Pouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Automatic Crack Detection Using Convolutional Neural Network11715327810.22115/scce.2022.325596.1397ENMihir PadsumbiyaB Tech, Department of Civil Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, IndiaVedant BrahmbhattB Tech, Department of Civil Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, IndiaSonal PThakkarAssociate Professor, Department of Civil Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, India0000-0002-7584-3198Journal Article20220119Manual inspection of cracks on concrete surfaces requires wholesome knowledge and depends entirely on the expertise and capabilities of the inspector. This study proposes the use of a simple Convolutional Neural Network (CNN) for automatic crack detection. A comparative approach for Automated Crack Detection is presented between Feed-Forward Fully Connected Neural Networks and CNN, focusing on the primary hyperparameters affecting the accuracy of both systems. An inclination towards CNN is concluded due to its simplicity and computational efficiency. For the purpose of this study, the input data is extracted from an open-source platform. In the second step, the images are pre-processed for obtaining low-pixel density images with the aim to get better accuracy at lower computer power. The CNN proposed uses Max Pooling and appropriate optimization techniques. The model is trained to detect and segregate cracked and non-cracked concrete surfaces through input images. The proposed model predicts and labels images with cracks on concrete surfaces and images with no cracks using pixel-level information. The final accuracy achieved is 97.8% by the proposed CNN model. The proposed model is a novel approach to detecting cracks on low pixel density images of concrete surfaces for its economic and processing efficiency and thus eliminates the need for high-cost digital image capturing devices. This study signifies and confirms the impact of Artificial Intelligence in the Civil Engineering field where using simple techniques like a simple four-layered Neural Network is capable of carrying automatic inspection of cracks which can be further developed for other applications.https://www.jsoftcivil.com/article_153278_2bf7e467d0f431a073b206e89cab394f.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Optimization of Concrete Beams Reinforced with GFRP Bars183815327710.22115/scce.2022.323501.1392ENThaer M SaeedAlrudainiLecturer, Department of Civil Engineering, Collage of Engineering, University of Basrah, Basrah, Iraq0000-0003-2033-9979Journal Article20220107Members with GFRP bars exhibit different behavior from those with steel bars due to the brittle and low elastic modulus of the GFRP bars. However, there are limited studies considering the optimum design of reinforced concrete members with GFRP bars compared with extensive studies for reinforced concrete members with steel bars. This study highlighted the performance of reinforced concrete beams with GFRP bars considering the optimum design. The behavioral flexural resistances involving compression, tension, and combined controls are incorporated in the formulation of the design constraints. Also, constraints including deflection serviceability limit states as well as construction requirements are considered. The optimization process is conducted using a genetic algorithm. Comparison with a conventional design is conducted by considering simply supported GFRP reinforced concrete beams in which the efficiency of the developed optimum design has been demonstrated. Analysis results show that tension-controlled sections govern the optimum design despite their brittle performance and highest reduction in strength. However, by increasing design restrictions including depth limits and deflection limits, tension-controlled sections became unable to provide sufficient strength and serviceability and the optimum design was shifted to a more ductile combined resisting control and then to compression-controlled sections.https://www.jsoftcivil.com/article_153277_11d2b73c9e1d50bd8b36e16f062b0299.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Parametric Assessment of Concrete Constituent Materials Using Machine Learning Techniques396215343510.22115/scce.2022.334664.1417ENYazan AlzubiCivil Engineering Department, Faculty of Engineering Technology Al-Balqa Applied University, 11134 Amman, Jordan0000-0002-8096-2992Jamal Al AdwanCivil Engineering Department, Faculty of Engineering Technology Al-Balqa Applied University, 11134 Amman, JordanAhmed KhatatbehCivil Engineering Department, Faculty of Engineering, Al Albayt University, 25113 Mafraq, JordanButhainah Al-kharabshehCivil Engineering Department, Faculty of Engineering, Al Albayt University, 25113 Mafraq, JordanJournal Article20220318Nowadays, technology has advanced, particularly in machine learning which is vital for minimizing the amount of human work required. Using machine learning approaches to estimate concrete properties has unquestionably triggered the interest of many researchers across the globe. Currently, an assessment method is widely adopted to calculate the impact of each input parameter on the output of a machine learning model. This paper evaluates the capability of various machine learning methodologies in conducting parametric assessments to understand the influence of each concrete constituent material on its compressive strength. It is accomplished by conducting a partial dependence analysis to quantify the effect of input features on the prediction results. As a part of the study, the effects of machine learning method selection for such analysis are also investigated by employing a concrete compressive strength algorithm developed using a decision tree, random forest, adaptive boosting, stochastic gradient boosting, and extreme gradient boosting. Additionally, the significance of the input features to the accuracy of the constructed estimation models is ranked through drop-out loss and MSE reduction. This investigation shows that the machine learning techniques could accurately predict the concrete's compressive strength with very high performance. Further, most analyzed algorithms yielded similar estimations regarding the strength of concrete constituent materials. In general, the study's results have shown that the drop-out loss and MSE reduction outputs were misleading, whereas the partial dependence plots provide a clear idea about the influence of the value of each feature on the prediction outcomes.https://www.jsoftcivil.com/article_153435_67bdde298e2b23f3c47b50f03a810431.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Combined Standardized Precipitation Index and ANFIS Approach for Predicting Rainfall in the Tropical Savanna Region637715548410.22115/scce.2022.333365.1412ENFenil R.GandhiPh.D. Student, Department of Civil Engineering, S. V. National Institute of Technology, Surat, IndiaJayantilal N.PatelProfessor (HAG), Department of Civil Engineering, S. V. National Institute of Technology, Surat, IndiaJournal Article20220310Climate change has affected many sectors in the world. Therefore, the Prediction of climatic factors is essential in case to achieve sustainability in human life. Rainfall prediction is also important as the agricultural sector depends on rainfall, and human life depends on agricultural products. This study presents the Standardized Precipitation Index (SPI) prediction using the adaptive neuro-fuzzy inference system (ANFIS). Various models (6 nos.) with different combinations of Rainfall and SPI values are prepared to predict the SPI index. Out of these six models, the M2 model (SPI3 SPI4 R4) performed best in the case of SPI 5. (RMSE value is 0.059, the R<sup>2</sup> value is 0.987, and the value of the coefficient of determination is 0.993. In the case of SPI 6, the M1 model (SPI5 SPI4 SPI3 R5) performed best (RMSE value is 0.042, the R<sup>2</sup> value is 0.992, and the value of the coefficient of determination is 0.996. The outcome may be helpful to the policymakers, scientists, researchers and government authorities in building a policy for sustainable water resources management in the region.https://www.jsoftcivil.com/article_155484_6214c91e498d7e4128d8c5e254e18c3b.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701An Applied Study on Integration Edges of Failure and TOPSIS to Educational Environment Safety Assessment: A Case Study7810015548110.22115/scce.2022.342342.1435ENMojtaba RezaiePh.D. Student, Department of Civil Engineering, Central Tehran Branch, Islamic Azad University, Tehran, IranNaser ShamskiaDepartment of Civil Engineering, Qazvin Branch, Islamic Azad University, Qazvin, 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 Article20220514A reliability and safety assessment for a bunch of listed schools can be challengeable for experts by the checklist system for safety reports. This paper aimed to respond to this challenge by merging the edges of failure 'EoF' and the technique for order of preference by similarity to ideal solution 'TOPSIS' to achieve an integrative approach for educational environment safety assessment. The qualitative assessment was implemented to detect safety faults in the case study area based on the results of the inspections. Then, the quantitative assessment was done to calculate critical points in edges of failure using the TOPSIS method. These points have been calculated for a bunch of listed schools that detected safety faults, and it also takes the form of the 'Jeopardous Pentagon' to calculate 'EoF Integration Mode'. It is an overall safety assessment to indicate performances region by region. This paper collected items of information about the twelve schools in Shahriar divided into three districts. Afterwards, a dangerous area is estimated to rank the existing options by the amount of achievement information. The first rank of the dangerous area between existence options is Shahriar two district. The most critical sides of the JP for first ranked reflect the human error 'RHE' and cultural governance 'CG' by values 0.989 and 0.989 for both intersection points. The combination of EoF and TOPSIS is recommended to apply for a physical and non-physical environment based on the safety checklist system.https://www.jsoftcivil.com/article_155481_e65d64b93cd5d1b630dc62ab2f25f9c1.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Reference Evapotranspiration Estimation Using ANN, LSSVM, and M5 Tree Models (Case Study: of Babolsar and Ramsar Regions, Iran)10111815835910.22115/scce.2022.342290.1434ENYashar DadrasajirlouFaculty of Civil Engineering, Semnan University, Semnan, IranHamidreza GhazvinianFaculty of Civil Engineering, Semnan University, Semnan, Iran0000-0002-3531-9922Salim HeddamProfessor, Faculty of Science, Agronomy Department, Hydraulics Division, Laboratory of Research in Biodiversity Interaction Ecosystem and Biotechnology, University 20 Août 1955, Skikda, Algeria0000-0002-8055-8463Mariam GanjiFaculty of Natural Resources and Environment, Islamic Azad University Science and Research Branch, Tehran, IranJournal Article20220514Evapotranspiration is a non-linear and complex phenomenon requiring different climatic variables for accurate estimation. In this study, the performance of several artificial intelligence models in estimating the amount of monthly reference evapotranspiration was investigated. Babolsar and Ramsa regions located in the north of Iran were selected as case study models proposed in this study: artificial neural network (ANN), least square support vector machines (LSSVM), and M5 tree models. The data used in this study was gathered between 2009 till 2019 (11 consecutive years). In the present study, 70% of the data were used for the training stage, and 30% of the data were reserved for testing the proposed models. Models' performances were evaluated using several evaluation criteria, i.e., the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error (MAE). The results for Babolsar and Ramsar stations showed that all three models have a relatively good performance in estimating the rate of reference evapotranspiration. However, the LSSVM model performed better than the other models. The R<sup>2</sup>, MAE, and RMSE for the LSSVM model in the test stage were 0.982, 0.366 mm, 0.425 mm, 0.937, 0.018 mm, and 0.350 mm for Babolsar and Ramsar stations, respectively.https://www.jsoftcivil.com/article_158359_1a94892da0a9801cbca3d04596bedc68.pdfPouyan PressJournal of Soft Computing in Civil Engineering2588-28726320220701Evaluating Adaptive Neuro-Fuzzy Inference System (ANFIS) To Assess Liquefaction Potential And Settlements Using CPT Test Data11913915823710.22115/scce.2022.345237.1456ENHimanshu KumarJangirMtech Student, Dr. B.R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, Punjab, IndiaRupali SatavalekarAssistant Professor, Dr. B.R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, Punjab, IndiaJournal Article20220601Liquefaction occurs when saturated, non-cohesive soil loses strength. This phenomenon occurs as the water pressure in the pores rises and the effective stress drops because of dynamic loading. Liquefaction potential is a ratio for the factor of safety used to figure out if the soil can be liquefied, and liquefaction-induced settlements happen when the ground loses its ability to support construction due to liquefaction. Traditionally, empirical and semi-empirical methods have been used to predict liquefaction potential and settlements that are based on historical data. In this study, MATLAB's Fuzzy Tool Adaptive Neuro-Fuzzy Inference System (ANFIS) (sub-clustering) was used to predict liquefaction potential and liquefaction-induced settlements. Using Cone Penetration Test (CPT) data, two ANFIS models were made: one to predict liquefaction potential (LP-ANFIS) and the other to predict liquefaction-induced settlements (LIS-ANFIS). The RMSE correlation for the LP-ANFIS model (input parameters: Depth, Cone penetration, Sleeve Resistance, and Effective stress; output parameters: Liquefaction Potential) and the LIS-ANFIS model (input parameters: Depth, Cone penetration, Sleeve Resistance, and Effective stress; output parameters: Settlements) was 0.0140764 and 0.00393882 respectively. The Coefficient of Determination (R2) for both the models was 0.9892 and 0.9997 respectively. Using the ANFIS 3D-Surface Diagrams were plotted to show the correlation between the CPT test parameters, the liquefaction potential, and the liquefaction-induced settlements. The ANFIS model results displayed that the considered soft computing techniques have good capabilities to determine liquefaction potential and liquefaction-induced settlements using CPT data.https://www.jsoftcivil.com/article_158237_8c5e7e119e44a5eda3e51ebda7574bd7.pdf