Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
16 results
Search Results
Article Citation - WoS: 72Citation - Scopus: 79Artificial Neural Networks for Estimating Daily Total Suspended Sediment in Natural Streams(IWA Publishing, 2006) Tayfur, Gökmen; Güldal, VeyselEstimates of sediment loads in natural streams are required for a wide spectrum of water resources engineering problems from optimal reservoir design to water quality in lakes. Suspended sediment constitutes 75-95% of the total load. The nonlinear problem of suspended sediment estimation requires a nonlinear model. An artificial neural network (ANN) model has been developed to predict daily total suspended sediment (TSS) in rivers. The model is constructed as a three-layer feedforward network using the back-propagation algorithm as a training tool. The model predicts TSS rates using precipitation (P) data as input. For network training and testing 240 sets of data sets were used. The model successfully predicted daily TSS loads using the present and past 4 days precipitation data in the input vector with R2 = 0.91 and MAE = 34.22 mg/L. The performance of the model was also tested against the most recently developed non-linear black box model based upon two-dimensional unit sediment graph theory (2D-USGT). The comparison of results revealed that the ANN has a significantly better performance than the 2D-USGT. Investigation results revealed that the ANN model requires a period of more than 75 d of measured P-TSS data for training the model for satisfactory TSS estimation. The statistical parameter range (xmin - xmax) plays a major role for optimal partitioning of data into training and testing sets. Both sets should have comparable values for the range parameter.Article Citation - WoS: 91Citation - Scopus: 122Artificial Neural Networks To Predict Daylight Illuminance in Office Buildings(Elsevier Ltd., 2009) Kazanasmaz, Zehra Tuğçe; Günaydın, Hüsnü Murat; Binol, SelcenA prediction model was developed to determine daylight illuminance for the office buildings by using artificial neural networks (ANNs). Illuminance data were collected for 3 months by applying a field measuring method. Utilizing weather data from the local weather station and building parameters from the architectural drawings, a three-layer ANN model of feed-forward type (with one output node) was constructed. Two variables for time (date, hour), 5 weather determinants (outdoor temperature, solar radiation, humidity, UV index and UV dose) and 6 building parameters (distance to windows, number of windows, orientation of rooms, floor identification, room dimensions and point identification) were considered as input variables. Illuminance was used as the output variable. In ANN modeling, the data were divided into two groups; the first 80 of these data sets were used for training and the remaining 20 for testing. Microsoft Excel Solver used simplex optimization method for the optimal weights. The model's performance was then measured by using the illuminance percentage error. As the prediction power of the model was almost 98%, predicted data had close matches with the measured data. The prediction results were successful within the sample measurements. The model was then subjected to sensitivity analysis to determine the relationship between the input and output variables. NeuroSolutions Software by NeuroDimensions Inc., was adopted for this application. Researchers and designers will benefit from this model in daylighting performance assessment of buildings by making predictions and comparisons and in the daylighting design process by determining illuminance.Article Citation - WoS: 11Citation - Scopus: 18Ann Model for Prediction of Powder Packing(Elsevier Ltd., 2007) Sütçü, Mücahit; Akkurt, SedatA multilayer feed forward backpropagation (MFFB) learning algorithm was used as an artificial neural network (ANN) tool to predict packing of fused alumina powder mixtures of three different sizes in green state. The data used in model construction were collected by mixing and pressing powders with average particle sizes of 350, 30 and 3 μm and with narrow particle size distributions. The data sets that were composed of green densities of cylindrical pellets were first randomly partitioned into two for training and testing of the ANN models. Based on the training data an ANN model of the packing efficiencies was created with low average error levels (3.36%). Testing of the model was also performed with successfully good average error levels of 3.39%.Article Citation - WoS: 46Citation - Scopus: 49Predicting and Forecasting Flow Discharge at Sites Receiving Significant Lateral Inflow(John Wiley and Sons Inc., 2007) Tayfur, Gökmen; Moramarco, Tommaso; Singh, Vijay P.Two models, one linear and one non-linear, were employed for the prediction of flow discharge hydrographs at sites receiving significant lateral inflow. The linear model is based on a rating curve and permits a quick estimation of flow at a downstream site. The non-linear model is based on a multilayer feed-forward back propagation (FFBP) artificial neural network (ANN) and uses flow-stage data measured at the upstream and downstream stations. ANN predicted the real-time storm hydrographs satisfactorily and better than did the linear model. The results of sensitivity analysis indicated that when the lateral inflow contribution to the channel reach was insignificant, ANN, using only the flow-stage data at the upstream station, satisfactorily predicted the hydrograph at the downstream station. The prediction error of ANN increases exponentially with the difference between the peak discharge used in training and that used in testing. ANN was also employed for flood forecasting and was compared with the modified Muskingum model (MMM). For a 4-h lead time, MMM forecasts the floods reliably but could not be applied to reaches for lead times greater than the wave travel time. Although ANN and MMM had comparable performances for an 8-h lead time, ANN is capable of forecasting floods with lead times longer than the wave travel time.Article Doe and Ann Models for Powder Mixture Packing(American Ceramic Society, 2007) Akkurt, Sedat; Romagnoli, Marcello; Sütçü, MücahitDesign of experiments (DOE) and artificial neural network (ANN) techniques were used to study packing of fused alumina powders composed of three different sizes of particles. The first is the mixture design technique that produces a polynomial model of the powder-packing system. While, the ANN technique is extensively used to model complex systems in many fields. The methodological approach used is mixture design, which can be used to study the influences of two or more additives. It is a structured and organized method for determining the relationship between the components and the output of that process. The mixture design approach permits optimization of size distribution to obtain a target value of porosity. Sensitivity analysis involves the use of the developed ANN model to predict outputs (porosity) at varying levels of the input factor effects.Article Citation - WoS: 121Citation - Scopus: 136Quantification of Caco3-Caso3·0.5h 2o-Caso4·2h2o Mixtures by Ftir Analysis and Its Ann Model(Elsevier Ltd., 2004) Böke, Hasan; Akkurt, Sedat; Özdemir, Serhan; Göktürk, E. Hale; Caner Saltık, Emine N.A new quantitative analysis method for mixtures of calcium carbonate (CaCO3), calcium sulphite hemihydrate (CaSO 3·1/2H2O) and gypsum (CaSO 4·2H2O) by FTIR spectroscopy is developed. The method involves the FTIR analysis of powder mixtures of several compositions on KBr disc specimens. Intensities of the resulting absorbance peaks for CaCO 3, CaSO3·1/2H2O and CaSO 4·2H2O at 1453, 980, 1146 cm-1 were used as input data for an artificial neural network (ANN) model, the output being the weight percent compositions of the mixtures. The training and testing data were randomly separated from the complete original data set. Testing of the model was done with successfully low-average error levels. The utility of the model is in the potential ability to use FTIR spectrum to predict the proportions of the three substances in unknown mixtures.Article Citation - Scopus: 33Modeling Freight Distribution Using Artificial Neural Networks(Elsevier Ltd., 2004) Çelik, Hüseyin MuratStudies about freight distribution modeling are limited due to the limitations in data availability. Existing studies in this subject, generally either use the conventional gravity models or the regression based models as modeling techniques. The present study, using the 1993 US Commodity Flow Survey Data, models inter-regional commodity flows for 48 continental states of the US with three different artificial neural networks (ANN). The results are compared with those of Celik and Guldmann's (2002) Box-Cox Regression Model. The ANN using conventional gravity model variables provides a slight improvement with respect to this Box-Cox model. However, the ANNs using theoretically relevant variables provide surprising improvements in comparison to the Box-Cox model. It is concluded that ANN architecture is a very promising technique for predicting short-term inter-regional commodity flows.Article Citation - WoS: 175Citation - Scopus: 203Fuzzy Logic Model for the Prediction of Cement Compressive Strength(Elsevier Ltd., 2004) Akkurt, Sedat; Tayfur, Gökmen; Can, SeverA fuzzy logic prediction model for the 28-day compressive strength of cement mortar under standard curing conditions was created. Data collected from a cement plant were used in the model construction and testing. The input variables of alkali, Blaine, SO3, and C3S and the output variable of 28-day cement strength were fuzzified by the use of artificial neural networks (ANNs), and triangular membership functions were employed for the fuzzy subsets. The Mamdani fuzzy rules relating the input variables to the output variable were created by the ANN model and were laid out in the If-Then format. Product (prod) inference operator and the centre of gravity (COG; centroid) defuzzification methods were employed. The prediction of 50 sets of the 28-day cement strength data by the developed fuzzy model was quite satisfactory. The average percentage error levels in the fuzzy model were successfully low (2.69%). The model was compared with the ANN model for its error levels and ease of application. The results indicated that through the application of fuzzy logic algorithm, a more user friendly and more explicit model than the ANNs could be produced within successfully low error margins.Conference Object Citation - WoS: 4Citation - Scopus: 4Prediction of the Slag Corrosion of Mgo-C Ladle Refractories by the Use of Artificial Neural Networks(Trans Tech Publications, 2004) Akkurt, SedatA multilayer feed-forward back-propagation learning algorithm was employed as an artificial neural network (ANN) tool to create a model to predict the corrosion of MgO-C ladle refractory bricks based on laboratory slag corrosion test data. The corrosion process occurred by immersion of the rectangular refractory specimens in molten slag-steel bath. An ANN model to predict the amount of corrosion was created by using the training data. The model was also tested with experimentally measured data and relatively low error levels were achieved. This model was then used to predict the response of the slag-corrosion system to different values of the factors affecting the corrosion of bricks at high temperatures. Exposure time, exposure temperature of slag-brick contact and CaO/SiO2 ratio of the slag were the factors used for modelling. Model results provided the potential for selection of the best conditions for avoiding the factor combinations that may accelerate corrosion.Article Citation - WoS: 5Citation - Scopus: 8Forecasting Interregional Commodity Flows Using Artificial Neural Networks: an Evaluation(Taylor and Francis Ltd., 2004) Çelik, Hüseyin MuratPrevious studies have concluded that the use of artificial neural networks (ANNs) is a promising new technique for modelling freight distribution, supporting, the findings of other studies in the area of spatial interaction modelling. However, the forecasting performance of ANNs is still under investigation. This study tests the predictive performance of the ANN Model with respect to a Box-Cox spatial interaction model. It is concluded that the Box-Cox model outperforms ANN in forecasting interregional commodity flows even if ANN had proven calibration superiority in comparison to conventional gravity type models.