Predicting load capacity of shear walls using SVR–RSM model

Topology optimization of the flat steel shear wall based on the volume constraint and strain energy assumptions under the seismic loading conditions

In structural engineering systems, shear walls are two-dimensional vertical elements designed to endure lateral forces acting in-plane, most frequently seismic and wind loads. Shear walls come in a variety of materials and are typically found in high-rise structures. Because steel shear walls are lighter, more ductile, and stronger than other concrete shear walls, they are advised for usage in steel constructions. It is important to remember that the steel shear wall has an infill plate, which can be produced in a variety of forms. The critical zones in flat steel shear walls are the joints and corners where the infill plate and frame meet. The flat infill plate can be modified to improve the strength and weight performance of the steel shear walls. One of these procedures is Topology Optimization (TO) and this method can reduce the weight and also, increase the strength against the cyclic loading sequences. In the current research paper, the TO of the infill steel plate was considered based on the two methods of volume constraint and maximization of strain energy. Four different volumes (i.e., 60%, 70%, 80%, and 90%) were assumed for the mentioned element in the steel shear wall. The obtained results revealed that the topology configuration of CCSSW with 90% volume constraint presented the highest seismic loading performance. The cumulated energy for this type of SSW was around 700 kJ while it was around 600 kJ for other topology optimization configurations.

The consumer price index prediction using machine learning approaches: Evidence from the United States

The consumer price index (CPI) is one of the most important macroeconomic indicators for determining inflation, and accurate predictions of CPI changes are important for a country's economic development. This study uses multivariate linear regression (MLR), support vector regression (SVR), autoregressive distributed lag (ARDL), and multivariate adaptive regression splines (MARS) to predict the CPI of the United States. Data from January 2017 to February 2022 were randomly selected and divided into two stages: 80 % for training and 20% for testing. The US CPI was modeled for the observed period and relied on a mix of elements, including crude oil price, world gold price, and federal fund effective rate. Evaluation metrics-mean absolute percentage value, mean absolute error, root mean square error, R-squared, and correlation of determination-were employed to estimate forecasted values. The MLR, SVR, ARDL, and MARS models attained high accuracy parameters, while the MARS algorithm generated higher accuracy in US CPI forecasts than the others in the testing phase. These outputs could support the US government in overseeing economic policies, sectors, and social security, thereby boosting national economic development.

Optimization of biocementation responses by artificial neural network and random forest in comparison to response surface methodology

In this article, the optimization of the specific urease activity (SUA) and the calcium carbonate (CaCO₃) using microbially induced calcite precipitation (MICP) was compared to optimization using three algorithms based on machine learning: random forest regressor, artificial neural networks (ANNs), and multivariate linear regression. This study applied the techniques in two existing response surface method (RSM) experiments involving MICP technique. Random forest-based models and artificial neural network-based models were submitted through the optimization of hyperparameters via cross-validation technique and grid search, to select the best-optimized model. For this study, the random forest-based algorithm is aimed at having the best performance of 0.9381 and 0.9463 in comparison to the original r² of 0.9021 and 0.8530, respectively. This study is aimed at exploring the capability of using machine learning-based models in small datasets for the purpose of optimization of experimental variables in MICP technique and the meaningfulness of the models by their specificities in the small experimental datasets applied to experimental designs. This study is aimed at exploring the capability of using machine learning-based models in small datasets for experimental variable optimization in MICP technique. The use of these techniques can create prerogatives to scale and mitigate costs in future experiments associated to the field.

Prediction of monthly precipitation using various artificial models and comparison with mathematical models

Precipitation (PP) prediction is an interesting topic in the meteorology or hydrology field since it is directly related to agriculture, the management of water resources in hydrologic basins, and water scarcity. Selecting the right model to predict precipitation has always been a challenge because it could help researchers to use the proper model for their purposes. Accordingly, the performance of five artificial models (feed-forward neural network, cascade forward neural network, Elman neural network, multi-layer perceptron neural network, and radial basis neural network) and three mathematical models (Poisson regression model (PRM), quadratic model, and multiple linear regression) were evaluated for their ability to predict the monthly precipitation in Mediterranean coastal cities located in Eastern part of Mediterranean Sea for the first time. Twenty-seven Mediterranean coastal cities are considered case studies. For this aim, scenario 1 and scenario 2 with various input variables are proposed. Scenario 1 is developed using the number of months (MN), maximum temperature (Tmax), minimum temperature (Tmin), downward radiation (DR), wind speed (WS), vapor pressure (VP), and actual evapotranspiration (AE). Scenario 2 is developed by adding geographical coordinates (latitude, longitude, and altitude) to the global meteorological data to see the impact of geographical coordinates on the accuracy of the prediction of monthly precipitation. This study utilized the monthly data, which were obtained from TerraClimate for the period from 2010 to 2021. Based on the performance indexes, the PRM model performed best for the prediction of monthly precipitation in all selected locations compared to other models. Moreover, the results indicate that scenario 2 ([Formula: see text]) has shown higher prediction accuracy compared to scenario 1 ([Formula: see text]). In conclusion, PRM with the combination of [[Formula: see text]] had RMSE value that was lower by 12% relative to PRM with the combination of [[Formula: see text]]. Consequently, the PRM model can be recommended for modeling the complexity of interactions for precipitation-climate conditions-geographical coordinates and predicting precipitation.

Regional collaboration to simultaneously mitigate PM2.5 and O3 pollution in Beijing-Tianjin-Hebei and the surrounding area: Multi-model synthesis from multiple data sources

Beijing-Tianjin-Hebei and the surrounding area (BTHSA) shows the poorest air quality in China, reflected in sub-standard PM_2.5 and increasingly pronounced O₃ pollution, stressing the urgency for regional cooperation and collaborative control of PM_2.5 and O₃. With the aim to explore the cooperative regions and response mechanisms of PM_2.5 and O₃ in BTHSA, this study applied multiple mathematical models and analytical indicators to multiple data sources, including applying self-organizing map (SOM), response surface model (RSM), random forest (RF), distributed lag nonlinear models (DLNMs), and meta-analysis, on ground observations of air quality and meteorology, ozone monitoring instrument (OMI) observations, and air pollutant emission inventory. The results revealed that BTHSA exhibited clear regional characteristics of air pollution and can be divided into four clusters for enhanced intercity cooperation. Over 2015-2020, anthropogenic factors played more important roles than meteorological ones on the alleviation of PM_2.5 and the deterioration of O₃. RSM based on observations and RF based on emissions both suggested that, in the near future, strengthened abatement of SO₂, PM_2.5 and VOC can be beneficial for controlling PM_2.5 and O₃ pollution, while intensive NOx reduction in PM_2.5-dominant months and mitigatory NOx reduction in O₃-dominant months should be formulated before certifying an obvious transition of O₃-NOx-VOC sensitivity. This study, with multi-model and multi-data fusion, can be expected to provide synthesized fact- and science-based guidance for the next-stage collaborative control of PM_2.5 and O₃ in BTHSA.

A Semi-Active Control Technique through MR Fluid Dampers for Seismic Protection of Single-Story RC Precast Buildings

The work proposes an innovative solution for the reduction of seismic effects on precast reinforced concrete (RC) structures. It is a semi-active control system based on the use of magnetorheological dampers. The special base restraint is remotely and automatically controlled according to a control algorithm, which modifies the dissipative capability of the structure as a function of an instantaneous dynamic response. The aim is that of reducing the base bending moment demand without a significant increase in the top displacement response. A procedure for the optimal calibration of the parameters involved in the control logic is also proposed. Non-linear modelling of a case-study structure has been performed in the OpenSees environment, also involving the specific detailing of a novel variable base restraint. Non-linear time history analyses against natural earthquakes allowed testing of the optimization procedure for the control algorithm parameters, finally the capability of the proposed technology to mitigate seismic risk of new or existing one-story precast RC structures is highlighted.