Civil Engineering / İnşaat Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/13
Browse
4 results
Search Results
Article Citation - WoS: 1Citation - Scopus: 1Estimation of Mechanical Properties of Limestone Using Regression Analyses and Ann(Foundation Cement, Lime, Concrete, 2012) Teomete, Egemen; Tayfur, Gökmen; Aktaş, EnginEstimation of mechanical properties of rocks is important for researchers and field engineers working in cement and concrete industry. Limestone is used in cement production. In this study, Schmidt hammer, ultrasonic pulse velocity, porosity, uniaxial compression and indirect tension tests were conducted on limestone obtained from a historical structure. Regression analyses were used to develop models relating mechanical properties of limestone. Artificial Neural Network (ANN) was performed to determine the mechanical properties. The performance of regression models and ANN were compared by existing models in the literature. The results showed that the regression models and ANN yield satisfactory performance with minimum error. The regression models between tensile strength and wave velocity, tensile strength and porosity, wave velocity and porosity have been developed for the first time in literature. The ANN is used for the first time to estimate the mechanical properties of limestone. The use of separate training and testing sets in the regression analyses of mechanical properties of limestone is conducted for the first time. The models developed in this study can be used by researchers and field engineers to relate the mechanical properties of limestone.Article Citation - WoS: 2Citation - Scopus: 1Significance of Rent Attributes in Prediction of Earthquake Damage in Adapazari, Turkey(Czech Technical University in Prague, 2014) Tayfur, Gökmen; Bektaş, Birkan; Duvarcı, YavuzThis paper analyses rent-based determinants of earthquake damage from an urban planning perspective with the data gathered from Adapazari, Turkey, after the disaster in 1999 Eastern Marmara Earthquake (EME). The study employs linear regression, log-linear regression, and artificial neural networks (ANN) methods for cross-verification of results and for finding out the significant urban rent attribute(s) responsible for the damage. All models used are equally capable of predicting the earthquake damage and converge to similar results even if the data are limited. Of the rent variables, the physical density is proved to be especially significant in predicting earthquake damage, while the land value contributes to building resistance. Thus, urban rent can be the primary tool for planners to help reduce the fatalities in preventive planning studies.Article Citation - WoS: 29Citation - Scopus: 34Prediction of Suspended Sediment Concentration From Water Quality Variables(Springer Verlag, 2014) Bayram, Adem; Kankal, Murat; Tayfur, Gökmen; Önsoy, HızırThis study investigates use of water quality (WQ) variables, namely total chromium concentration, total iron concentration, and turbidity for predicting suspended sediment concentration (SSC). For this purpose, the artificial neural networks (ANNs) and regression analysis (RA) models are employed. Seven different RA models are constructed, considering the functional relation between measured WQ variables and SSC. The WQ and SSC data are fortnightly obtained from six monitoring stations, located on the stream Harsit, Eastern Black Sea Basin, Turkey. A total of 132 water samples are collected from April 2009 to February 2010. Model prediction results reveal that ANN is able to predict SSC from WQ data, with mean absolute error (MAE) of 10.30 mg/L and root mean square error (RMSE) of 13.06 mg/L. Among seven RA models, the best one, which has the form including all independent parameters, produces results comparable to those of ANN, with MAE = 14.28 mg/L and RMSE = 15.35 mg/L. The sensitivity analysis results reveal that the most effective parameter on the SSC is total chromium concentration. These results have time- and cost-saving implications.Article Citation - WoS: 37Citation - Scopus: 49Predicting Suspended Sediment Loads and Missing Data for Gediz River, Turkey(American Society of Civil Engineers (ASCE), 2009) Ülke, Aslı; Tayfur, Gökmen; Özkul, SevinçPrediction of suspended sediment load (SSL) is important for water resources quantity and quality studies. The SSL of a stream is generally determined by direct measurement of the suspended sediment concentration or by employing sediment rating curve method. Although direct measurement is the most reliable method, it is very expensive, time consuming, and, in many instances, problematic for inaccessible sections, especially during floods. On the other hand, measuring precipitation and flow discharge is relatively easier and hence, there are more rain and flow gauging stations than SSL gauging stations in Turkey. Furthermore, due to its cost, measurements of SSL are carried out in longer periods compared to precipitation and flow measurements. Although daily precipitation and flow measurements are available for most of the Turkish river basins, at best semimonthly measurements are available for SSL. As such, it is essential to predict SSL from precipitation and flow data and to fill the gap for the missing data records. This study employed artificial intelligence methods of artificial neural networks (ANN) and neurofuzzy inference system, the sediment rating curve method, multilinear regression, and multinonlinear regression methods for this purpose. The comparative analysis of the results showed that the artificial intelligence methods have superiority over the other methods for predicting semimonthly suspended sediment loads. The ANN using conjugate gradient optimization method showed the best performance among the proposed models. It also satisfactorily generated daily SSL data for the missing period record of Gediz River, Turkey.