Fiber-reinforced polymer (FRP) is an innovative material in the construction industry. It is beneficial because of its toughness, and unlike steel, it is not prone to corrosion. Some research studies focus its behavior as a reinforcement in concrete while deriving several equations pertaining to its shear strength capacity. This study used the artificial neural network modeling technique to derive a more accurate solution to predict concrete shear capacity with FRP as reinforcement. Experimental data from previous studies were collected and used to train the model. The parameters considered were compressive strength of concrete, FRP ratio, beam dimensions, and modulus of elasticity. As a result, the model consistently provides a better prediction of the shear capacity of concrete against existing models like ACI 440.1R-03, ACI 440.1R-06, and El-Sayed. Furthermore, the ANN model showed no sign of disarray in predicting every parameter compared to other existing models. According to ACI 440.1R-06, FRP bars largely affect the total shear capacity of concrete. In the model provided by ACI, FRP reinforcement’s axial stiffness accounts linearly to the shear strength capacity of concrete. Since then, the predicted capacity in accordance with the ACI was excessively conservative. With respect to the derived model, axial stiffness offered a variation in the shear capacity. The proposed ANN model can be utilized for the design since the minimum ratio between the actual test result yields to 0.77 which is greater than the strength reduction factor of 0.75. Parametric studies were also conducted to show the effect of the modulus of elasticity of FRP, FRP ratio, and beam dimensions on the shear capacity.

Carbonation is a dangerous threat to concrete since it reduces the alkalinity of normal or self-compacting concrete (SCC), allowing iron to corrode and spall the cover. The goal of this research is to use an artificial neural network to create a corrosion prediction model for steel in self-compacting concrete that has been subjected to carbonation. In this study, MATLABR2019a was used to create a feedforward back propagation neural network. As a training function, the researchers utilized the Levenberg-Marquardt back propagation (TRAINLM) which adjusts weights and bias values using Levenberg-Marquardt optimization. The researchers used gradient descent with momentum weight/bias learning (LEARNGDM) for the adaptation learning function, which is a technique that aids the gradient in determining which way to go. The network’s performance was measured using the mean square error (MSE). The Hyperbolic tangent sigmoid transfer function (TANSIG) was also employed as the transfer function since the values obtained by this function range from +1 to -1, considering both the positive and negative aspects of the parameter. To minimize overfitting, the number of hidden nodes should be fewer than the number of input parameters. The researchers tested 4-12 hidden nodes. Modeling was done using data from 102 experimental studies of self-compacting concrete exposed to corrosion. Using feed-forward back propagation ANN with 1 hidden layer and 8 hidden nodes, a Pearson R-value of 0.98748 and a mean square error of 0.5725 were obtained. The factor that most affect the carbonation depth were water-cement ratio and fly ash content. The suggested model was able to analytically describe the connection and behaviors of the various mixtures to the carbonation depth in the parametric investigation. The parameters characteristics were likewise described by the model.

The study observes the Pandemic Crisis (Covid 19) that resulted in impacts on the Transportation category in the area National Capital Region. Public transportation is an important aspect of human’s ability to travel to different places whether its personal or business purpose, it’s a part of life that people take for granted and can’t be taken away easily. But due to the pandemic era, people have been careful in their choices, which resulted in the change standard when it comes to public transportation choices. With that said, to understand and observe these impacts, a scenario must be made such as before and after the pandemic designed as an environment for the study to take root. The study has used machine learning called Random Forest Algorithm with the used several parameters to create a prediction model. As for the method in gathering data, a survey of Google Form is utilized to gather 200 participants of the National Capital Region with varying parameters for their choice of public transportation. The machine algorithm has shown satisfactory accuracy of 89.88% and 88.88%. As an important note, it is observed that travel expense has more impact on public transportation choices than other parameters. The Random Forest Algorithm has been utilized in creating classification types of models and can help future researchers improve the machine learning approach.