Yazar "Tutmez, Bulent" seçeneğine göre listele
Listeleniyor 1 - 20 / 32
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analyzing non-stationarity in cement stone pit by median polish interpolation: a case study(Taylor & Francis Ltd, 2014) Tutmez, BulentThe raw materials utilized in the manufacture of cement comprise mainly of lime, silica, alumina and iron oxide. Spatial evaluation of these main chemical constituents of cement has crucial importance for providing effective production. Because these components are composed of some raw materials such as limestone and marl, the spatial relationships in a calcareous marl stone pit was taken into consideration. In practice, spatial field data taken from a cement quarry may include some variations and trends. For modeling and removing spatial trend in a cement raw material quarry as well as providing unbiased estimates, median polish kriging was used. By using the variation of the data itself, some approximations and interpolations were carried out. It was recorded that the method obtained outlier-resistant estimation of spatial trend without needing an external exploratory variable. In addition, it provided very effective estimations and additional information for analyzing spatial non-stationary data.Öğe Assessing uncertainty of nitrate variability in groundwater(Elsevier Science Bv, 2009) Tutmez, BulentNitrate is the primary form of nitrogen in natural waters and it can easily pass through soil to groundwater. Some levels of nitrate concentration in groundwater can cause some health problems such as methemoglobinemia in infants and several cancers. Since geological structures are not homogeneous, investigation of spatial variability of nitrate concentrations in groundwater is characterized by particularly high uncertainties. In this paper, a novel methodology for measure of uncertainty in groundwater nitrate variability is presented. To appraise the fuzziness, which is a type of uncertainty in spatial models, point cumulative semimadogram (PCSM) measure and a metric distance were employed. Measures of fuzziness have been carried out for each location using the experimental and model PCSMs. Finally an uncertainty map, which defines the regional variation of the uncertainty in different categories, has been composed. (C) 2008 Elsevier B.V. All rights reserved.Öğe Assessment of porosity using spatial correlation-based radial basis function and neuro-fuzzy inference system(Springer London Ltd, 2010) Tutmez, BulentAquifer porosity indicates the storage groundwater capacity and groundwater quality. It may be measured via different techniques. This paper presents a novel spatial methodology based on radial basis function (RBF) and neuro-fuzzy inference system for modelling the porosity. Use of the point cumulative semimadogram in RBF as a spatial measure is a novel contribution. In addition, the methodology examines the use of a neural network-based fuzzy inference system for porosity estimation. Performance comparisons with conventional methods show that the proposed spatial model has high modelling and generalization capability.Öğe Bauxite quality classification by shrinkage methods(Elsevier, 2018) Tutmez, BulentGeochemically, bauxite ore may contain some clay minerals, aluminum oxides-hydroxides, and insoluble materials such as quartz and magnetite. The amounts of the geochemical components and their ratios (modules) have critical importance in bauxite quality classification. A classification study was conducted by way of Al2O3/ SiO2 module and its corresponding indicators such as spatial coordinates, thickness, and some of the geochemical contributors. The classification was made benefit of two advanced regularization methods such as ridge and the Lasso regression methods. Accuracy, interpretability and simplicity were appraised. Both the algorithms had influence on reducing variance. The smoothing levels of the algorithms also were discussed. The resulting classification provided by the strong estimators can provide a reliable tool for industrial decision making and control.Öğe Clustering-based identification for the prediction of splitting tensile strength of concrete(Techno-Press, 2009) Tutmez, BulentSplitting tensile strength (STS) of high-performance concrete (HPC) is one of the important mechanical properties for structural design. This property is related to compressive strength (CS), water/binder (W/B) ratio and concrete age. This paper presents a clustering-based fuzzy model for the prediction of STS based on the CS and (W/B) at a fixed age (28 days). The data driven fuzzy model consists of three main steps: fuzzy clustering, inference system, and prediction. The system can be analyzed directly by the model from measured data. The performance evaluations showed that the fuzzy model is more accurate than the other prediction models concerned.Öğe Comparing two data driven interpolation methods for modeling nitrate distribution in aquifer(Elsevier, 2010) Tutmez, Bulent; Hatipoglu, ZubeydeAs a soluble compound in water, nitrate could easily pass through soil to the groundwater. In recent decades, nitrate pollution of groundwater has been increased mainly as a result of excessive application of fertilizers in agricultural areas. Appraisal of nitrate distribution in aquifers is not a new problem but it is still unsolved. This paper compares the performances of two modeling approaches such as geostatistical (kriging) and soft (fuzzy) computing in spatial interpolation of nitrate concentration in groundwater. For this purpose, the groundwater samples are collected from springs and wells in Mersin-Tarsus Aquifer to be considered. The estimation models are established based on data driven modeling concept. The results and performance evaluations indicate that the estimation capacity of the fuzzy model is higher than that of the kriging model. (C) 2009 Elsevier BM. All rights reserved.Öğe Comparison of measurement uncertainty calculation methods on example of indirect tensile strength measurement(Techno-Press, 2017) Tutmez, BulentIndirect measure of the tensile strength of laboratory samples is an important topic in rock engineering. One of the most important tests, the Brazilian strength test is performed to obtain the tensile strength of rock, concrete and other quasi brittle materials. Because the measurements are provided indirectly and the inspected rock materials may have heterogeneous properties, uncertainty quantification is required for a reliable test evaluation. In addition to the conventional measurement evaluation uncertainty methods recommended by the Guide to the Expression of Uncertainty in Measurement (GUM), such as Taylor's and Monte Carlo Methods, a fuzzy set-based approach is also proposed and resulting uncertainties are discussed. The results showed that when a tensile strength measurement is measured by a laboratory test, its uncertainty can also be expressed by one of the methods presented.Öğe A data-driven study for evaluating fineness of cement by various predictors(Springer Heidelberg, 2015) Tutmez, BulentModelling relationships among cement and concrete parameters from different perspectives is preferred due to its practical importance. The relationship between chemical ingredients and specific surface area which addresses fineness of cement were appraised via three predictors: robust regression (RR), support vector regression (SVR) and multi-layer perception (MLP). The main motivation of the study was to give a comparative assessment with sparse data based on accuracy of the models. In addition to accuracy, smoothing level of the estimations was also considered and the performances of three models were compared with the former practices. The experimental studies showed that the SVR model performs better than the rest of the models for identifying the relationships. The potentials of the MLP and the RR models have also been discussed.Öğe Evaluating geo-environmental variables using a clustering based areal model(Pergamon-Elsevier Science Ltd, 2012) Tutmez, Bulent; Kaymak, Uzay; Tercan, A. Erhan; Lloyd, Christopher D.Global regression models do not accurately reflect the spatial heterogeneity which characterises most geo-environmental variables. In analysing the relationships between such variables, an approach is required which allows the model parameters to vary spatially. This paper proposes a new framework for exploring local relationships between geo-environmental variables. The method is based on extended objective function based fuzzy clustering with the environmental parameters estimated through on a locally weighted regression analysis. The case studies and prediction evaluations show that the fuzzy algorithm yields well-fitted models and accurate predictions. In addition to an increased accuracy of prediction relative to the widely-used geographically weighted regression (GWR), the proposed algorithm provides the search radius (bandwidth) and weights for local estimation directly from the data. The results suggest that the method could be employed effectively in tackling real world kernel-based modelling problems. (C) 2012 Elsevier Ltd. All rights reserved.Öğe Fuzzy optimization of slab production from mechanical stone properties(Springer, 2008) Tutmez, Bulent; Kaymak, UzayThis paper aims to conduct slab production optimization by a flexible tool, which is fuzzy linear programming. There is a direct relationship between slab production and mechanical stone characteristics. In this process, the goal and its tolerance cannot be specified firstly due to a lack of knowledge. Therefore, the optimal system design problem for optimal slab production under soft constraints is constructed and solved in a fuzzy environment. The results show that fuzzy linear optimization is a convenient tool for optimizing slab production.Öğe Identifying electrical conductivity in topsoil by interpretable machine learning(Springer Heidelberg, 2024) Tutmez, BulentImplementing computational and statistical intelligence allows understanding variations to make knowledgeable decisions in agriculture and land use. In this study, using the interpretation capacity of functional precision models against the lower-level mechanistic models has been given priority and advanced regression algorithms were used for this purpose. For exploring the relationships between electrical conductivity (EC) which is the most critical indicator for salinity and irrigation and soil parameters (texture, chemical concentrations) a comparative assessment based on supervised learning algorithms has been conducted and the outcomes have been interpreted by statistical learning. Both linear and non-linear statistical approaches have been used to analyze EC since it is a heterogeneous natural feature in topsoil. The implementations showed that the non-linear MARS model has provided the best testing accuracy. In addition to precision, relationships between EC and indicator variables, major modelling components and measure of the parameter effects have been exhibited by estimated probabilities and partial dependence measures. The main drivers for EC assessment in topsoil, specifically pH in water, CaCl2, and nitrogen concentration, have been discovered. The benchmarking results revealed that different from the conventional mechanistic models, interpretable machine learning provides additional interpretation, meta-data and transparency for sustainable soil management and environment.Öğe Learning distance effect on lignite quality variables at global and local scales(Springernature, 2021) Yaylagul, Cem; Tutmez, BulentDetermining scale and variable effects have critical importance in developing an energy resource policy. This study aims to explore the relationships in heterogeneous lignite sites using different scale models, spatial weighting as well as error-based pair-wise identification. From a statistical learning framework, the relationships among the quality variables such as geochemical variables and the contributions of the coordinates to quality measures have been exhibited by generalized additive models. In this way, the critical roles of spatial weights provided by the coordinates have been specified at a global scale. The experimental studies reveal that incorporating the geological weighting in the models as the additional information improves both accuracy and transparency. Because relationships among lignite quality variables and sampling locations are spatially non-stationary, the local structure and interdependencies among the variables were analyzed by geographically weighting regression. The local analyses including spatial patterns of bandwidths, search domains as well as residual-based areal dependencies provided not only the critical zones but also availability of pair-wise model alternatives by calibrating a model at each point for location-specific parameter learning. The results completely show that the weighting models applied at different scales can take spatial heterogeneity into consideration and these abilities provide some meta-data and specific information using in sustainable energy planning.Öğe Lithological classification of cement quarry using discriminant algorithms(Journal Of Central South Univ, 2019) Tutmez, BulentAs such in any industrial raw material site characterization study, making a lithological evaluation for cement raw materials includes a description of physical characteristics as well as grain size and chemical composition. For providing the cement components in accordance with the specifications required, making the classification of the cement raw material pit is needed. To make this identification in a spatial system at a quarry stage, the supervised pattern recognition analysis has been performed. By using four discriminant analysis algorithms, lithological classifications at three levels, which are with limestone, marly-limestone (calcareous marl) and marl, have been made based on the main chemical components such as calcium oxide (CaO), alumina (Al2O3), silica (SiO2), and iron (Fe2O3). The results show that discriminant algorithms can be used as strong classifiers in cement quarry identification. It has also recorded that the conditional and mixed classifiers perform better than the conventional discriminant algorithms.Öğe Local models for the analysis of spatially varying relationships in a lignite deposit(European Soc Fuzzy Logic & Technology, 2009) Tutmez, Bulent; Tercan, A. Erhan; Kaymak, Uzay; Lloyd, Christopher D.Relationships between geographically referenced variables are usually spatially heterogeneous and, to account for such variations, local models are necessary. This paper compares the Geographically Weighted Regression (GWR) model, usually used to integrate and examine the spatial heterogeneity of a relationship, and the Fuzzy Clustering-Based Least Squares (FCBLS) model for the analysis of spatially varying relationships. Both models use the same model parameters and bandwidth values derived from the Akaike Information Criterion. The results show that FCBLS outperforms the GWR model.Öğe Local spatial regression models: a comparative analysis on soil contamination(Springer, 2012) Tutmez, Bulent; Kaymak, Uzay; Tercan, A. ErhanSpatial data analysis focuses on both attribute and locational information. Local analyses deal with differences across space whereas global analyses deal with similarities across space. This paper addresses an experimental comparative study to analyse the spatial data by some weighted local regression models. Five local regression models have been developed and their estimation capacities have been evaluated. The experimental studies showed that integration of objective function based fuzzy clustering to geostatistics provides some accurate and general models structures. In particular, the estimation performance of the model established by combining the extended fuzzy clustering algorithm and standard regional dependence function is higher than that of the other regression models. Finally, it could be suggested that the hybrid regression models developed by combining soft computing and geostatistics could be used in spatial data analysis.Öğe Mapping forest fires by nonparametric clustering analysis(Northeast Forestry Univ, 2018) Tutmez, Bulent; Ozdogan, Mert G.; Boran, AhmetFires have a noteworthy role to play with regards to ecological and environmental losses in Mediterranean forests. In addition to ecological impacts, fire may create economic, social as well as cultural changes. The detection of fire-scars has critical importance to help decrease losses. In the present study, forest fires recorded in Antalya, one of the most important ecological and tourist regions within the Western Mediterranean, were clustered and mapped. Since the dominant factors and devastation records derived from the cases had nominal-scaled properties, a categorical data-based nonparametric clustering algorithm was performed in this evaluation. The proposed tool, k-modes algorithm, uses modes instead of means for clustering. The algorithm may be implemented quickly and does not make distributional assumptions concerning the available data. It uses a frequency-based method to update the modes of the fires. The derived modes from the maps may be useful information for local authorities to manage. In conclusion, the proposed nonparametric clustering procedure may be employed to build a decision-support system to monitor and identify fire activities and to enhance fire management efficiency.Öğe Mapping water chemical variables with spatially correlated errors(Springer, 2013) Tutmez, Bulent; Dag, AhmetOne of the most important considerations in many environmental studies is need to allow for correlations among the variables. Monitoring and analyzing relationships between chemical environmental parameters using spatial correlation based regression modelling is the main motivation of this applied study. For this purpose, some noticeable environmental parameters of data sets obtained from two lakes have been considered and the concentrations of chemical variables such as cadmium and nitrate have been appraised by a regression-based geostatistical methodology. The modelling procedure consists of two stages. In the first stage, spatial variables are analyzed via multi-linear regression and some relationships are provided. Next, by using the spatial auto-correlations of the residuals, a type of regression-based kriging procedure is applied. The capacity of the model for appraising the water chemical variables is also tested and performance comparisons with ordinary kriging are conducted. Finally, the applications showed that analyzing water chemical variables with spatially correlated errors is a convenient and applicable approach for assessing the environmental systems.Öğe Measure of uncertainty in regional grade variability(Springer-Verlag Berlin, 2007) Tutmez, Bulent; Kaymak, UzayBecause the geological events are neither homogeneous nor isotropic, the geological investigations are characterized by particularly high uncertainties. This paper presents a hybrid methodology for measuring of uncertainty in regional grade variability. In order to evaluate the fuzziness in grade values at ore deposit, point cumulative semimadogram (PCSM) measure and a metric distance have been employed. By using the experimental PCSMs and their linear models, measures of fuzziness have been carried out for each location. Finally, an uncertainty map, which defines the regional variation of the uncertainty in different categories, has been composed.Öğe Measurement uncertainty analysis for compressive loading-based ultrasonic wave propagation(Taylor & Francis Ltd, 2017) Tutmez, BulentAs a non-destructive test, the ultrasonic pulse velocity measure is one of the convenient tools suggested to estimate elasticity and strength properties of rocks. Since the experimental procedure and identification process cover various uncertainty sources, an extensive measurement uncertainty analysis is required to determine the variations in the testing procedure and measurement. As a generally accepted document for the measurement uncertainty, the Guide to expression of uncertainty in measurement (GUM)' recommends Taylor and Monte Carlo methods to evaluate the measurement uncertainties. In this study, both random and systematic uncertainties encountered in ultrasonic wave propagation are analysed and appraised. Starting from the conventional methods recommended in GUM and further approaches proposed previously, a copula-based evaluation procedure is proposed in order to improve the consideration of dependencies in the measurement data.Öğe Quantifying uncertainty in railway noise measurement(Elsevier Sci Ltd, 2019) Tutmez, Bulent; Baranovskii, AndreiEven though the railway is very safe and environmentally friendly mode of transport, it also gives rise to immense noise problems. Over the past several decades, the overall railway noise level has been compounded by increasing in railway transport traffic in the world. At this stage, conducting effective noise measurement and making a reliable control come to exist as critical operations. When a noise measurement is performed, a reliable uncertainty evaluation on the measurement accuracy should be considered by the evaluators. This study focuses on the measurement uncertainties dealing with noise measurements recorded in the railway transport. Together with the effects of the systematic uncertainty sources such as equipment, calibration, environment and operator uncertainties as well as the amount of the random uncertainties, the uncertainties resourced from the angular dependency (measurement position) were quantified based on measurement uncertainty analysis framework. The calculations revealed that the main effective uncertainty components are repeatability uncertainty arising from the data variability and the position uncertainty arising from the angular dependency. Based on the position of the equipment (critical angle) and corresponding uncertainty, a trade trade-off analysis between the amount of the combined uncertainty and the distance has also been made for determining the optimum instrument position. The results showed that providing practical and correct measurement records together with created uncertainties have a remarkable amount of importance in noise measurement. (C) 2019 Elsevier Ltd. All rights reserved.
