MCBÜ Açıkerişim Sistemi :: Browsing by Author "Çiftçioğlu A.Ö."

Browsing by Author "Çiftçioğlu A.Ö."

Now showing 1 - 13 of 13

Wind load design of hangar-type closed steel structures with different roof pitches using abaqus CAE software
(UIKTEN - Association for Information Communication Technology Education and Science, 2017) Çiftçioğlu A.Ö.; Yildizel S.A.; Yildirim M.S.; Doğan E.
Structures convert the kinetic energy available in the air into potential energy which is in the form of pressure and suction forces reducing or fully stopping its motion. The potential impact of the wind depends on the geometric properties and pertinacity of a building, the angle of the wind flow, its strength and velocity. Design gains importance for tall buildings against the impact of the resonance along with the force based on pressure. Relevant calculations are made in Turkey based on the TS 498 Wind Load Velocity Criterion and this standard is currently being updated. This study develops the wind load design of hangar-type closed steel structures with different roof pitches using Abaqus CAE software. © 2017 Aybike Özyüksel Çiftçioğlu et al.
A Study on the Performance of Grey Wolf Optimizer
(Springer Science and Business Media Deutschland GmbH, 2021) Çiftçioğlu A.Ö.
In recent years there is an enormous increase in the emergence of non-deterministic search methods. The effective way of animals in problem-solving (like discovering the shortest path to the food source) has been examined by scientists and swarm intelligence has become a research field that imitates the behaviour of animals in swarm. The moth-flame optimization (MFO) algorithm, salp swarm algorithm (SSA), firefly algorithm (FFA), bat (BAT) algorithm, cuckoo search (CS) algorithm, genetic algorithm (GA), and grey wolf optimizer (GWO) are some of the swarm intelligence based non-deterministic methods. In the present study, the seven methods above are investigated separately. Five mathematical functions are resolved individually by these seven methods. Each algorithm is run 30 times in each benchmark function. The performances of these optimization methods are evaluated and compared within each function individually. Performances of algorithms over convergence are compared by plotting convergence rate graph and boxplots of methods for each function. Considering most of the functions, GWO is observed to be stronger than other algorithms. © 2021, Springer Nature Switzerland AG.
A comparison performance analysis of eight meta-heuristic algorithms for optimal design of truss structures with static constraints
(Elsevier Inc., 2023) Khodadadi N.; Çiftçioğlu A.Ö.; Mirjalili S.; Nanni A.
Metaheuristics have been successfully used for solving complex structural optimization problems. Many algorithms are proposed for truss structure size and shape optimization under some constraints. This study considers eight population-based meta-heuristic methods: African Vultures Optimization Algorithm (AVOA), Flow Direction Algorithm (FDA), Arithmetic Optimization Algorithm (AOA), Generalized Normal Distribution Optimization (GNDO), Stochastic Paint Optimizer (SPO), Chaos Game Optimizer (CGO), Crystal Structure Algorithm (CRY) and Material Generation Algorithm (MGO). These meta-heuristics methods are used to optimize the size of three aluminum truss structures. Optimization aims to reduce the weight of the truss members while meeting a set of displacement and stress constraints. The performance of these methods is assessed by solving and optimizing three well-known truss structure benchmarks under some constraints. The results show that the Stochastic Paint Optimizer (SPO) outperforms the other algorithms in terms of accuracy and convergence rate. © 2023
Causal discovery and inference for evaluating fire resistance of structural members through causal learning and domain knowledge
(John Wiley and Sons Inc, 2023) Naser M.Z.; Çiftçioğlu A.Ö.
Experiments remain the gold standard to establish an understanding of fire-related phenomena. A primary goal in designing tests is to uncover the data generating process (i.e., the how and why the observations we see come to be); or simply what causes such observations. Uncovering such a process not only advances our knowledge but also provides us with the capability to be able to predict phenomena accurately. This paper presents an approach that leverages causal discovery and causal inference to evaluate the fire resistance of structural members. In this approach, causal discovery algorithms are adopted to uncover the causal structure between key variables pertaining to the fire resistance of reinforced concrete columns. Then, companion inference algorithms are applied to infer (estimate) the influence of each variable on the fire resistance given a specific intervention. Finally, this study ends by contrasting the algorithmic causal discovery with that obtained from domain knowledge and traditional machine learning. Our findings clearly show the potential and merit of adopting causality into our domain. © 2023 The Authors. Structural Concrete published by John Wiley & Sons Ltd on behalf of International Federation for Structural Concrete.
Revisiting Forgotten Fire Tests: Causal Inference and Counterfactuals for Learning Idealized Fire-Induced Response of RC Columns
(Springer, 2023) Naser M.Z.; Çiftçioğlu A.Ö.
The expensive nature and unique facilities required for fire testing make it difficult to conduct comprehensive experimental campaigns. As such, engineers can often afford to test a small number of specimens. This complicates attaining a proper inference, especially when addressing questions in the form of what would have been the fire response of a particular specimen had it been twice as large? Or had it been made from a different material grade? In hindsight, answering causal and hypothetical (counterfactual) questions goes beyond the capacity of statistical and machine learning methods which were built to address observational data. To overcome the above challenges, this paper presents a causal approach to answering such questions. In this approach, principles of causal inference are adopted to reconstruct the deformation-time history of reinforced concrete (RC) columns and propose an idealized fire response for these columns. The findings of this study indicate the significant influence of the loading level, aggregate type, and longitudinal steel ratio on the deformation history of fire-exposed RC columns. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Fire Resistance Analysis Through Synthetic Fire Tests
(Springer Science and Business Media Deutschland GmbH, 2023) Çiftçioğlu A.Ö.; Naser M.Z.
Fire resistance analysis is a complex procedure. In this pursuit, engineers design experiments. However, fire tests are expensive and complex and require specialized equipment that is not accessible to many engineers. This further constrains the ability to test and advance fire research. In order to overcome the above challenges, this paper adopts novel machine learning to generate synthetic fire test data via Generative Adversarial Networks (GANs) from real fire tests to expand our knowledge database. Thus, with the addition of new tests, engineers will have access to a much larger pool of data that can help us to better analyze and design structures for fire. In addition, the availability of more data allows us to seriously integrate machine learning into the fire domain. Thus, this paper presents a new approach to expanding fire test data and applying regression and classification machine learning to predict the fire response of reinforced concrete columns. GANs provide an efficient way to generate synthetic data from real fire tests. Moreover, new data additions contribute to improving predictions of classification-based machine learning in comparison with regression-based machine learning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
The Application of Machine Learning on Concrete Samples
(Springer Science and Business Media Deutschland GmbH, 2023) Çiftçioğlu A.Ö.
Machine learning is a branch of artificial intelligence that helps computers to learn from data and make predictions based on patterns identified in big data. The purpose of this study is to explore the applicability of machine learning models in classifying the compressive strength of concrete specimens with different types of ingredients. Despite the investigations in the literature about estimating concrete density, there is no relevant study on categorizing compressive strength. To address this gap, in this study, three machine learning classification algorithms (Decision Tree, Naive Bayes Classifier, and K-Nearest Neighbors) are employed to classify concrete samples. The performance of each algorithm is evaluated and compared. The results show that the Decision Tree classifier provides the best performance with an average precision and recall of 99%, f1-score of 0.99, and accuracy of 99%. Moreover, the study provides insights into the application of ML algorithms in a real-world dataset. This study demonstrates that machine learning is a powerful tool that can be used to improve the accuracy of concrete strength classification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Unsupervised Machine Learning for Fire Resistance Analysis
(Springer Science and Business Media Deutschland GmbH, 2023) Çiftçioğlu A.Ö.; Naser M.Z.
Due to its inert nature, concrete has good fire resistance properties. As such, concrete has often been favored for construction – especially where fire hazard is expected. However, this does not mean that reinforced concrete cannot catch fire. It can still be affected by heat and, if exposed to high temperatures, can eventually break down. Therefore, the fire resistance of the reinforced concrete (RC) columns is a critical concern. There are many ways for assessing the fire resistance of structures, but it is difficult to quantify the fire resistance in quantitative terms. The purpose of this work is to investigate the use of unsupervised machine learning by means of clustering to examine the fire resistance of RC columns. A database of over 144 RC columns subjected to standard fire conditions has been collected and then examined via the interpretable Fuzzy C-Means algorithm (FCM) and the Classification and Regression Tree (CART) model. Our results indicate that this clustering technique groups RC columns into four natural groups – each with specific properties and characteristics. Moreover, the CART model is used to analyze the variables used as the basis for the clustering of RC columns. Accordingly, when RC columns are separated into four natural clusters, the first split occurs due to restrictions, and the second separation is controlled by the compressive strength and reinforcement ratios of the columns. This research might be the first to attempt to leverage clustering analysis to investigate the fire response of RC columns. The findings of the study clearly show that unsupervised machine learning can provide valuable insights to fire engineers often missing from traditional supervised learning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
A Novel Hierarchical Extreme Machine-Learning-Based Approach for Linear Attenuation Coefficient Forecasting
(MDPI, 2023) Varone G.; Ieracitano C.; Çiftçioğlu A.Ö.; Hussain T.; Gogate M.; Dashtipour K.; Al-Tamimi B.N.; Almoamari H.; Akkurt I.; Hussain A.
The development of reinforced polymer composite materials has had a significant influence on the challenging problem of shielding against high-energy photons, particularly X-rays and (Formula presented.) -rays in industrial and healthcare facilities. Heavy materials’ shielding characteristics hold a lot of potential for bolstering concrete chunks. The mass attenuation coefficient is the main physical factor that is utilized to measure the narrow beam (Formula presented.) -ray attenuation of various combinations of magnetite and mineral powders with concrete. Data-driven machine learning approaches can be investigated to assess the gamma-ray shielding behavior of composites as an alternative to theoretical calculations, which are often time- and resource-intensive during workbench testing. We developed a dataset using magnetite and seventeen mineral powder combinations at different densities and water/cement ratios, exposed to photon energy ranging from 1 to (Formula presented.) kiloelectronvolt (KeV). The National Institute of Standards and Technology (NIST) photon cross-section database and software methodology (XCOM) was used to compute the concrete’s (Formula presented.) -ray shielding characteristics (LAC). The XCOM-calculated LACs and seventeen mineral powders were exploited using a range of machine learning (ML) regressors. The goal was to investigate whether the available dataset and XCOM-simulated LAC can be replicated using ML techniques in a data-driven approach. The minimum absolute error (MAE), root mean square error (RMSE), and (Formula presented.) were employed to assess the performance of our proposed ML models, specifically a support vector machine (SVM), 1d-convolutional neural network (CNN), multi-Layer perceptrons (MLP), linear regressor, decision tree, hierarchical extreme machine learning (HELM), extreme learning machine (ELM), and random forest networks. Comparative results showed that our proposed HELM architecture outperformed state-of-the-art SVM, decision tree, polynomial regressor, random forest, MLP, CNN, and conventional ELM models. Stepwise regression and correlation analysis were further used to evaluate the forecasting capability of ML techniques compared to the benchmark XCOM approach. According to the statistical analysis, the HELM model showed strong consistency between XCOM and predicted LAC values. Additionally, the HELM model performed better in terms of accuracy than the other models used in this study, yielding the highest R2score and the lowest MAE and RMSE. © 2023 by the authors.
Identifying and estimating causal effects of bridge failures from observational data
(Elsevier B.V., 2024) Çiftçioğlu A.Ö.; Naser M.Z.
This paper presents a causal analysis aimed at identifying and estimating causal effects with regard to bridge failures under extreme events. Observational data on about 299 bridge incidents were used to conduct this causal investigation and examine bridges’ performance. As causal investigations can also deliver counterfactual assessments of parallel worlds, a causal analysis can serve as a high-merit methodology to evaluate the performance of critical bridges. Our findings quantify the causal impacts of various factors spanning the characteristics of bridges, traffic demands, and incident type (i.e., fire, high wind, scour/flood, earthquake, and impact/collision). More specifically, our analysis reveals high causal effects related to the used structural system, construction materials, and demand served. © 2023 The Authors
A Simulation Study on the Performance of Jacket Type Offshore Structures Using Machine Learning Algorithms
(Universidad de Cantabria, 2024) Gücüyen E.; Çiftçioğlu A.Ö.; Tuğrul Erdem R.
In this study, the behaviors of jacket-type offshore structures are numerically investigated. The examined four-legged models with a total height of 60 m have four layers and three different cylindrical element sizes are fixed to the seabed. The structures are under the effect of environmental forces, including wind and wave loads, as well as operational loads. Three different marine environments have been generated in environmental modeling. Thus, the parametric study has been performed using bidirectional fluid-structure interaction (FSI) analyses of 36 models. Structural outputs such as displacement, reaction force, and stress values are determined by numerical analyses. In the second part of the study, the implementation of machine learning algorithms, including Xgboost, Random Forest, and Support Vector regressors, is employed to automate the assessment of performance in jacket-type offshore structures. The evaluation of these machine learning models in predicting the displacement, reaction force, and stress values of offshore jacket structures is conducted, revealing Xgboost as the most promising technique, although with satisfactory overall performance across all algorithms. These findings provide empirical evidence supporting the feasibility and applicability of employing machine learning methodologies in the analysis of performance for jacket-type offshore structures. © SEECMAR | All rights reserved.
Fire resistance evaluation through synthetic fire tests and generative adversarial networks
(Higher Education Press Limited Company, 2024) Çiftçioğlu A.Ö.; Naser M.Z.
This paper introduces a machine learning approach to address the challenge of limited data resulting from costly and time-consuming fire experiments by enlarging small fire test data sets and predicting the fire resistance of reinforced concrete columns. Our approach begins by creating deep learning models, namely generative adversarial networks and variational autoencoders, to learn the spatial distribution of real fire tests. We then use these models to generate synthetic tabular samples that closely resemble realistic fire resistance values for reinforced concrete columns. The generated data are employed to train state-of-the-art machine learning techniques, including Extreme Gradient Boost, Light Gradient Boosting Machine, Categorical Boosting Algorithm, Support Vector Regression, Random Forest, Decision Tree, Multiple Linear Regression, Polynomial Regression, Support Vector Machine, Kernel Support Vector Machine, Naive Bayes, and K-Nearest Neighbors, which can predict the fire resistance of the columns through regression and classification. Machine learning analyses achieved highly accurate predictions of fire resistance values, outperforming traditional models that relied solely on limited experimental data. Our study highlights the potential for using machine learning and deep learning analyses to revolutionize the field of structural engineering by improving the accuracy and efficiency of fire resistance evaluations while reducing the reliance on costly and time-consuming experiments. © The Author(s) 2024.
COVID-19 chest CT scan image segmentation based on chaotic gravitational search algorithm
(Springer Nature, 2025) Rather S.A.; Das S.; Çiftçioğlu A.Ö.
Image segmentation is a pivotal phase in the image processing pipeline, offering detailed insights into various image features. Traditional segmentation methods grapple with challenges such as local minima and premature convergence when navigating intricate pixel search spaces. Additionally, these algorithms experience prolonged processing times as the number of threshold levels increases. To mitigate these issues, we implemented the Chaotic Gravitational Search Algorithm (CGSA), a robust optimizer, for the multi-level thresholding of COVID-19 chest CT scan images. CGSA amalgamates the Gravitational Search Algorithm (GSA) for exploration with chaotic maps for exploitation. Kapur’s entropy method was employed to partition the sample images based on optimal pixel values. The segmentation performance of CGSA was rigorously assessed on various COVID-19 chest CT scan imaging datasets from Kaggle, utilizing metrics such as Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Feature Similarity Index Measure (FSIM). The qualitative analysis encompassed convergence curves, segmented graphs, colormap images, histogram curves, and boxplots. Statistical validation was conducted using the signed Wilcoxon rank sum test, and eight sophisticated heuristic algorithms were enlisted for comparative analysis. The comprehensive evaluation unequivocally demonstrated CGSA's superiority in terms of processing time efficiency and its ability to provide optimal values for image quality metrics, establishing it as a powerful tool for quickly assessing COVID-19 disease severity. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

Browsing by Author "Çiftçioğlu A.Ö."

Results Per Page

Sort Options