Yazar "Kardes, Serkan" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    An Artificial Neural Network (ANN) Modelling Approach for Evaluating Turbidity Properties of Paper Recycling Wastewater
    (North Carolina State Univ Dept Wood & Paper Sci, 2024) Kardes, Serkan; Ozkan, Ugur; Bayram, Okan; Sahin, Halil Turgut
    A pre-treatment process was evaluated in this work for wastewater from precipitation of contaminants through centrifugation. Artificial neural networks (ANNs) were used to analyze and optimize the turbidity values. Thirty experimental runs were utilized including microwave (MW) power, duration, centrifuge time, and centrifuge speed as input variables, generated by the Central Composite Full Design (CCFD) approach. The experimental turbidity ranged from 8.1 to 19.7 NTU, while predicted values ranged from 8.4 to 19.7 NTU by ANN. The ANN model showed a robust prediction performance with low mean squared error values during training and testing. Moreover, high R2 values showed a remarkable agreement between the experimental observations and ANN predictions. The results obtained from the input values (A:150.00, B:60.00, C:15.00, D:30.00) of sample 2, which gave the lowest turbidity value, showed the most removal of pollution. The results obtained from the input values (A:250.00, B:60.00, C:7.00, D:20.00) of sample 30, which gave the highest turbidity value, showed the least removal of pollution. The results showed that increasing RPM and time of the centrifugation process significantly affected the removal of pollution in wastewater.
  • Küçük Resim Yok
    Öğe
    Disentangling the determinants of household energy expenditure: A quantile regression approach with machine learning
    (Elsevier Science Sa, 2025) Karaaslan, Abdulkerim; Karaaslan, Kubranur Cebi; Kardes, Serkan
    Household energy consumption is a key driver of national energy demand and emissions. Understanding household behaviour is therefore essential for designing effective and socially sensitive energy policies. This study investigates the determinants of household energy expenditure in T & uuml;rkiye using microdata from the 2023 Household Budget Survey. Variable selection was conducted with machine learning algorithms, and quantile regression was applied to capture heterogeneity across different expenditure levels. The results show that socioeconomic and housing characteristics shape energy spending in diverse ways. In lower quantiles, household type, vehicle fuel choice, and heating systems are more influential, while in upper quantiles, income, residence type, and the number of automobiles dominate. Across all quantiles, appliance efficiency and fuel preferences remain important levers. These findings highlight that uniform policies are unlikely to succeed and that tailored, contextsensitive strategies are needed. By linking household behaviour with institutional realities, the study provides evidence to guide more inclusive and effective energy policy design.
  • Küçük Resim Yok
    Öğe
    Machine Learning-Based Modeling of Methyl Blue Adsorptive Removal from Aqueous Solutions with Lignin
    (Wiley-V C H Verlag Gmbh, 2025) Bayram, Okan; Ozkan, Ugur; Kardes, Serkan; Sahin, Halil Turgut
    Dyes are chemical compounds extensively utilized in numerous industries such as textile, paper, leather, and cosmetics. These substances can cause serious environmental problems by mixing into wastewater during production processes. Methyl blue (MB), which is an anionic dye, has a wide range of applications and poses serious ecological and health risks if discharged untreated into water bodies. In this study, the adsorption process of MB removal using lignin was explained by examining the parameters of temperature, contact time, pH, initial MB dye concentration and initial lignin amount. In addition, lignin was characterized by FT-IR, SEM-EDS, XRD, Zeta potential, DSC, and BET. Then, the results obtained by artificial neural networks (ANN) and support vector regression (SVR) methods were modeled. The analysis revealed that the process is endothermic, follows a pseudo-second-order (PSO) kinetic model, and conforms to the Langmuir isotherm model, with a maximum adsorption capacity (q(max)) of 175.439 +/- 8.772 mg/g, R-2 = 96.200% for ANN and R-2 = 93.500% for SVR. The results obtained showed that lignin can be used for MB removal and that it would be suitable for use in machine learning algorithms.
  • Küçük Resim Yok
    Öğe
    Sustainable decolorization of methyl blue and malachite green from an aqueous environment using magnetic biochar prepared from the fruit seeds of Mespilus germanica L.
    (Taylor & Francis Ltd, 2025) Bayram, Okan; Ozkan, Ugur; Kardes, Serkan; Moral, Emel; Gode, Fethiye; Pehlivan, Erol
    The purpose of this study was to assess the properties of nano-iron loaded biosorbent produced from Mespilus germanica L. fruits seed biochar (MGLfsB) powder, as well as the adsorption/desorption properties of two commonly used dyes; Methyl Blue (MB), and malachite green (MG). Mespilus germanica L. fruits seed biochar (nM-MGLfsB) was produced and used as a biosorbent to remove MB and MG from the solution. SEM and FT-IR analysis were used to characterize the prepared nM-MGLfsB. Temperature (303-333 K), pH (2.0-9.0), initial dye concentration (5-200 mg/L), nM-MGLfsB mass (0.1-0.9 g) and contact time (15-240 min) were all tested in batches to see how they influenced adsorption. The Freundlich, Langmuir, Scatchard, and Temkin models were used to analyze the equilibrium adsorption data. The Langmuir isotherm properly represented the adsorption data, and the saturated maximum removal of nM-MGLfsB determined using this model was 13.09 mg/g for MB and 28.33 mg/g for MG. For MB, nM-MGLfsB had a Delta S degrees value of 63.974 and a Delta H degrees value of 8.05; for MG, the values were 49.660 and 3.490, respectively. The results indicate that the nM-MGLfsB can effectively overcome the limitations of using nano-iron alone and achieve highly efficient dyes removal.