Pouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Environmental Risk Management of Eyvashan Dam Using Traditional-FMEA and FIS-FMEA Methods12016889510.22115/scce.2023.369468.1564ENBehrang BeiranvandPh.D. Candidate in Civil Engineering, Water and Hydraulic Structures, University of Qom, Iran0000-0001-8934-2020Taher RajaeeProfessor, Department of Civil Engineering, University of Qom, Iran0000-0002-4325-2537Journal Article20221112The implementation of large dam construction projects, despite the positive economic and social effects on the region, may endanger the development of the region with long-term negative effects. Therefore, it seems necessary to pay attention to this issue to reduce the negative effects of large dam construction projects and to consider them in the evaluation of benefits and costs for policy and codified planning in the water resources sector. In this research, Shannon's entropy-TOPSIS methodology and fuzzy TOPSIS methods have been used to identify and prioritize the environmental risk of Eyvashan dam in the construction and operation phases. Also, in this article, to improve the risk management of earthen dams, a comprehensive review was presented to overcome the disadvantages of traditional FMEA through the improvement of FMEA, with the combination of Fuzzy Inference System (FIS). The results show that in both Shannon's entropy-TOPSIS and fuzzy TOPSIS methods, soil erosion in the construction phase and aquatic in the exploitation phase is the major environmental risks. Evaluation of Risk Priority Number (RPN) in both traditional RPN and FIS-RPN modes shows a significant increase in RPN in fuzzy mode compared to the traditional method in all risk environments. Therefore, the urgency of action evaluation criteria in the FIS-FMEA mode is much more serious than in the traditional FMEA mode and requires more accurate identification and monitoring of risk environments.https://www.jsoftcivil.com/article_168895_b7b9afa986df3aa8dc2ad7c26a87eea6.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Computer Vision-Based Recognition of Pavement Crack Patterns Using Light Gradient Boosting Machine, Deep Neural Network, and Convolutional Neural Network215116889410.22115/scce.2023.367276.1547ENNhat-Duc HoangLecturer, Institute of Research and Development, Duy Tan University, Da Nang, 550000, VietnamLecturer, Faculty of Civil Engineering, Duy Tan University, Da Nang, 550000, VietnamQuoc-Lam NguyenLecturer, Faculty of Civil Engineering, Duy Tan University, Da Nang, 550000, VietnamJournal Article20221025The performance and serviceability of asphalt pavements have a direct influence on people's daily lives. Timely detection of pavement cracks is crucial in the task of periodic pavement survey. This paper proposes and verifies a novel computer vision-based method for recognizing pavement crack patterns. Image processing techniques, including Gaussian steerable filters, projection integrals, and image texture analyses, are employed to characterize the surface condition of asphalt pavement roads. Light Gradient Boosting Machine, Deep Neural Network, and Convolutional Neural Network are employed to recognize various patterns including longitudinal, transverse, diagonal, minor fatigue, and severe fatigue cracks. A dataset, including 12,000 samples, has been collected to construct and verify the computer vision-based approaches. Based on experiments, it can be found that all three machine learning models are capable of delivering good categorization results with an accuracy rate > 0.93 and Cohen's Kappa coefficient > 0.76. Notably, the Light Gradient Boosting Machine has achieved the most desired performance with an accuracy rate > 0.96 and Cohen's Kappa coefficient > 0.88.https://www.jsoftcivil.com/article_168894_3a5faac9b41ed3f5d9273a1da3c0b4b3.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Tree-Based Techniques for Predicting the Compression Index of Clayey Soils526716817810.22115/scce.2023.377601.1579ENTsang LongGeofirst Pty Ltd., 2/7 Luso Drive, Unanderra, NSW 2526, AustraliaBiao HeDepartment of Civil Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, Malaysia0000-0003-0906-7298Ali GhorbaniAssistant Professor, Department of Engineering, Payame Noor University, Tehran, Iran0000-0001-7637-6846Seyed Mohammad Hossein KhatamiDepartment of Civil Engineering, Technical and Vocational University (TVU), Tehran, IranJournal Article20221228Compression index is an effective assessment of primary consolidation settlement of clayey soils, but the process of obtaining compression index is time-consuming and laborious. Thus, in the present study, we developed two classical tree-based techniques: random forest (RF) and extreme gradient boosting (XGBoost), to predict the compression index of clayey soils. To establish these two models, we collected an available dataset—including 391 consolidation tests for soils—from previously published research. The dataset consists of six physical parameters, including the initial void ratio, natural water content, liquid limit, plastic index, specific gravity, and soil compression index. The first five parameters are the models’ inputs while the compression index is the models’ output. We trained both two tree-based models using 90% of the entire dataset and used the remaining 10% to assess the well-trained models, which is consistent with the published research. Several statistical metrics, such as coefficient of determination (R<sup>2</sup>), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), are the criteria for assessing the models’ performance. The results show that the RF model has better accuracy in predicting compression index compared with the XGBoost model because it outperforms the XGBoost model both on the training and testing datasets. The performance of the RF model is R<sup>2</sup> of 0.928 and 0.818, RMSE of 0.016 and 0.025, MAPE of 7.046% and 10.082%, and MAE of 0.012 and 0.020 on the training and testing datasets, respectively. The sensitivity analysis reveals that the initial void ratio has a significant impact on the compression index of clayey soils.https://www.jsoftcivil.com/article_168178_28f85a701dd16b8159874d1863bd7622.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Prediction of Compressive Strength for Fly Ash-Based Concrete: Critical Comparison of Machine Learning Algorithms6811016921810.22115/scce.2023.353183.1493ENSifti WadhawanGraduate Students, Department of Civil Engineering, DR BR Ambedkar National Institute of Technology, Jalandhar, Punjab, India0000-0002-5525-6762Akshita BassiGraduate Students, Department of Civil Engineering, DR BR Ambedkar National Institute of Technology, Jalandhar, Punjab, India0000-0003-2266-9744Rajwinder SinghPh.D. Student, Department of Civil Engineering, DR BR Ambedkar National Institute of Technology, Jalandhar, Punjab, India0000-0002-2621-4985Mahesh PatelAssistant Professor, Department of Civil Engineering, DR BR Ambedkar National Institute of Technology, Jalandhar, Punjab, India0000-0001-8679-3205Journal Article20220724In the construction field, compressive strength is one of the most critical parameters of concrete. However, a significant amount of physical effort and natural raw materials are required to produce concrete. In addition, the curing period of concrete for at least 28 days is a must for attaining the required compressive strength. Various types of industrial and agricultural wastes have been used in concrete to reduce cement consumption and problems due to its production. Therefore, considering such constraints, the application of Artificial Intelligence (AI) has been widely used in the current scenarios to predict the desired output parameters. In the present study, 12 input parameters have been considered along with 455 data points and nine Machine Learning (ML) models to forecast the compressive strength of Fly Ash (FA) based concrete. The output from the models has been compared to find the best-fit model in terms of numerous analyses such as visual descriptive statistics, errors, <em>R<sup>2</sup></em>, Taylor’s diagram, Feature Importance (FI), and scatter plots. Based on the analysis of the current study, Decision Tree (DT) and Gradient Boost (GB) were found to be the best-fit model because of the least errors and higher <em>R<sup>2</sup></em> values as compared to other models.https://www.jsoftcivil.com/article_169218_72e6f1b2b45196a5e0aa6dd1ea8b0006.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Effect of SVM Kernel Functions on Bearing Capacity Assessment of Deep Foundations11112816921910.22115/scce.2023.356959.1510ENDanial Jahed ArmaghaniCentre of Tropical Geoengineering (GEOTROPIK), Institute of Smart Infrastructure and Innovative Engineering (ISIIC), Faculty of Civil Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia0000-0001-8171-6403Yong Yi MingDepartment of Civil Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, MalaysiaAhmedh Salih MohammedCivil Engineering Department, College of Engineering, University of Sulaimani, Kurdistan Region, IraqEhsan MomeniDepartment of Civil Engineering, Faculty of Engineering, Lorestan University, Khorramabad 6815144316, Iran0000-0003-4084-485XHarnedi MaizirDepartment of Civil Engineering, Sekolah Tinggi Teknologi Pekanbaru, IndonesiaJournal Article20220820Pile foundations are vastly utilized in construction projects where their capacities (pile bearing capacity, PBC) should be determined in different stages of construction. A highly reliable and accurate prediction model can lead to many advantages, such as reducing the construction cost, shortening the construction timeline, and providing safety construction. Hence, the aim of this study is the developments of statistical and artificial intelligence (AI) models for predicting bearing capacities of 141 piles. At the preliminary of the study, features or inputs of this study to predict PBC were selected trough simple regression analysis. Then, this study presents different kernels of support vector machine (SVM) technique, i.e., the dot, the radial basis function (RBF), the polynomial, the neural, and the ANOVA to predict the PBC. The aforementioned models were evaluated by several performance indices and their results were compared using a simple ranking system. The results showed that the SVM-RBF model is able to achieve the highest coefficient of determination, R<sup>2</sup> values which are 0.967 and 0.993 for training and testing stages, respectively. It is important to mention that a multiple regression model was also employed to predict PBC values. The other SVM kernels were provided a high degree of accuracy for estimating PBC, however, the SVM-RBF model is recommended to be used as a powerful, highly reliable, and simple solution for PBC prediction.https://www.jsoftcivil.com/article_169219_7f5241581497d32a89dd2bc7cf5b956b.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Attenuation Models for Estimation of Vertical Peak Ground Acceleration Based on PSO Algorithm for the North of Iran12914216921610.22115/scce.2023.374235.1576ENElham Mohammad KamarehM.Sc. Student in Civil-Earthquake Engineering, Faculty of Civil Engineering, Urmia University of Technology, Urmia, IranJavad Mokari RahmdelAssistant Professor, Faculty of Civil Engineering, Urmia University of Technology, Urmia, IranAkbar ShirzadAssociate Professor, Faculty of Civil Engineering, Urmia University of Technology, Urmia, IranRashed PoormirzaeAssistant Professor, Faculty of Mining Engineering, Urmia University of Technology, Urmia, IranJournal Article20221202Peak ground acceleration (PGA) is a critical parameter in ground-motion investigations, in particular in earthquake-prone areas such as Iran. In the current study, a new method based on particle swarm optimization (PSO) is developed to obtain an efficient attenuation relationship for the vertical PGA component within the northern Iranian plateau. The main purpose of this study is to propose suitable attenuation relationships for calculating the PGA for the Alborz, Tabriz and Kopet Dag faults in the vertical direction. To this aim, the available catalogs of the study area are investigated, and finally about 240 earthquake records (with a moment magnitude of 4.1 to 6.4) are chosen to develop the model. Afterward, the PSO algorithm is used to estimate model parameters, i.e., unknown coefficients of the model (attenuation relationship). Different statistical criteria showed the acceptable performance of the proposed relationships in the estimation of vertical PGA components in comparison to the previously developed relationships for the northern plateau of Iran. Developed attenuation relationships in the current study are independent of shear wave velocity. This issue is the advantage of proposed relationships for utilizing in the situations where there are not sufficient shear wave velocity data.https://www.jsoftcivil.com/article_169216_8e67c9f28ace7a1679dc3ffe22e24340.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727320230701Connection Design of Precast Concrete Structures Using Machine Learning Techniques14315516921510.22115/scce.2023.356547.1506ENNitin DahiyaPh.D. Student, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, IndiaBabita SainiAssociate Professor, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, IndiaH. D.ChalakAssistant Professor, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, IndiaJournal Article20220817In this research, the number of dowels (horizontal connection) has been determined using support vector machines (SVM), gradient boosting and artificial neural networks (ANN-Multilayer perceptron). Building height, length and thickness of the wall, maximum shear, maximum compressive force and maximum tension were the input parameters while the output parameter was the number of dowels. 1140 machine learning models were used, out of which 814 were used as training datasets and 326 as test datasets. A coefficient of correlation of 0.9264, root mean square error of 0.3677 and scattering Index of 4.75 % was achieved by SVM radial basis kernel function (SVM-RBF) as compared to a coefficient of correlation of 0.9232, root mean square error of 0.3743 and scattering Index of 4.83 % by resilient ANN-Multilayer perceptron, suggesting that SVM-RBF is more accurate in estimating the number of dowels. The study's encouraging findings highlight the need for additional research into the use of machine learning in civil engineering.https://www.jsoftcivil.com/article_169215_a89513093a05a707ab863534b5d275f3.pdf