Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001A New Enhanced Hybrid Grey Wolf Optimizer (GWO) Combined with Elephant Herding Optimization (EHO) Algorithm for Engineering Optimization14215548210.22115/scce.2022.342360.1436ENZeynab HoseiniDepartment of Engineering, Ale Taha Institute of Higher Education, 14888-36164, Tehran, IranHesam VaraeeDepartment of Engineering, Ale Taha Institute of Higher Education, 14888-36164, Tehran, Iran0000-0001-5967-1077Mahdi RafieizonoozSchool of Civil and Environmental Engineering, Yonsei University, Yonsei-ro 50, Seodaemun-gu, Seoul 03722, South KoreaJang-Ho Jay KimSchool of Civil and Environmental Engineering, Yonsei University, Yonsei-ro 50, Seodaemun-gu, Seoul 03722, South KoreaJournal Article20220514Although the exploitation of GWO advances sharply, it has limitations for continuous implementing exploration. On the other hand, the EHO algorithm easily has shown its capability to prevent local optima. For hybridization and by considering the advantages of GWO and the abilities of EHO, it would be impressive to combine these two algorithms. In this respect, the exploitation and exploration performances and the convergence speed of the GWO algorithm are improved by combining it with the EHO algorithm. Therefore, this paper proposes a new hybrid Grey Wolf Optimizer (GWO) combined with Elephant Herding Optimization (EHO) algorithm. Twenty-three benchmark mathematical optimization challenges and six constrained engineering challenges are used to validate the performance of the suggested GWOEHO compared to both the original GWO and EHO algorithms and some other well-known optimization algorithms. Wilcoxon's rank-sum test outcomes revealed that GWOEHO outperforms others in most function minimization. The results also proved that the convergence speed of GWOEHO is faster than the original algorithms.https://www.jsoftcivil.com/article_155482_fd3f2f423a612de44da0e60e9c28bfc1.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001Soft Computing Based Prediction of Unconfined Compressive Strength of Fly Ash Stabilised Organic Clay435815823510.22115/scce.2022.339698.1429ENTammineni GnananandaraoAssistant Professor, Department of Civil Engineering, Aditya College of Engineering and Technology, Surampalem, Andhra Pradesh, IndiaJawaharlal Nehru Technological University Kakinada, Kakinada, East Godavari District, India0000-0002-3332-8083Rakesh KumarDuttaProfessor, National Institute of Technology, Hamirpur, Himachal Pradesh, Pin No: 177005, India0000-0002-4611-9950Vishwas NandakishorKhatriAssistant Professor, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, Pin No: 826004, IndiaMummidivarapu SatishKumarAssistant Professor, Department of Civil Engineering, Aditya College of Engineering and Technology, Surampalem, Andhra Pradesh, IndiaJawaharlal Nehru Technological University Kakinada, Kakinada, East Godavari District, IndiaJournal Article20220427The current study uses machine learning techniques such as Random Forest Regression (RFR), Artificial Neural Networks (ANN), Support Vector Machines Ploy kernel (SVMP), Support Vector Machines Radial Basis Function Kernel (SVMRBK), and M5P model tree (M5P) to estimate unconfined compressive strength of organic clay stabilized with fly ash. The unconfined compressive strength of stabilized clay was computed by considering the different input variables namely i) the ratio of Cao to Sio<sub>2</sub>, ii) organic content (OC), iii) fly ash (FA<sub>per</sub>) content, iv) the unconfined compressive strength of organic clay without fly ash (UCS<sub>0</sub>) and v) the pH of soil-fly ash (pH<sub>mix</sub>). By comparing the performance measure parameters, each model performance is evaluated. The result of present study can conclude the random forest regression (RFR) model predicts the unconfined compressive strength of the organic clay stabilized with fly ash with least error followed by Support Vector Machines Radial Basis Function Kernel (SVMRBK), Support Vector Machines Ploy kernel (SVMP), Artificial Neural Networks (ANN) and M5P model tree (M5P). When compared to the semi-empirical model available in the literature, all of the model predictions given in this study perform well. Finally, the RFR and SVMRBK sensitivity analyses revealed that the CaO/SiO<sub>2</sub> ratio was the most relevant parameter in the prediction of unconfined compressive strength.https://www.jsoftcivil.com/article_158235_ac5ba3299fe4e2c30b6196e191edfe6b.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001Investigating the Correlation between the Parameters of Ground Motion Intensity Measures for Iran's Data598215823410.22115/scce.2022.344135.1450ENMansoureh RezaeemaneshPh.D. Student, School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran0000-0002-0968-0829Mohammadreza MashayekhiAssistant Professor, Department of Civil Engineering, K.N. Toosi University of Technology, Tehran, Iran0000-0002-2697-6795Journal Article20220525This paper presents a statistical correlation analysis of peak ground acceleration to peak ground velocity ratio (A/V) and other ground motion intensity measures (IMs) for Iran’s data. A/V is an important parameter that can significantly affect nonlinear structural responses. Findings from this study provide beneficial insights into selecting suitable parameters for characterizing earthquake ground motions. The studied database included 2053 strong ground motion records with the moment magnitude from 4.5 to 7.8 MW, rupture distance from 1 to 600 km, and average shear wave velocity from 155 to 1594 m/s. Correlation coefficients between A/V and several IMs were obtained for near-field and far-field records at three A/V levels, low A/V, middle A/V, and high A/V. Regression analyses for predicting A/V from the IMs were also conducted for near-field and far-field records. The results showed that the mean period (Tm) has the highest correlation with A/V at all A/V levels and for both far-field and near-field earthquakes compared to the other IMs. Therefore, this parameter can be employed for record selection as a frequency content-based parameter. Finally, current results showed that the accuracy of the Artificial Neural Network (ANN) models are more than the regression models for predicting A/V.https://www.jsoftcivil.com/article_158234_bc6e339bfc8ce8a25183e25bd77b8323.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001Prediction of Safe Bearing Capacity with Adaptive Neuro-Fuzzy Inference System of Fine-Grained Soils839415548310.22115/scce.2022.345362.1457ENVaddi Phani KumarResearch Scholar, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh, India0000-0002-7583-374XCh SudharaniProfessor, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh, IndiaJournal Article20220603A lot of fieldwork is required to assess the safe bearing capacity (SBC) of fine-grained soil using IS Code, along with performing shear parameters to determine angle of internal friction and cohesion. Standard penetration tests are conducted in order to obtain N-value of soil, and evaluating atterberg limits and dry soil density. Here, it is proposed that Adaptive Neuro-Fuzzy Inference System(ANFIS) is adopted to predict fine-grained soil's safe bearing capacity. For this, input parameters considered for ANFIS system are depth of foundation, dry density, liquid limit, plasticity index, Percentage fine fraction, width/Length ratio, and N-Value. A wide range of safe bearing capacity data from various site locations was investigated and trained on. Four different models were developed with variations in membership function for each input, all the models are used with a gaussbell type of membership function. Among the four, the third model is predicting the nearest value with an R<sup>2</sup> of 0.9738. Based on the conclusion the ANFIS model is the most reliable technique for assessing the SBC of soils. Investigation of soil properties and estimation of safe bearing capacity will be having more difficulty with respect to skilled person to investigate and time required is also more as dimension of the footing changes SBC also varies. So, to overcome this type of problems my model will give you a best suitable and reliable SBC.https://www.jsoftcivil.com/article_155483_e2dcaa2b0d9ff3d15dea5343158f7346.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001Optimization of Invasive Weed for Optimal Dimensions of Concrete Gravity Dams9511115849610.22115/scce.2022.340697.1432ENVahed GhiasiAssistant Professor of Geotechnical Engineering, Department of Civil Engineering, Faculty of Civil and Architecture Engineering, Malayer University, Iran0000-0002-4192-8097Morteza Alborzi MoghadamMaster of Civil Engineering, Khoramshahr Marine Science and Technology University, Khorramshahr, IranMehdi KoushkiPh.D. Student of Civil Engineering, Geotechnical, Razi University, Kermanshah, IranJournal Article20220505Dam construction projects among the most extensive and most expensive projects are considered. It is always appropriate and optimal for such concrete structures to reduce the volume of concrete and consequently reduce construction costs is essential. In this study, invasive weed optimization software GNU octave, dimensions of concrete gravity dam Koyna located in India optimized stability constraints. For this purpose, a cross-section with a length unit consists of eight geometric parameters as input variables, and other geometric parameters were defined using these variables. The result showed that invasive weeds are well-optimized dimensions of the dam as the volume of concrete in the construction of the dam at the current level measures 3633 cubic meters that optimal dropped 3353 cubic meters, which is a mean of 7.7% of the value of the objective function (the volume of concrete in dams) is reduced. This amount of concrete decreased the construction of the dam, saving the cost and is more economical.https://www.jsoftcivil.com/article_158496_4fc7e68363d414ba7bc1bb17290bd03b.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001New Method of Getting Position of Instrument Station Based on Two Known Points and The Law of Cosines11212915882410.22115/scce.2022.348159.1472ENTotok SulistyoLecturer, Department of Civil Engineering, Politeknik Negeri Balikpapan, Indonesia0000-0001-7612-5959Desak Made RistiaKartikaLecturer, Department of Civil Engineering, Politeknik Negeri Balikpapan, Indonesia0000-0002-3204-5575Journal Article20220621Getting the position of the instrument in starting traverse and staking out surveying can be very helpful for the surveyors. The most common method is the placement of the instrument on the known point, then those surveys are possible to be accomplished. This research is aimed to develop a new method and procedure to get x, y, and z values of the unknown position of the instrument based on two known points and the law of cosines. The method of this research is the implementation of the law of cosines and Euclidean Norm in solving the problem of getting the coordinate of instrument position. The innovation of this procedure has not been used yet in survey practice and has not been accommodated in electronic distance measuring (EDM) based survey instruments such as Total Station. The experiment of measurement to test the procedure is conducted virtually using the total station of SimusurveyX 1.0.7. The total measurement of ten random triangles is 60 times, where each triangle is measured 6 times. The result of measurement is close to the ground truth, and it can be repeatable. The implication of this research is enabling the surveyors to shortcut traverse measurement by locating Total Station in the first unknown point of the traverse.https://www.jsoftcivil.com/article_158824_447d05d7b1d9bb90e7f5f2f89c9e80be.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726420221001Application of Machine Learning Technique in Predicting the Bearing Capacity of Rectangular Footing on Layered Sand under Inclined Loading13015215823610.22115/scce.2022.343236.1445ENVishal PanwarDepartment of Civil Engineering, NIT Hamirpur, Himachal Pradesh, India0000-0002-4942-1995Rakesh KumarDuttaDepartment of Civil Engineering, NIT Hamirpur, Himachal Pradesh, India0000-0002-4611-9950Journal Article20220520The aim of the present study is to apply machine learning technique to predict the ultimate bearing capacity of the rectangular footing on layered sand under inclined loading. For this purpose, a total 5400 data based on the finite element method for the rectangular footing on layered sand under inclined loading were collected from the literature to develop the machine learning model. The input variables chosen were the thickness ratio (0.00 to 2.00) of the upper dense sand layer, embedment ratio (0 to 2), the friction angle of upper dense (41<sup>0 </sup>to 46<sup>0</sup>) sand and lower loose (31<sup>0</sup> to 36<sup>0</sup>) sand layer and inclination (0<sup>0</sup> to 45<sup>0</sup>) of the applied load with respect to vertical. The output is the ultimate bearing capacity. Further, the impact of the individual variable on the bearing capacity was also assessed by conducting sensitivity analysis. The results reveal that, the load inclination is the major variable affecting the bearing capacity at embedment ratio 0, 1 and 2. Finally, the performance of the developed machine learning model was assessed using six assessing statistical parameters. The results reveal that the developed model was performing satisfactorily for the prediction of the ultimate bearing capacity of the rectangular footing on layered sand under inclined loading.https://www.jsoftcivil.com/article_158236_c36963bdb7592e6ad7ae24e3a37bba5f.pdf