@article { author = {Javidrad, F. and Nazari, M. and Javidrad, H. R.}, title = {An Innovative Optimized Design for Laminated Composites in terms of a Proposed Bi-Objective Technique}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {1-28}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.218142.1173}, abstract = {The article proposes a bi-objective optimization approach for layup design of laminates. The optimization method combines the Particle Swarm Optimization (PSO) heuristics and Simulated Annealing (SA) optimization method. The minimum weight optimization is subjected to design constraints such as strength, stiffness, layup blending continuity, and several manufacturing design rules, which are combined as a single function and included within the bi-objective formulation. Several composite materials design problems are included to show the capabilities and usefulness of the proposed method. The optimization analysis has also been connected to the finite element analysis to solve the problem of composite plate optimization with blending constraints. The plate is divided into some regions, and the blending constraints are imposed globally by using the concepts of the greater-than-or-equal-to blending to achieve continuity of laminate layups across the regions. The results generally showed that the proposed method led to excellent results, representing a promising approach for the design of laminated composite materials.}, keywords = {Laminated composites,Layup design,Bi-objective Optimization,Hybrid PSO-SA optimization,Layup blending}, url = {https://www.jsoftcivil.com/article_103760.html}, eprint = {https://www.jsoftcivil.com/article_103760_2d4a8bc5d6e28ded75f4db2e0d2f0b05.pdf} } @article { author = {Aiyelokun, Oluwatobi and Ojelabi, Akintunde and Agbede, Oluwole}, title = {Performance Evaluation of Machine Learning Models in Predicting Dry and Wet Climatic Phases}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {29-48}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.213319.1154}, abstract = {Water resource and environmental engineers need accurate information in harnessing water for diverse uses, therefore it is expedient to accurately predict dry and wet climatic phases in order to ensure optimum water resource planning and management. This study examined the applicability of machine learning models for the prediction of extreme dry and wet conditions in Minna, North Central Nigeria. Recorded rainfall, maximum temperature, minimum temperature, relative humidity, wind speed, sunshine hours and estimated potential evapotranspiration were used as predictors in the machine learning models, while hydrological extremes estimated from standardized precipitation index (SPI) served as a response variable. The performance of Support Vector Machine (SVM) based on different kernel types and Artificial Neural Network (ANN) based on different network structures were assessed for the prediction of the different phases of the climate of the study area. The study showed that while normal meteorological conditions occurred for about 74.8% of the study period, 8.9%, 4.6% and 1.9% of this period were moderately wet, severely wet and extremely wet respectively, and 4.7%, 3.4% and 1.7% of the study period were moderately dry, severely dry and extremely dry respectively. Furthermore, SVM based on Radial Basis Kernel with a coefficient of determination of 0.64 outperformed other SVM types and ANN with two hidden layers; with of coefficient of determination 0.68 was found to perform better than ANN with single layers. Generally, ANN was found to have higher accuracy than SVM in predicting dry and wet climatic phases in North Central Nigeria.}, keywords = {Water resources,Support Vector Machine,Artificial Neural Network,non-linear models}, url = {https://www.jsoftcivil.com/article_103457.html}, eprint = {https://www.jsoftcivil.com/article_103457_1988ab981f4ca9bca8b1803246ad5511.pdf} } @article { author = {Teimouri, Fateme and Ghatee, Mehdi}, title = {A Real-Time Warning System for Rear-End Collision Based on Random Forest Classifier}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {49-71}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.217605.1172}, abstract = {Rear-end collision warning system has a great role to enhance driving safety. In this system, some measures are used to evaluate the safety and in the case of dangerous, the system warns drivers. This system should be executed in real-time, to remain enough time to avoid collision with the front vehicle. To this end, in this paper, a new system is developed by using a random forest classifier to extract knowledge about warning and safe situations. This knowledge can be extracted from accidents and vehicle trajectory data. Since the data of these situations are imbalanced, a combination of cost-sensitive learning and classification methods was used to improve the sensitivity, specificity, and processing time of classification. To evaluate the performance of this system, vehicle-trajectory-data of 100 cars that have been provided by Virginia tech transportation institute, are used. The comparison results are given in terms of accuracy and processing time. By using TOPSIS multi-criteria selection method, it is shown that the implemented classifier is better than different classifiers including Bayesian network, Naive Bayes, MLP neural network, support vector machine, k-nearest neighbor, rule-based methods and decision tree. The implemented random forest gets 88.4% accuracy for detection of the dangerous situations and 94.7% for detection of the safe situations. Also, the proposed system is more robust compared with the perceptual-based and kinematic-based algorithms.}, keywords = {Rear-end collision,Driver assistant systems,Data mining,Classification Algorithms,TOPSIS}, url = {https://www.jsoftcivil.com/article_104357.html}, eprint = {https://www.jsoftcivil.com/article_104357_9b2e72712a07592b45dc4779534c1704.pdf} } @article { author = {Sharmila, R. and Velaga, Nagendra}, title = {Mode-Wise Corridor Level Travel-Time Estimation Using Machine Learning Models}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {72-97}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.215679.1164}, abstract = {This research is oriented towards exploring mode-wise corridor level travel-time estimation using Machine learning techniques such as Artificial Neural Network (ANN) and Support Vector Machine (SVM). Authors have considered buses (equipped with in-vehicle GPS) as the probe vehicles and attempted to calculate the travel-time of other modes such as cars along a stretch of arterial roads. The proposed study considers various influential factors that affect travel time such as road geometry, traffic parameters, location information from the GPS receiver and other spatiotemporal parameters that affect the travel-time. The study used a segment modeling method for segregating the data based on identified bus stop locations. A k-fold cross-validation technique was used for determining the optimum model parameters to be used in the ANN and SVM models. The developed models were tested on a study corridor of 59.48 km stretch in Mumbai, India. The data for this study were collected for a period of five days (Monday-Friday) during the morning peak period (from 8.00 am to 11.00 am). Evaluation scores such as MAPE (mean absolute percentage error), MAD (mean absolute deviation) and RMSE (root mean square error) were used for testing the performance of the models. The MAPE values for ANN and SVM models are 11.65 and 10.78 respectively. The developed model is further statistically validated using the Kolmogorov-Smirnov test. The results obtained from these tests proved that the proposed model is statistically valid.}, keywords = {Machine Learning,Travel-time,Support Vector Machines,Artificial Neural Networks}, url = {https://www.jsoftcivil.com/article_104410.html}, eprint = {https://www.jsoftcivil.com/article_104410_9b30aa82b5f33dfac039e2279a76dd22.pdf} } @article { author = {Ghazvinian, Hamidreza and Karami, Hojat and Farzin, Saeed and Mousavi, Sayed Farhad}, title = {Effect of MDF-Cover for Water Reservoir Evaporation Reduction, Experimental, and Soft Computing Approaches}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {98-110}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.213617.1156}, abstract = {In the civil engineering designs and water resources management projects, various methods have been proposed to prevent the evaporation of water storage tanks and pools, including the use of physical materials. The use of MDF sheets is an evaporation reduction method using physical elements, which can be useful in controlling evaporation. The present study investigates water evaporation reduction from a standard Colorado Sunken evaporation pan using 50 mm-thick MDF sheets covering 100% of the evaporation pan. The least-square support vector machine (LSSVM) and an artificial neural network (ANN) were used to estimate evaporation reduction. The efficiency of the intelligent methods was evaluated by the root mean square error (RMSE), coefficient of determination (R2), and mean absolute error (MAE). The R2, RMSE, and MAE values were attained for the LSSVM method in the test stage 0.8755, 1.6517, and 2.2042, and for the ANN model 0.7714, 2.112 and 1.6732 respectively which shows the LSSVM model has better performance than ANN model. The evaporation correlation, according to the Pearson test for sheet cover, MDF with minimum temperature, maximum temperature, sunny hours, is positive. It has 0.442, 0.362, and 0.387 values, respectively, and with minimum damp, maximum damp, pressure is negative and has -0.313, -0.350, and -0.319 values, respectively. The results reveal that MDF had satisfactory performance in controlling evaporation and lead to higher water resource storage. Performing tests for three months indicate that MDF sheets can result in an approximately 91% reduction in evaporation on average.}, keywords = {evaporation reduction,MDF,Artificial Neural Network,Least-square support vector machine}, url = {https://www.jsoftcivil.com/article_104761.html}, eprint = {https://www.jsoftcivil.com/article_104761_3a82494dae78ce400d54f86203a1433a.pdf} } @article { author = {Kalman Sipos, Tanja and Parsa, Payam}, title = {Empirical Formulation of Ferrocement Members Moment Capacity Using Artificial Neural Networks}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {111-126}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.221268.1181}, abstract = {In the two past decades, ferrocement members have been with a wide variety of uses in structural applications because of their unique physical properties (high surface-area-to-volume ratio and possible fabrication in any shape). In this study, two models were presented for a predict of the moment capacity of ferrocement members, one based on a back-propagation multilayer perceptron artificial neural network and the other proposing a new equation based on the multilayer perceptron network trained. These models with five input parameters including volume fraction of wire mesh, tensile strength, cube compressive strength of mortar, and width and the depth of specimens are presented. The results obtained from the two models are compared with experimental data and experimental equations such as plastic analysis, mechanism, and nonlinear regression approaches. Also, these results are compared with the results of the equations that researchers have proposed in recent years with soft computing methods (ANFIS, GEP, or GMDH). The prediction performance of the two models is significantly better than the experimental equations. These models are comparable to that of models provided with different soft computing methods to predict the moment capacity of ferrocement members. The result of this research has proposed a general equation with less mathematical complexity and more explicit.}, keywords = {Moment Capacity,Ferrocement Members,Artificial Neural Networks,Flexure Failure}, url = {https://www.jsoftcivil.com/article_104916.html}, eprint = {https://www.jsoftcivil.com/article_104916_5f6836479576600b535beae04ab852d7.pdf} } @article { author = {Shahrokhinasab, Esmail and Hosseinzadeh, Nima and Monirabbasi, Armin and Torkaman, Sadegh}, title = {Performance of Image-Based Crack Detection Systems in Concrete Structures}, journal = {Journal of Soft Computing in Civil Engineering}, volume = {4}, number = {1}, pages = {127-139}, year = {2020}, publisher = {Pouyan Press}, issn = {2588-2872}, eissn = {2588-2872}, doi = {10.22115/scce.2020.218984.1174}, abstract = {The traditional methods for calculating the width of the cracks in concrete structures are mainly based on the manual and non-systematic collection of information, and also depend on personal justifications and judgment. Due to the fact that these approaches are time-consuming and always there are some human errors inevitably, in recent years more attention is paid to the new methods for detection and monitoring of cracks. One of the most important new approaches is the application of image-based techniques. These schemes use field images and photos provided by the camera to determine specific parameters, such as damage occurrence, location, severity, length of cracks, width and depth of cracks. Moreover, tracking the crack propagation over time using a set of timed photos is among the design purposes of these methods. Image processing, and targeting are two common methods which have their own pros and cons. Results showed that the image processing approach detects some surface noises as cracks which is most challenging error in this method. On the other hand, targeting approach has shown weakness in determining the exact location of cracks. These limitations have pushed researchers to innovate more modern techniques such as Digital Image Correlation (DIC) and mathematical tools like Wavelet transform (WT) to eliminate these errors.}, keywords = {Crack detection,Damage Assessment,image processing,Percolation model,Digital Image Correlation}, url = {https://www.jsoftcivil.com/article_104922.html}, eprint = {https://www.jsoftcivil.com/article_104922_3db5fa818746505ac419cf27840d983e.pdf} }