Yazar "Ucan, O. Nuri" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Modeling of Methane Distribution in a Landfill Using Genetic Algorithms
    (Mary Ann Liebert, Inc, 2009) Ozcan, H. Kurtulus; Balkaya, Nilgun; Bilgili, Erdem; Demir, Goksel; Ucan, O. Nuri; Bayat, Cuma
    Landfill gas (LFG) results from the biologic decomposition of municipal waste and consists of mostly methane (CH4) and carbon dioxide (CO2), as well as trace amounts of a variety of other compounds. In this study, the major landfill gas emissions produced in Istanbul Hasdal landfill were investigated and modeled. In the investigated area, CH4, CO2, and O-2 measurements were made for 3.5 years in order to monitor long-term variations. In addition, a supervised algorithm for the evaluation of CH4 concentration using a genetic algorithm (GA) was developed and applied to real data. The model and the actual measurement results were compared and statistically evaluated. It was observed that the long term changes of the CH4 concentrations can be estimated effectively by the GA model structure. A correlation with 0.86 value was ascertained between the actual values and model results. The results of the study indicated that the GA can be used in modeling landfill gases generated in solid waste deposition areas.
  • Küçük Resim Yok
    Öğe
    Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks
    (Science China Press, 2007) Ozcan, H. Kurtulus; Bilgil, Erdem; Sahin, Ulku; Ucan, O. Nuri; Bayat, Cuma
    Tropospheric ozone concentrations, which are an important air pollutant, are modeled by the use of an artificial intelligence structure. Data obtained from air pollution measurement stations in the city of Istanbul are utilized in constituting the model. A supervised algorithm for the evaluation of ozone concentration using a genetically trained multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. A genetic algorithm is used in the optimization of CNN templates. The model results and the actual measurement results are compared and statistically evaluated. It is observed that seasonal changes in ozone concentrations are reflected effectively by the concentrations estimated by the multilevel-CNN model structure, with a correlation value of 0.57 ascertained between actual and model results. It is shown that the multilevel-CNN modeling technique is as satisfactory as other modeling techniques in associating the data in a complex medium in air pollution applications.