Yazar "Demir, Vahdettin" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Forecasting of Lake Level by Soft Computing Approaches
    (Springer Science and Business Media Deutschland GmbH, 2024) Demir, Vahdettin; Tamer, Mehmet Ali; Çarbaş, Serdar
    To ensure the sustainability and management of water resources, regularly monitoring the water levels in lakes, rivers, basins, dam reservoirs, etc. is a very important engineering task. Our freshwater resources are gradually decreasing due to the destruction of freshwater resources and climate change. For this reason, monitoring, modelling, and researching of freshwater resources, especially lakes, are increasingly important issue for nowadays. In this chapter, soft computing approaches are used to forecast of lake water levels at Beyşehir Lake, located in the central part of Turkey. To do this, three artificial neural network algorithms (Multilayer, Radial Basis and Generalized Regression), two heuristic algorithms (Model 5-Tree and Multivariate Adaptive Regression Spline), and a Support Vector Machines containing three different functions (Radial, Polynomial, and Linear) are used. In addition to being models used successfully in hydrological modelling of civil engineering, the changes in modelling performance with the number of iterations, kernel functions, optimization algorithms, and data input sets that constitute the internal dynamite of the techniques are investigated. The attained results show that through these multiple parameters, radial basis artificial neural networks are the most successful when compared with mean absolute error, root mean square error, coefficient of determination, Taylor diagrams and Violin plots. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Modeling Civil Engineering Problems via Hybrid Versions of Machine Learning and Metaheuristic Optimization Algorithms
    (Springer Science and Business Media Deutschland GmbH, 2023) Demir, Vahdettin; Uray, Esra; Carbas, Serdar
    The aim of this study is to develop hybrid solution models by integrating metaheuristic optimization algorithms and machine learning technique. These hybrid models are utilized to estimate bearing capacity of pile groups and lake levels, which are common challenges to calculate in the geotechnical and hydrology designs of civil engineering. To achieve this, Lake Beyşehir lake-water level observations and various pile group designs are used as a dataset, which is divided into two parts; 75% for training and 25% for testing. By employing improved hybrid models that combine metaheuristic algorithms such as harmony search, artificial bee colony, and particle swarm optimization with a machine learning technique called least squares support vector regression (LSSVR), optimal values of kernel parameters are obtained reliably and robustly. The results suggest that these hybrid models can be successfully applied to complex real-world problems, as evidenced by nine evaluation metrics, including mean absolute error (MAE), root mean squared error (RMSE), and determination coefficient (R2), which showed satisfactory and reasonable performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.