• Steel and Composite Structures
• /
• 제39권4호
• /
• pp.471-491
• /
• 2021

In this study, we estimate the ultimate load of rectangular concrete-filled steel tubes (CFST) by developing a novel hybrid predictive model (ANN-BCMO) which is a combination of balancing composite motion optimization (BCMO) - a very new optimization technique and artificial neural network (ANN). For this aim, an experimental database consisting of 422 datasets is used for the development and validation of the ANN-BCMO model. Variables in the database are related with the geometrical characteristics of the structural members, and the mechanical properties of the constituent materials (steel and concrete). Validation of the hybrid ANN-BCMO model is carried out by applying standard statistical criteria such as root mean square error (RMSE), coefficient of determination (R²), and mean absolute error (MAE). In addition, the selection of appropriate values for parameters of the hybrid ANN-BCMO is conducted and its robustness is evaluated and compared with the conventional ANN techniques. The results reveal that the new hybrid ANN-BCMO model is a promising tool for prediction of the ultimate load of rectangular CFST, and prove the effective role of BCMO as a powerful algorithm in optimizing and improving the capability of the ANN predictor.

• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.1-10
• /
• 2021

Analysis and Tracking of bug reports is a challenging field in software repositories mining. It is one of the fundamental ways to explores a large amount of data acquired from defect tracking systems to discover patterns and valuable knowledge about the process of bug triaging. Furthermore, bug data is publically accessible and available of the following systems, such as Bugzilla and JIRA. Moreover, with robust machine learning (ML) techniques, it is quite possible to process and analyze a massive amount of data for extracting underlying patterns, knowledge, and insights. Therefore, it is an interesting area to propose innovative and robust solutions to analyze and track bug reports originating from different open source projects, including Mozilla and Eclipse. This research study presents an ML-based classification model to analyze and track bug defects for enhancing software engineering management (SEM) processes. In this work, Artificial Neural Network (ANN) and Naive Bayesian (NB) classifiers are implemented using open-source bug datasets, such as Mozilla and Eclipse. Furthermore, different evaluation measures are employed to analyze and evaluate the experimental results. Moreover, a comparative analysis is given to compare the experimental results of ANN with NB. The experimental results indicate that the ANN achieved high accuracy compared to the NB. The proposed research study will enhance SEM processes and contribute to the body of knowledge of the data mining field.

• Computers and Concrete
• /
• 제24권4호
• /
• pp.329-345
• /
• 2019

Despite the extensive use of mortar materials in constructions over the last decades, there is not yet a robust quantitative method, available in the literature, which can reliably predict mortar strength based on its mix components. This limitation is due to the highly nonlinear relation between the mortar's compressive strength and the mixed components. In this paper, the application of artificial neural networks for predicting the compressive strength of mortars has been investigated. Specifically, surrogate models (such as artificial neural network models) have been used for the prediction of the compressive strength of mortars (based on experimental data available in the literature). Furthermore, compressive strength maps are presented for the first time, aiming to facilitate mortar mix design. The comparison of the derived results with the experimental findings demonstrates the ability of artificial neural networks to approximate the compressive strength of mortars in a reliable and robust manner.

• Advances in nano research
• /
• 제11권6호
• /
• pp.595-606
• /
• 2021

This paper conducted mainly for forecasting the behavior of the shear connectors in steel-concrete composite beams based on the different factors. The main goal was to analyze the influence of variable parameters on the shear strength of C-shaped and L-shaped angle shear connectors. The method of ANFIS (adaptive neuro fuzzy inference system) was applied to the data in order to select the most influential factors for the mentioned shear strength forecasting. Five inputs are considered: height, length, thickness of shear connectors together with concrete strength and respective slip of the shear connectors after testing. The ANFIS process for variable selection was also implemented in order to detect the predominant factors affecting the forecasting of the shear strength of C-shaped and L-shaped angle shear connectors. The results show that the forecasting methodology developed in this research is useful for enhancing the multiple performances characterizing in the shear strength prediction of C and L shaped angle shear connectors analyzing.

• Computers and Concrete
• /
• 제26권4호
• /
• pp.327-342
• /
• 2020

The objective of this study is to manufacture environmentally-friendly synthetic lightweight aggregates that may be used in the structural lightweight concrete production. The cold-bonding pelletization process has been used in the agglomeration of the pozzolanic materials to achieve these synthetic lightweight aggregates. In this context, it was aimed to recycle the waste fly ash by employing it in the manufacturing process as the major cementitious component. According to the well-known facts reported in the literature, it is stated that the main disadvantage of the synthetic lightweight aggregate produced by applying the cold-bonding pelletization technique to the pozzolanic materials is that it has a lower strength in comparison with the natural aggregate. Therefore, in this study, the metakaolin made of high purity kaolin and calcined kaolin obtained from impure kaolin have been employed at particular contents in the synthetic lightweight aggregate manufacturing as a cementitious material to enhance the particle crushing strength. Additionally, to propose a curing condition for practical attempts, different curing conditions were designated and their influences on the characteristics of the synthetic lightweight aggregates were investigated. Three substantial features of the aggregates, specific gravity, water absorption capacity, and particle crushing strength, were measured at the end of 28-day adopted curing conditions. Observed that the incorporation of thermally treated kaolin significantly influenced the crushing strength and water absorption of the aggregates. The statistical evaluation indicated that the investigated properties of the synthetic lightweight aggregate were affected by the thermally treated kaolin content more than the kaoline type and curing regime. Utilizing the thermally treated kaolin in the synthetic aggregate manufacturing lead to a more than 40% increase in the crushing strength of the pellets in all curing regimes. Moreover, two numerical formulations having high estimation capacity have been developed to predict the crushing strength of such types of aggregates by using soft-computing techniques: gene expression programming and artificial neural networks. The R-squared values, indicating the estimation performance of the models, of approximately 0.97 and 0.98 were achieved for the numerical formulations generated by using gene expression programming and artificial neural networks techniques, respectively.

• 한국전산구조공학회논문집
• /
• 제19권2호
• /
• pp.125-138
• /
• 2006

교량의 손상추정을 위한 구조계 규명기법은 신호취득시스템 및 정보처리기술의 발전과 함께 최근에 많은 연구개발이 이루어지고 있다. 신경망기법이나 유전자 알고리즘과 같은 소프트컴퓨팅 기법은 뛰어난 패턴인식성능 때문에 손상추정 문제에 활발히 활용되고 있다. 본 연구에서는 모드계수를 활용한 신경망기법기반 손상추정을 수행하였으며, 신경망을 훈련시키기 위한 훈련패턴을 생성하는 해석모델에서의 불확실성을 효과적으로 고려할 수 있는 방법을 제시하였다. 해석모델의 불확실성 대하여 민감하지 않은 입력자료인 손상 전 후의 모드형상의 차 또는 모드형상의 비를 신경망의 입력자료로 활용하였다. 단 순보와 다주형교량에 대한 수치예제를 통하여 본 연구에서 제시한 기법의 타당성 및 적용성을 검증하였다.

• Advances in environmental research
• /
• 제6권2호
• /
• pp.83-94
• /
• 2017

Air quality planning and management requires accurate and consistent records of the air quality parameters. Limited number of monitoring stations and inconsistent measurements of the air quality parameters is a very serious problem in many parts of India. It becomes difficult for the authorities to plan proactive measures with such a limited data. Estimation models can be developed using soft computing techniques considering the physics behind pollution dispersion as they can work very well with limited data. They are more realistic and can present the complete picture about the air quality. In the present case study spatio-temporal models using Linear Genetic Programming (LGP) have been developed for estimation of air quality parameters. The air quality data from four monitoring stations of an Indian city has been used and LGP models have been developed to estimate pollutant concentration of the fifth station. Three types of models are developed. In the first type, models are developed considering only the pollutant concentrations at the neighboring stations without considering the effect of distance between the stations as well the significance of the prevailing wind direction. Second type of models are distance based models based on the hypothesis that there will be atmospheric interactions between the two stations under consideration and the effect increases with decrease in the distance between the two. In third type the effect of the prevailing wind direction is also considered in choosing the input stations in wind and distance based models. Models are evaluated using Band Error and it was observed that majority of the errors are in +/-1 band.

• 천문학회지
• /
• 제24권2호
• /
• pp.129-149
• /
• 1991

An attempt has been made to examine the characteristics of acoustic and MHD waves generated in stellar convection zones($4000\;K\;{\leq}\;T_{eff}\;{\leq}\;7000\;K$, $3\;{\leq}\;\log\;g\;{\leq}\;4.5$). With the use of wave generation theories formulated for acoustic waves by Stein (1967), for MHD body waves by Musielak and Rosner (1987, 1988) and for MHD tube waves by Musielak et al.(l989a, 1989b), the energy fluxes are calculated and their dependence on effective temperature, surface gravity and megnetic field strength are analyzed by optimization techniques. In computing magneto-convection models, the effect of magnetic fields on the efficiency of convection has been taking into account by extrapolating it from Yun's sunspot models(1968; 1970). Our study shows that acoustic wave fluxes are dominant in F and G stars, while the MHD waves dominant in K and M stars, and that the MHD wave fluxes vary as $T_{eff}^4{\sim}T_{eff}^7$ in contrast to the acoustic fluxes, as $T_{eff}^{10}$. The gravity dependence, on the other hand, is found to be relatively weak; the acoustic wave fluxes ${\varpropto}\;g^{-0.5}$, the longitudinal tube wave fluxes ${\varpropto}\;g^{0.3}$ and the transverse tube wave fluxes ${\varpropto}\;g^{0.3}$. In the case of the MHD body waves their gravity dependence is found to be nearly negligible. Finally we assesed the computed energy fluxes by comparing them with the observed fluxes $F_{ob}$ of CIV(${\lambda}1549$) lines and soft X-rays for selected main sequence stars. When we scaled the corrected wave fluxes down to $F_{ob}$, it is found that these slopes are almost in line with each other.

• Steel and Composite Structures
• /
• 제41권5호
• /
• pp.761-773
• /
• 2021

This study presents a 3D non-linear finite element (FE) assessment of dynamic soil-structure interaction (SSI). The numerical investigation has been performed on the time domain through a Finite Element (FE) system, while considering the nonlinear behavior of soil and the multi-directional nature of genuine seismic events. Later, the FE outcomes are analyzed to the recorded in-situ free-field and structural movements, emphasizing the numerical model's great result in duplicating the observed response. In this work, the soil response is simulated using an isotropic hardening elastic-plastic hysteretic model utilizing HSsmall. It is feasible to define the non-linear cycle response from small to large strain amplitudes through this model as well as for the shift in beginning stiffness with depth that happens during cyclic loading. One of the most difficult and unexpected tasks in resolving soil-structure interaction concerns is picking an appropriate ground motion predicted across an earthquake or assessing the geometrical abnormalities in the soil waves. Furthermore, an artificial neural network (ANN) has been utilized to properly forecast the non-linear behavior of soil and its multi-directional character, which demonstrated the accuracy of the ANN based on the RMSE and R² values. The total result of this research demonstrates that complicated dynamic soil-structure interaction processes may be addressed directly by passing the significant simplifications of well-established substructure techniques.

• Steel and Composite Structures
• /
• 제45권2호
• /
• pp.205-218
• /
• 2022

Proper calculation of splitting tensile strength (STS) of concrete has been a crucial task, due to the wide use of concrete in the construction sector. Following many recent studies that have proposed various predictive models for this aim, this study suggests and tests the functionality of three hybrid models in predicting the STS from the characteristics of the mixture components including cement compressive strength, cement tensile strength, curing age, the maximum size of the crushed stone, stone powder content, sand fine modulus, water to binder ratio, and the ratio of sand. A multi-layer perceptron (MLP) neural network incorporates invasive weed optimization (IWO), cuttlefish optimization algorithm (CFOA), and electrostatic discharge algorithm (ESDA) which are among the newest optimization techniques. A dataset from the earlier literature is used for exploring and extrapolating the STS behavior. The results acquired from several accuracy criteria demonstrated a nice learning capability for all three hybrid models viz. IWO-MLP, CFOA-MLP, and ESDA-MLP. Also in the prediction phase, the prediction products were in a promising agreement (above 88%) with experimental results. However, a comparative look revealed the ESDA-MLP as the most accurate predictor. Considering mean absolute percentage error (MAPE) index, the error of ESDA-MLP was 9.05%, while the corresponding value for IWO-MLP and CFOA-MLP was 9.17 and 13.97%, respectively. Since the combination of MLP and ESDA can be an effective tool for optimizing the concrete mixture toward a desirable STS, the last part of this study is dedicated to extracting a predictive formula from this model.