Çakmakçı, Mehmet | Kınacı, Cumali | Bayramoğlu, Mahmut | Yıldırım, Yılmaz

Article | 2010 | Expert Systems with Applications37 ( 2 ) , pp.1369 - 1373

Effluent iron concentration is an important water quality criterion used for the assessment of the performance of rapid sand filters, in addition to other criteria. This study deals with the prediction of effluent iron concentrations by adaptive neuro-fuzzy (ANFIS) model with input parameters including filter hydraulic loading rate, influent iron concentration, bed porosity and operation time. With trying various types of membership functions, two rule base generation methods, namely subtractive clustering and grid partition were used for a first order Sugeno type inference system. Models were evaluated using root mean squared error . . . (RMSE), index of agreement (IA) and R2 as statistical performance parameters. The fit between experimental results and model outputs showed good agreement for tap water and deionized water; testing RMSE values were 36.33 and 7.66 µg/L, the IA values were 0.996 and 0.971, and R2 values were 0.99 and 0.89, respectively. It was concluded that neuro-fuzzy modeling may be successfully used to predict effluent iron concentration in sand filtration. © 2009 Elsevier Ltd. All rights reserved Daha fazlası Daha az

Özdemir, Kadir | Yıldırım, Yılmaz | Toröz, İsmail | Uyak, Vedat

Article | 2015 | Asian Journal of Chemistry27 ( 3 ) , pp.984 - 990

This research developed models using multiple linear regression analysis for the prediction of trihalomethane formation in coagulated Istanbul drinking water sources. The power-law model (model 1), using only ?UV272 as the designed parameter, proved the best model to describe the formation of trihalomethane. The other model (model 2), included pH, total organic carbon, chlorine dosages, ultraviolet absorbance at 254 nm (UV254), specific ultraviolet absorbance (SUVA) and differential absorbance at 272 nm (?UV272). The root-meansquare error (RMSE), normalization mean square error (NMSE), regression coefficient (R2) and index of agreem . . .ent (IA) were used as statistical variables to evaluate the model performance. The better prediction results were obtained by model 1 for root-mean-square error, normalization mean square error, R2 and index of agreement as 9.14, 0.015, 0.95 and 0.99, respectively. © 2015, Chemical Publishing Co. All rights reserved Daha fazlası Daha az

Yıldırım, Yılmaz | Bayramoğlu, Mahmut | Hasıloğlu, Samet

Article | 2003 | Fresenius Environmental Bulletin12 ( 10 ) , pp.1173 - 1179

Air pollution continues to be a major problem in many countries. Mathematical models are useful in relating emissions to air quality under a variety of meteorological conditions and source emission concentrations over an urban area. Meanwhile, the forecasting capability of sophisticated models is limited to very large and complex terrains. In this study, an adaptive neuro-fuzzy logic method has been developed to estimate the impact of meteorological factors on SO2 pollution levels. The model satisfactorily forecasts the trends of SO2 concentration levels with a performance between 78-90%.