicting GGBFS. The RF model first evaluated determine best architecture, constitutes 500 growth trees...

Determination of pile bearing capacity is essential in foundation design. This study focused on the use evolutionary algorithms to optimize Deep Learning Neural Network (DLNN) algorithm predict driven pile. For this purpose, a Genetic Algorithm (GA) was developed select most significant features raw dataset. After that, GA-DLNN hybrid model optimal parameters for DLNN model, including: network algorithm, activation function hidden neurons, number layers, and neurons each layer. A database...

The principal purpose of this work is to develop three hybrid machine learning (ML) algorithms, namely ANFIS-RCSA, ANFIS-CA, and ANFIS-SFLA which are a combination adaptive neuro-fuzzy inference system (ANFIS) with metaheuristic optimization techniques such as real-coded simulated annealing (RCSA), cultural algorithm (CA) shuffled frog leaping (SFLA), respectively, predict the critical buckling load I-shaped cellular steel beams circular openings. For purpose, existing database tests on were...

Machine Learning (ML) has been applied widely in solving a lot of real-world problems. However, this approach is very sensitive to the selection input variables for modeling and simulation. In study, main objective analyze sensitivity an advanced ML method, namely Extreme (ELM) algorithm under different feature scenarios prediction shear strength soil. Feature backward elimination supported by Monte Carlo simulations was evaluate importance factors used modeling. A database constructed from...

The prediction accuracy of concrete compressive strength is important and considered a challenging task, aiming at reducing costly time‐consuming experiments. Moreover, using blast‐furnace slag (BFS) fly ash (FA) more difficult due to the complex mix design composition. In this investigation, an approach artificial neuron network (ANN), one most powerful machine learning algorithms, applied predict containing BFS FA. ANN models with hidden layer 13 number cases are proposed determine best...

In this study, a novel hybrid surrogate machine learning model based on feedforward neural network (FNN) and one step secant algorithm (OSS) was developed to predict the load-bearing capacity of concrete-filled steel tube columns (CFST), whereas OSS used optimize weights bias FNN for developing (FNN-OSS). For achieving goal, an experimental database containing 422 instances firstly gathered from literature develop FNN-OSS algorithm. The input variables in contained geometrical...

This study aims to predict the shear strength of reinforced concrete (RC) deep beams based on artificial neural network (ANN) using four training algorithms, namely, Levenberg–Marquardt (ANN-LM), quasi-Newton method (ANN-QN), conjugate gradient (ANN-CG), and descent (ANN-GD). A database containing 106 results RC beam tests is collected used investigate performance proposed algorithms. The ANN phase uses 70% data, randomly taken from dataset, whereas remaining 30% data are for algorithms’...

In this paper, an extensive simulation program is conducted to find out the optimal ANN model predict shear strength of fiber-reinforced polymer (FRP) concrete beams containing both flexural and reinforcements. For acquiring purpose, experimental database 125 samples collected from literature used best architecture ANN. database, input variables consist 9 inputs, such as ratio beam width, effective depth, span compressive concrete, longitudinal FRP reinforcement ratio, modulus elasticity...

Accurate determination of the axial load capacity pile is utmost importance when designing foundation. However, methods determining in field are often costly and time-consuming. Therefore, purpose this study to develop a hybrid machine-learning predict pile. In particular, two powerful optimization algorithms named Herd Optimization (PSO) Genetic Algorithm (GA) were used evolve Random Forest (RF) model architecture. For research, data set including 472 results tests Ha Nam province-Vietnam...

Abstract Understanding and predicting concrete carbonation are significant in designing durability maintaining the service life of reinforced structures. However, this purpose can hardly be reached because complex mechanisms depending on various variables such as cement content (C), fly ash (FA), water (W), concentration CO 2 , relative humidity (RH), temperature (T°C), exposition time (Time). This investigation proposes a machine learning (ML) approach including eight ML algorithms four...