Yazar "Ertam, Fatih" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    An intelligent approach to investigate the effects of container orientation for PCM melting based on an XGBoost regression model
    (Elsevier Sci Ltd, 2024) Kiyak, Burak; Oztop, Hakan F.; Ertam, Fatih; Aksoy, I. Gokhan
    The orientation of the container filled with phase change material (PCM) is a critical parameter that significantly effects the performance of thermal energy storage systems. In this study, the Computational Fluid Dynamics (CFD) method is utilised to analyse the effects of container position on the melting process of PCM. Unlike conventional methods, the melting process of PCM was conducted using the hot air jet impingement method. The study investigated the impact of two various Reynolds numbers (2235 and 4470) and three different H/D ratio (the ratio of the distance between the jet and the container to the container diameter) which were 0.4, 0.5, and 0.6, on the PCM melting process. In addition, regression analysis was executed using the Extreme Gradient Boosting algorithm (XGBoost). The outcomes unveiled that the artificial intelligence model attained a minimum accuracy of 97.89 % and reached a maximum accuracy of 99.35 % across the 12 datasets for comparing performance metrics. These results serve as a testament to the prowess of the XGBoost algorithm in providing precise predictions of the target variable within a notably extensive range of accuracy for the datasets under consideration.
  • Küçük Resim Yok
    Öğe
    A survival classification method for hepatocellular carcinoma patients with chaotic Darcy optimization method based feature selection
    (Elsevier, 2020) Demir, Fahrettin Burak; Tuncer, Turker; Kocamaz, Adnan Fatih; Ertam, Fatih
    Survey is one of the crucial data retrieval methods in the literature. However, surveys often contain missing data and redundant features. Therefore, missing feature completion and feature selection have been widely used for knowledge extraction from surveys. We have a hypothesis to solve these two problems. To implement our hypothesis, a classification method is presented. Our proposed method consists of missing feature completion with a statistical moment (average) and feature selection using a novel swarm optimization method. Firstly, an average based supervised feature completion method is applied to Hepatocellular Carcinoma survey (HCC). The used HCC survey consists of 49 features. To select meaningful features, a chaotic Darcy optimization based feature selection method is presented and this method selects 31 most discriminative features of the completed HCC dataset. 0.9879 accuracy rate was obtained by using the proposed chaotic Darcy optimization-based HCC survival classification method.