@article { author = {Shalchi Tousi, Mehdi and Ghazavi, Mahmoud and Laali, Samane}, title = {Optimizing Reinforced Concrete Cantilever Retaining Walls Using Gases Brownian Motion Algorithm (GBMOA)}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {1-18}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.248638.1256}, abstract = {In this paper, the cost and weight of the reinforcement concrete cantilever retaining wall are optimized using Gases Brownian Motion Optimization Algorithm (GBMOA) which is based on the gas molecules motion. To investigate the optimization capability of the GBMOA, two objective functions of cost and weight are considered and verification is made using two available solutions for retaining wall design. Furthermore, the effect of wall geometries of retaining walls on their cost and weight is investigated using four different T-shape walls. Besides, sensitivity analyses for effects of backfill slope, stem height, surcharge, and backfill unit weight are carried out and of soil. Moreover, Rankine and Coulomb methods for lateral earth pressure calculation are used and results are compared. The GBMOA predictions are compared with those available in the literature. It has been shown that the use of GBMOA results in reducing significantly the cost and weight of retaining walls. In addition, the Coulomb lateral earth pressure can reduce the cost and weight of retaining walls.}, keywords = {Retaining wall optimization,Sensitivity analysis,gasses Brownian motion optimization,Cost and weight objective functions}, url = {https://www.jsoftcivil.com/article_122527.html}, eprint = {https://www.jsoftcivil.com/article_122527_ce372588de3b46df8b9c21e8eb2bc6c2.pdf} } @article { author = {Pandey, Shivam and Kumar, Veerendra and Kumar, Pawan}, title = {Application and Analysis of Machine Learning Algorithms for Design of Concrete Mix with Plasticizer and without Plasticizer}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {19-37}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.248779.1257}, abstract = {The objective of this paper is to find an alternative to conventional method of concrete mix design. For finding the alternative, 4 machine learning algorithms viz. multi-variable linear regression, Support Vector Regression, Decision Tree Regression and Artificial Neural Network for designing concrete mix of desired properties. The multi-variable linear regression model is just a simplistic baseline model, support vector regression Artificial Neural Network model were made because past researchers worked heavily on them, Decision tree model was made by authors own intuition. Their results have been compared to find the best algorithm. Finally, we check if the best performing algorithm is accurate enough to replace the convention method. For this, we utilize the concrete mix designs done in lab for various on site designs. The models have been designed for both mixes types – with plasticizer and without plasticizer The paper presents detailed comparison of four models Based on the results obtained from the four models, the best one has been selected based on high accuracy and least computational cost. Each sample had 24 features initially, out of which, most significant features were chosen which were contributing towards prediction of a variable using f regression and p values and models were trained on those selected features. Based on the R squared value, best fitting models were selected among the four algorithms used. From the paper, the author(s) conclude that decision tree regression is best for calculating the amount of ingredients required with R squared values close to 0.8 for most of the models. DTR model is also computationally cheaper than ANN and future works with DTR in mix design is highly recommended in this paper.}, keywords = {Machine Learning,linear regression,Support vector regression,Decision tree regression,Artificial Neural Network,Feature selection}, url = {https://www.jsoftcivil.com/article_122526.html}, eprint = {https://www.jsoftcivil.com/article_122526_71ddba188ca30d2f01105a4341cecfa0.pdf} } @article { author = {Esmaeilzadeh, Akbar and Khademi, Diako and Mikaeil, Reza and Taghizadeh, Shadi}, title = {The Use of VIKOR Method to Set up Place Locating of Processing Plant (Case Study: Processing Plant of South of West Azerbaijan)}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {38-48}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.237655.1245}, abstract = {Selecting the propriate place of mineral processing plant is one of the most important steps in setting up it. It depends on several factors that make it a subroutine of multi criteria decision making (MCDM) problem. In this research, locating an optimal site for quarries processing plant, using VIKOR method is studied. Three sites were considered for this purpose and criteria such as transportation, water supply, electricity supply, gas supply, distance to markets, the price of land, topography and distance to where personal supplement place for the three possible regions were analyzed. After calculating parameters of VIKOR method, according to the obtained and ranked Q values of 0.8969, 0.0000, 0.1000, respectively for three possible cases of place A1, A2 and A3, case of A2 is selected as best choice.}, keywords = {Place Locating,Processing Plant,Multi-criteria decision making,VIKOR}, url = {https://www.jsoftcivil.com/article_122019.html}, eprint = {https://www.jsoftcivil.com/article_122019_10a1af3e0dfa2e35e22806d265e0df34.pdf} } @article { author = {Ahmad, Burhan and Ali, Shaukat and Khan, Tahir and Hasson, Shabehul and Bukhari, Syed Ahsan Ali}, title = {Simulating the Urban Heat Island Augmented with a Heat Wave Episode Using ICTP RegCM4.7 in a Mega-Urban Structure of Karachi, Pakistan}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {49-61}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.237606.1243}, abstract = {The metropolis of Karachi, with a density of around 4000 persons/km2 at present, is going through unprecedented urbanization and population growth, which can augment Urban Heat Island (UHI) triggered heat wave impacts on life and living. Here, we investigate skill of Regional Climate Model version 4.7 (RegCM4.7) in simulating 2015 heat wave episode in southern Pakistan by dynamically downscaling ERA-Interim reanalysis at 10km resolution and switching on the urban parameterization in the employed land surface scheme. Our results suggest that the RegCM4.7 has successfully reproduced the overall conditions of the 2015 heat wave. For instance simulated surface temperature maxima is seen well above 50°C for at least three consecutive days along the austere heat wave duration. Also, extended sustenance of a ridge in locality of the Karachi, as well as a low pressure system in adjacent Arabian Sea is seen to restrain normal drift of sea-breeze to the coastal city, in the simulated output. The National Weather Service (NWS) based heat index derived from the simulation is seen to remain well above 124°F during the whole heat wave period, placing the city in an “Extreme Danger” class of discomfort and high vulnerability to heat stroke. The UHI integrated RegCM4.7 is hence recommended for use in modelling to help in adaptation strategies against occurrences of such heat wave events in future.}, keywords = {Karachi Heat Wave,Urban Heat Island,RegCM4.7,Heat Index}, url = {https://www.jsoftcivil.com/article_122528.html}, eprint = {https://www.jsoftcivil.com/article_122528_1242040a372fe211fb8f3d1e8fe1046f.pdf} } @article { author = {Rahmati, Yalda and Samimi, Amir}, title = {Escort Patterns in Dual-Worker Households with Students}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {62-79}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.257897.1261}, abstract = {Individuals have been regarded as independent decision makers in majority of transportation analysis. However, agents’ behaviors are usually affected by the interactions among the members in a group; and therefore, individual decision-making paradigms may result in unrealistic outcomes and erroneous interpretations of the results. In light of this, the present study develops discrete choice models in individual and group levels and compares their prediction power in predicting the choice of escort pattern in dual-worker households with at least one under-18-year-old student. The main purpose is to reveal the efficiency of each approach in analyzing parent-child joint activities and highlight the effect of model misspecification in predicting group decisions using a quantifiable measure. The results reveal that more than 25 percent of correct predictions in school trips will be missed when the conventional individual decision-making procedure, rather than a group decision-making paradigm, is adopted. Also, 20 percent of the observed reduction in the explanatory power of the model was associated with trips from school. The findings of this study underscore the significance of implementing group decision-making paradigms when the context requires.}, keywords = {group decision-making,Interactions,Escort patterns,School trips}, url = {https://www.jsoftcivil.com/article_122719.html}, eprint = {https://www.jsoftcivil.com/article_122719_886b1c78e8d4bf5b4176170b92d7906c.pdf} } @article { author = {Ghanizadeh, Ali Reza and Heidarabadizadeh, Nasrin and Heravi, Fahimeh}, title = {Gaussian Process Regression (GPR) for Auto-Estimation of Resilient Modulus of Stabilized Base Materials}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {80-94}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.269187.1273}, abstract = {The resilient modulus of different pavement materials is one of the most important parameters for the pavement design using the mechanistic-empirical (M-E) method. The resilient modulus is generally determined by a triaxial test, which is expensive and time-consuming and requires special laboratory facilities. This study aims to develop a model based on the Gaussian Process Regression (GPR) to predict the resilient modulus of stabilized base material with different additives under wetting-drying cycles. For this purpose, a laboratory dataset containing 704 records have been used. The input parameters were considered as the wetting-drying cycles, free lime to silica ratio, Alumina and iron oxide compounds in the additives, maximum dry density to optimum moisture content ratio, deviator stress, and confining stress. The results indicate high accuracy of the GPR method with a regression coefficient of 0.997 and 0.986 respectively for train and test data and 0.995 for all datasets. Comparing the developed model based on the GPR method with the developed models in the literature based on the artificial neural network methods and the support vector machines shows higher accuracy of the GPR method.}, keywords = {Resilient Modulus,Stabilized base,Wetting and drying cycles,Gaussian Process Regression}, url = {https://www.jsoftcivil.com/article_128310.html}, eprint = {https://www.jsoftcivil.com/article_128310_636da5a2a24405a295194f872c1316ae.pdf} } @article { author = {Kumar, Pawan and Pandey, Shivam and Maiti, Pabitra}, title = {A Modified Genetic Algorithm in C++ for Optimization of Steel Truss Structures}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {5}, number = {1}, pages = {95-108}, year = {2021}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2021.242552.1249}, abstract = {A common structural design optimization problem is weight minimization which is done by choosing a set of variables that represent the structural or the architectural configuration of the system satisfying few design specific criterion. In general, genetic algorithms (GAs) are ideal to be used for unconstrained optimization, so it is required to transform the constrained problem into an unconstrained one. A violation of normalized constraints-based formulation method has been used in the present work for this purpose. A modified algorithm has been developed in C++ using concept of genotypes for optimization using discreet design variable. A detailed analysis of optimization of a simple steel truss with discrete design variables using different variations of genetic algorithm is presented here. Also, an attempt has been made to study the sensitivity of the algorithm with respect to the optimization operators i.e., initial population size, rate of mutation.}, keywords = {Genetic Algorithm,Optimization operators,Discreet Design Variables,Genotypes}, url = {https://www.jsoftcivil.com/article_129389.html}, eprint = {https://www.jsoftcivil.com/article_129389_fdf893c75ebafeb5d43a22ebdbcc1314.pdf} }