Pouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401A Comparative Study of Shearlet, Wavelet, Laplacian Pyramid, Curvelet, and Contourlet Transform to Defect Detection14216621810.22115/scce.2023.356475.1505ENSepideh VafaiePh.D. Student, Faculty of Earth and Environmental Studies, Montclair State University, United States0000-0003-4338-2937Eysa SalajeghehProfessor, Faculty of civil Engineering, Shahid Bahonar University of Kerman, Kerman, IranJournal Article20220816This study presents a new approach based on shearlet transform for the first time to detect damages, and compare it with the wavelet, Laplacian pyramid, curvelet, and contourlet transforms to specify different types of defects in plate structures. Wavelet and Laplacian pyramid transforms have inferior performance to detect flaws with different multi-directions, such as curves, because of their basic element form, expressing the need for more efficient transforms. Therefore, some transforms, including curvelet and contourlet, have been evaluated so far for improving the performance of traditional transforms. Although these transforms have overcome the deficiencies of previous methods, they have a weakness in detecting several imperfections with various shapes in plate structures —one of the essential requirements that each transform should possess. In this study, we have used the shearlet transform that is used for the first time to detect identification and overcome all previous transform dysfunctionalities. In this regard, these transforms were applied to a four-fixed supported square plate with various defects. The obtained results revealed that the shearlet transform has the premier capability to demonstrate all kinds of damages compared to the other transforms, namely wavelet, Laplacian pyramid, curvelet, and contourlet. Also, the shearlet transform can be considered as an excellent and operational approach to demonstrate different forms of defects. Furthermore, the performance and correctness of the transforms have been verified via the experiment.https://www.jsoftcivil.com/article_166218_fc82f36dfd8daac85eaece6a0394a110.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401Predictive Models for Prediction of Broad Crested Gabion Weir Aeration Performance437316891910.22115/scce.2023.357761.1516ENNand KumarTiwariAssociate Professor, Department of Civil Engineering, National Institute of Technology, Kurukshetra (Haryana), India0000-0002-3153-2531KM LuxmiPh.D. Scholar, Department of Civil Engineering, National Institute of Technology, Kurukshetra (Haryana), IndiaSubodh RanjanProfessor, Department of Civil Engineering, National Institute of Technology, Kurukshetra (Haryana), IndiaJournal Article20220826The gabion weirs serve the same functions that their counterpart impervious weirs do. However, they have the advantage of being eco-friendly, more stable, and economical in low to medium-head cases. Dissolved oxygen is one of the major determinants for the assessment of the purity of water. The purpose of the present work is to illustrate the comparison of multiple linear regression (MLR), neural network (NN), neuro-fuzzy system (NFS), deep neural network (DNN), and reported empirical models for the prediction of gabion weir aeration performance efficiency (APE<sub>20</sub>) with experimental results which are collected from the laboratory test. The NFS with four shaped membership functions, NN, DNN, MLR, and existing empirical models, are generated with the same input parameters, and their potentials are assessed to statistical appraisal indices. The results show that the DNN with the highest value of R<sup>2</sup> (0.935) and NSE (0.934) and having the least errors in validating phase is the outperforming proposed model in the prediction of the APE<sub>20, </sub>which the NN model follows with R<sup>2</sup> (0.917) and NSE (0.917). However, except trapezoidal shaped NFS model with R<sup>2</sup> (0.873) and NSE (0.852) and MLR with R<sup>2</sup> (0.905) and NSE (0.897), the remaining models of NFS-based and empirical relations could not perform better in validating phase. The sensitivity performance test is too conducted to find the relative relevance of the input parameter on the results of the APE<sub>20</sub>, where discharge per unit width (q) is found to be the most significant parameter, followed by the drop height (H<sub>0</sub>).https://www.jsoftcivil.com/article_168919_3a0d5e158125a7de9349aa7bc6c69a1c.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401Evaluation of Applicability and Accuracy of Bus Travel Time Prediction in High and Low Frequency Bus Routes Using Tree-Based ML Techniques749716892210.22115/scce.2023.356348.1503ENSeyed Mohammad Hossein MoosaviResearch Fellow, Centre for Transportation Research, Faculty of Engineering, University of Malaya, 50603, Kuala Lumpur, MalaysiaMahdi AghaabbasiResearcher, Transportation Institute, Chulalongkorn University, Bangkok, 10330, ThailandChoon Wah YuenAssociate Professor, Department of Civil Engineering, Faculty of Engineering, University of Malaya, 50603, Kuala Lumpur, MalaysiaDanial Jahed ArmaghaniCentre of Tropical Geoengineering (GEOTROPIK), Institute of Smart Infrastructure and Innovative Engineering (ISIIC), Faculty of Civil Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia0000-0001-8171-6403Journal Article20220816Prediction of bus travel time is a key component of an intelligent transportation system and has many benefits for both service users and providers. Although there is a rich literature on bus travel prediction, some limitations can still be observed. First, high-frequency and low-frequency bus routes have different characterizations in both operational and passenger behavior aspects. Therefore, it is highly expected that bus travel time prediction methods for different frequencies must have different outputs. Second, in the era of big data, applications of machine learning (ML) techniques in travel time prediction have significantly increased. However, there is no single ML model introduced in the literature that is the most accurate in predicting bus travel, especially with regard to bus service frequency. Consequently, the main objective of this study is to determine the most applicable route construction approach and most accurate tree-based ML technique for predicting bus travel time on high- and low-frequency bus routes. The following tree-based ML techniques were adopted in this study: chi-square automatic interaction detection (CHAID), random forest (RF), and gradient-boosted tree (GBT). According to the results, CHAID was selected as the most accurate model for predicting travel time on high-frequency routes, while GBT showed the best performance for low-frequency service. CHIAD analysis identified distance between stops and terminal departure behavior as the most significant factors of travel time on high-frequency routes. Moreover, we introduced the "key stop-based" route construction method for the first time, which is an accurate, reliable, and applicable method.https://www.jsoftcivil.com/article_168922_8889297458018cde3b6387844f74ff43.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401Application of Meta-Heuristic Algorithms in Reservoir Supply Optimization, Case Study: Mahabad Dam in Iran9811416892310.22115/scce.2023.359560.1518ENSomayeh EmamiPh.D. in Hydraulic Structures, Department of Water Engineering, University of Tabriz, Tabriz, Iran0000-0001-8034-4652Omid JahandidehPh.D. Student in Water Engineering, Department of Water Engineering, Isfahan University of Technology, Isfahan, IranHossein YousefiAssociate Professor, Department of Renewable Energies and Environment, University of Tehran, Tehran, IranHojjat EmamiAssociate Professor, Department of Computer Engineering, University of Bonab, Bonab, IranMohammed AchiteProfessor, Laboratory of Water and Environment, Hassiba Benbouali University of Chlef, Chlef, AlgeriaJournal Article20220828In arid and semi-arid areas, optimization and strategic planning of water delivery through an optimal and intelligently designed reservoir supply system is a primary task for water resources management. In this regard, the election algorithm (EA) is presented to estimate the optimal storage capacity of the Mahabad dam located in northwest Iran. EA is an intelligent iterative population-based algorithm that has recently been introduced for dealing with different optimization purposes. The capability of EA to address issues of local minimums in the feature search space is employed to yield a globally optimal explanation of the present issue. The data used in this study comprise 7-year (2008-2015) evaporation, rainfall, reservoir storage, reservoir inflows, and outflow. The results obtained from the EA approach are approximated with the continuous genetic algorithm (CGA). Based on the estimated results in the testing phase, an average relatively error (5.65%) is attained in the last implementation of the algorithm. The high efficacy of EA relative to the benchmark models in terms of the NSE and RMSE, MAE is found to be approximately 0.037, 0.41, and 0.74, respectively, which are less than the values of these criteria for the CGA. These error measures, i.e. NSE, MAE, and RMSE, for the CGA were calculated to be 0.66, 0.56, and 0.042, respectively. The obtained accurate results show the high performance of the EA model in estimating the optimal reservoir capacity and its efficiency in water resources management.https://www.jsoftcivil.com/article_168923_634459e927a464b1ef18b585e73bbc74.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401Prediction of Compressive Strength of Corncob Ash Concrete for Environmental Sustainability Using an Artificial Neural Network: A Soft Computing Techniques11513716892010.22115/scce.2023.347663.1471ENR AbhishekResearch Scholar, Department of Civil Engineering, Visvesvaraya Technological University, Mysuru, IndiaB S Keerthi GowdaDepartment of Civil Engineering, Visvesvaraya Technological University, Mysuru, India0000-0002-7612-8487D C NaveenDepartment of Civil Engineering, Sri Venkateswara College of Engineering, Tirupati, IndiaK NareshDepartment of Aerospace Engineering, Khalifa University of Science and Technology, Abu Dhabi, U.A.E.Department of Material science and Engineering, University of California, Irvine-92697, United StatesR SundarakannanInstitute of Agricultural Engineering, Saveetha School of Engineering, SIMATS, Chennai, IndiaV ArumugaprabuDepartment of Mechanical Engineering, Kalasalingam Academy of Research and Education, Tamilnadu, IndiaAmogha VarshaResearch Scholar, Department of Civil Engineering, PESCE (VTU), Mandya, Karnataka, IndiaJournal Article20220617Agricultural waste materials are increasingly being used as partial replacements for cement in concrete. Several experimental studies are available to evaluate the mechanical properties of plastic waste reinforced concrete but there are limited evaluations on agricultural waste material. In this study, an attempt is made to investigate the compressive strength of Corn Cob Ash (CCA) concrete at different replacement levels by implementing an Artificial Neural Network (ANN). As the percentage of CCA increases, workability, density and compressive strength decreases, hence the developed ANN model consists of 3 input parameters (cement content, CCA content, and curing ages) in the input layer, 4 hidden neurons in the hidden layer and 3 output parameters (slump, density, and compressive strength) in the output layer. Training is done by adopting Levenberg-Marquardt back-propagation algorithm by considering 80% of experimental data with log-sigmoid activation function for both hidden and output layers. The developed model has a high correlation coefficient of 0.999 for both the training and testing data sets. It has low MSE and MAPE values of 2.2768x10<sup>-5</sup> and 1.25 for training data respectively and 3.0463x10<sup>-5</sup> and 1.37 for testing data respectively. Hence, it is concluded that the developed model predicts the output at an average rate of 98% accuracy. The predicted 2.5% replaced CCA concrete shows the best performance at all curing ages. Therefore, this percentage level is considered as an optimum replacement level which does not much affect the hardened properties of concrete.https://www.jsoftcivil.com/article_168920_2b51a9342cfebf2d6732620b68d76246.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230401An Artificial Intelligence Approach for Tunnel Construction Performance13815416892110.22115/scce.2023.352867.1492ENSoo KiemEngDepartment of Civil Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, MalaysiaBiao HeDepartment of Civil Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, Malaysia0000-0003-0906-7298Masoud MonjeziFaculty of Engineering, Tarbiat Modares University, Tehran, IranRamesh MurlidharBhatawdekarInstitute of Smart Infrastructure and Innovative Construction (ISiiC), Faculty of Civil Engineering, Universiti Teknologi Malaysia, Skudai 81310, Johor Bahru, Johor, MalaysiaDepartment of Mining Engineering, Indian Institute of Technology, Kharagpur 721302 West Bengal, IndiaJournal Article20220722As massive tunneling projects become more and more popular, predicting the performance of Tunnel Boring Machine (TBM) has been a problem that arose recently. A TBM is a modern piece of machinery that is specially assembled to excavate a tunnel more efficiently and safely. However, the performance of TBM is very difficult to estimate due to the different geological formations and geotechnical factors. This research aims to predict the penetration rate (PR) of TBM utilizing statistical and artificial intelligence methods that are based on the rock mass and rock material properties: rock mass rating, rock quality designation, and rock strength. To achieve this goal, we used two neural network-based models: artificial neural network (ANN) and group method of data handling (GMDH), to forecast the TBM PR values. Then, we compared the performance of these two models using the well-known indices and a ranking system and selected the model with the highest degree of performance. As a result, an ANN model with one hidden layer and seven neurons showed the highest level of capability in predicting TBM PR. Correlation coefficient values of 0.947 and 0.921 for the training and testing phases, respectively, were obtained for the best model in this study. Our research can serve as a fundamental study for future geotechnical engineers or researchers who would like to predict TBM performance with similar rock mass and material properties to this study.https://www.jsoftcivil.com/article_168921_1564ba0ef800e19b189e38025a8c7786.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28727220230322Comparison of DEEP-LSTM and MLP Models in Estimation of Evaporation Pan for Arid Regions15517516892410.22115/scce.2023.367948.1550ENAmirhossein SamiiAdvanced Robotics and Automated Systems (ARAS), Faculty of Electrical Engineering. K. N. Toosi University of Technology, Tehran, IranHojat KaramiDepartment of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, Iran0000-0002-2017-7204Hamidreza GhazvinianDepartment of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, Iran0000-0002-3531-9922Amirsaeed SafariPh.D. Student, Department of Mechanical Engineering, University of Kentucky, Lexington, KY, United StatesYashar DadrasajirlouDepartment of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, IranJournal Article20221031The importance of evaporation estimation in water resources and agricultural studies is undeniable. Evaporation pans (EP) are used as an indicator to determine the evaporation of lakes and reservoirs around the world due to the ease of interpreting its data. The purpose of this study is to evaluate the efficiency of the Long- Short Term Memory (LSTM) model to estimate evaporation from a pan and compare it with the Multilayer Perceptron (MLP) model in Semnan and Garmsar. For this purpose, daily meteorological data recorded between 2000 and 2018 (19 consecutive years) in Semnan and Garmsar synoptic stations were used. Minimum and maximum air temperature (Tmax, Tmin), wind speed (WS), sunshine hours (SH), air pressure (PA), relative humidity (RH) were selected as input data and evaporation data from the pan (EP) was considered as the output of the case. Also, in modeling both networks in the input section, 4 different scenarios were used. The two studied models were evaluated by the evaluation criteria of coefficient of determination (R<sup>2</sup>), root mean square error (RMSE) and mean absolute error (MAE). The results showed that among the studied scenarios, the fourth scenario (considering all input parameters) had the highest R<sup>2</sup> and the lowest RMSE and MAE. In general, the two models performed well in predicting the rate of evaporation. Also, in both stations, the LSTM model had more R<sup>2</sup> and less RMSE and MAE than the MLP model. The values of R<sup>2</sup>, RMSE and MAE for the best DEEP-LSTM model (LSTM4) for Semnan city were 0.9451, 1.8345 and 0.5437 and for Garmsar city 0.9204, 1.8323 and 1.3531 respectively.https://www.jsoftcivil.com/article_168924_e72329148fe08c78d8b5c0b703ea3227.pdf