Sürdürülebilir Kalkınma Amaçları
Yayınlar
- ArticleYalnız künye2023Comparison of different optimized machine learning algorithms for daily river flow forecasting
Samui, Pijush; Yesilyurt, Sefa Nur; Dalkilic, Huseyin Yildirim; Yaseen, Zaher Mundher; Roy, Sanjiban Sekhar; Kumar, Sanjay
River flow modeling is essential for critical aspects such as effective water management and structure planning, together with flood and drought analysis. There has been a growing interest in modeling hydrological systems via machine learning (ML) models. Various optimization techniques are utilized to develop the applications of ML-based hydrological models. The ultimate aim of this research is to establish high performance forecasting model. Therefore, this study conducts river flow modeling by using the daily data attained from a gauge station situated in the Euphrates Basin. For this purpose, Artificial Neural Network (ANN) model was hybridized with five different optimization algorithms i.e., Artificial Bee Colony (ABC), Teaching-Learning Based Optimization (TLBO), Ant Colony Optimization (ACO), Ant-Lion Optimization (ALO), and Imperialist Competitive Algorithm (ICA). In determining the inputs used to create the models, the distribution graph and correlation of the data with the previous period data were examined. The results were evaluated with eleven different statistical parameters and an error matrix. Examining the obtained results, the study revealed all models present high performance. When the results were reviewed in general, it was seen that all determination coefficient (R2) and Nash-Sutcliffe coefficient (NSE) values were higher than 0.962, and other parameters were very close to the optimum. By comparing all the developed hybrid models, ANN-ALO model reported the highest performance for river flow forecasting.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2023Application of deep learning approaches to predict monthly stream flows
Dalkilic, H. Yildirim; Kumar, Deepak; Samui, Pijush; Dixon, Barnali; Yesilyurt, S. Nur; Katipoğlu, O. Mert
Accurate and reliable flow estimations are of great importance for hydroelectric power generation, flood and drought risk management, and the effective use of water resources. This research carries out a comprehensive study on the application of gated recurrent unit (GRU) neural network, recurrent neural network (RNN), and long short-term memory (LSTM) to predict with river flows at three different streamflow observation stations in Erzincan, Bayburt, and Gümüshane. Monthly streamflow time series covering the years 1978 to 2015 were used to set up artificial intelligence models. During the modeling phase, 70% of the data was divided into training (October 1978–April 2004), 15% validation (May 2004–September 2009), and 15% test set (October 2010–September 2015). Model performances were made according to the correlation coefficient, root mean square error, the ratio of RMSE to the standard deviation, Nash–Sutcliffe efficiency coefficient, index of agreement, and volumetric efficiency values. The calculation results show that GRU leads efficient estimation results for estimating streamflow and can also be used in allied water resources.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2023Application of Soft Computing Techniques in River Flow Modeling
Yesilyurt, Sefa Nur; Dalkilic, Huseyin Yildirim; Samui, Pijush
Modeling of data is critical in the analysis and evaluation of hydrological behavior. River flow data is one of the most important data in explaining hydrology. Management of water resources; It takes place in the literature as an area that needs to be investigated in order to provide early warning for undesirable situations such as floods and drought. For this reason, it is of important to develop different techniques for the estimation and modeling of river flow or to make comparisons between techniques. In this study, the flow data of fourteen stations located in the Euphrates-Tigris basin between 1981 and 2010 were used. Adaptive Network Based Fuzzy Inference Systems (ANFIS), Support Vector Machine (SVM) techniques that are frequently used in the literature, and newly introduced Gaussian Process Regression (GPR), Extreme Learning Machine (ELM) and Emotional Neural Network (ENN) artificial intelligence techniques are compared. In addition, considering all performance indices, it was determined which technique gave better results with rank analysis. Although all models worked well, it was seen that the methods were ranked as ELM, GPR, ENN, SVM and ANFIS starting from the best. This has shown that ELM, GPR and ENN methods, which have been used recently in flow modeling, give better results than traditional methods with complex structures. In addition, flow values were used in the whole study and these values were examined in 3 different combinations. It was seen that the model structure that gave the best performance was the model structure that used the flow data from one, two and three days ago as an estimator. The results were analyzed with a Taylor diagram and time series graphs.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2021Daily Flow Modeling With Random Forest and K-Nearest Neighbor Methods
Dalkılıç, Hüseyin Yıldırım; Yeşilyurt, Sefa Nur; Samui, Pijush
Water is an indispensable natural resource for life. Therefore, protection and control of water resources are of great importance. Since river flow estimation and modeling are very important in cases such as the management of water resources, irrigation, it is included in the literature as an issue that needs constant research and development. A large number of techniques are being used for estimation and modeling; thus, the estimation results are gradually improving with the development of the studies carried out, the comparison of techniques, and the determination and removal of the shortcomings. In this study, Random Forest and K-Nearest Neighbors nonlinear regression models, which are two of the machine learning methods, were used to evaluating the estimation results, to find the better estimation method, and to determine the advantages and disadvantages of these methods. In addition, Random Search and Grid Search methods were used to make the hyperparameter selection and comparison for the Random Forest model. In this study, in which daily flow data of 1981-2011 of the two stations in the Euphrates were used, and, when compared to other models, it was observed that better results were obtained when Random Search was applied to determine the hyperparameters of the Random Forest model.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2021Evaluation of combined use of drought indices in the case of Konya Closed Basin
Dalkilic, Huseyin Yildirim; Bayçinar, Metin; Samui, Pijush
The climate covers a series of events that deeply affect human life. Today, one of the most effective of these is climate change. As drought is cited as the most important one of the consequences of climate change, it is important to examine it with various. In this study, the drought status of the study area are located statistically calculated and evaluated 4 drought indices. At the same time, factor analysis and validity-reliability analysis were conducted to test the computability of the indices used in the study as a single index and to determine the reliability of the operations. While using exploratory factor analysis, Kaiser-Meyer-Olkin (KMO) test and Bartlett test for factor analysis; Cronbach's alpha coefficient was used for reliability analysis. In our study, K-means cluster analysis method was performed to determine the cut-off values of indices. According to the cluster analysis, new clusters were created and ANOVA test was conducted to determine the difference between clusters.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2021Reliability analysis of circular footing by using GP and MPMR
Kumar, Rahul; Samui, Pijush; Kumari, Sunita; Dalkilic, Yildirim Hüseyin
Circular footings are designed to bear a load of super structures. Studies have been done on the influence of soil properties on bearing capacity of shallow foundations. The use of circular foundation is practical in geotechnical engineering. During the design of circular footing, bearing capacity of soil is taken into consideration, and cohesion (c), unit weight (γ), and angle of internal friction (ϕ) are the most variable parameters. Reliability analysis is used frequently for the design of circular footing. Most of the authors have used first order second moment methods (FOSM). However, FOSM is a time-consuming method. Drawbacks of FOSM have been overcome by genetic programming (GP), minimax probability machine regression (MPMR). This article gives a distinct analysis between the developed MPMR based FOSM and GP-based FOSM.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2019Utilization of SVM, LSSVM and GP for predicting the medical waste generation
Jagan, J.; Dalkiliç., Yildirim; Samui, Pijush
The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2019Utilization of SVM, LSSVM and GP for predicting the medical waste generation
Jagan, J.; Dalkiliç, Yildirim; Samui, Pijush
The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2017Modeling of seismic liquefaction data using extreme learning machine
Samui, Pijush; Roy, Sanjiban Sekhar; Kurup, Pradeep; Dalkiliç, Yildirim
Seismic liquefaction is a major concern for any earthquake prone area. This article employs a new technique based on Extreme Learning Machine (ELM) for determination of liquefaction susceptibility of soil based on Standard Penetration Test (SPT) and Cone Penetration Test (CPT) from the Chi-Chi earthquake. ELM is the modified version of Single-hidden Layer Feed forward Neural Network. Different input combinations have been tried to get best performance. A comparative study has been carried out between the SPT and CPT based models. CPT based models give better performance than the SPT based model. The developed ELM model shows that Cone Resistance (qc) and Peck Ground Acceleration (PGA) are sufficient parameters for determination of liquefaction susceptibility of soil.
RDL Kalıcı Kaydıİncele - Book ChapterAçık Erişim2016Reliability analysis of slope using MPMR, GRNN and GPR
Subburaman, Dhivya; Jagan, J.; Dalkiliç, Yildirim; Samui, Pijush
First Order Second Moment Method (FOSM) is generally for determination of reliability of slope. This article adopts Minimax Probability Machine Regression (MPMR), Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) for reliability analysis of slope by using FOSM. In this study, an example of soil slope is given regarding how the proposed GPR-based FOSM, MPMR-based FOSM and GRNN-based FOSM analysis can be carried out. GPR, GRNN and MPMR have been used as regression techniques. A comparative study has been carried out between the developed GPR, MPMR and GRNN models. The results show that MPMR gives better performance than the other models.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2016Determination of bearing capacity of shallow foundation using soft computing
Jagan, J.; Chowdhury, Swaptik; Goyal, Pratik; Samui, Pijush; Dalkiliç, Yildirim
The ultimate bearing capacity is an important criterion for the successful implementation of any geotechnical projects. This chapter studies the feasibility of employing Gaussian process regression (GPR), Extreme learning machine (ELM) and Minimax probability machine regression (MPMR) for prediction of ultimate bearing capacity of shallow foundation based on cohesionless soils. The developed models have been compared on the basis of coefficient of relation (R) values (GPR= 0.9625, ELM= 0.938, MPMR= 0.9625). The results show that MPMR is more efficient tool but the models of GPR and ELM also gives satisfactory results.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2016Utilization of SVM, LSSVM and GP for predicting the medical waste generation
Jagan, J.; Dalkilç, Yildirim; Samui, Pijush
The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2016Determination of bearing capacity of shallow foundation using soft computing
Jagan, J.; Goyal, Pratik; Chowdhury, Swaptik; Samui, Pijush; Dalkiliç, Yildirim
The ultimate bearing capacity is an important criterion for the successful implementation of any geotechnical projects. This chapter studies the feasibility of employing Gaussian process regression (GPR), Extreme learning machine (ELM) and Minimax probability machine regression (MPMR) for prediction of ultimate bearing capacity of shallow foundation based on cohesionless soils. The developed models have been compared on the basis of coefficient of relation (R) values (GPR= 0.9625, ELM= 0.938, MPMR= 0.9625). The results show that MPMR is more efficient tool but the models of GPR and ELM also gives satisfactory results.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2016Design optimization of a wind turbine using artificial intelligence
Jayabalan, Jagan; Yildirim, Dalkilic; Kim, Dookie; Samui, Pijush
This chapter examines the capability of Support Vector Machine (SVM), Relevance Vector Machine (RVM) and Genetic Programming (GP) for the optimal design of wind turbine. The excellent design has been influenced by various factors, such as profile of the blade, number of blades, power factor and tip speed ratio. The key to design a wind turbine is to Assessing the optimal tip speed ratio (TSR) is the key for designing the wind turbine. This chapter handles the Artificial Intelligence techniques in predicting the optimal TSR and the power factor based on the parameters engaged for NACA 4415 and LS-1 profile types with 3 and 4 blades. The organized machine learning framework is anticipated to be lucrative than the traditional way in foretelling the TSR and power factor. The machine learning models are then compared with the existing Neural Network model and the pros and cons of the various models are inferred from the results.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2015Reliability analysis of slope using MPMR, GRNN and GPR
Subburaman, Dhivya; Jagan, J.; Dalkiliç, Yildirim; Samui, Pijush
First Order Second Moment Method (FOSM) is generally for determination of reliability of slope. This article adopts Minimax Probability Machine Regression (MPMR), Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) for reliability analysis of slope by using FOSM. In this study, an example of soil slope is given regarding how the proposed GPR-based FOSM, MPMR-based FOSM and GRNN-based FOSM analysis can be carried out. GPR, GRNN and MPMR have been used as regression techniques. A comparative study has been carried out between the developed GPR, MPMR and GRNN models. The results show that MPMR gives better performance than the other models.
RDL Kalıcı Kaydıİncele - Book ChapterAçık Erişim2015Minimax probability machine: A new tool for modeling seismic liquefaction data
Samui, Pijush; Dalkiliç, Yildirim Huseyin; Rajadurai, Hariharan; Jagan, J.
Liquefaction in soil is one of the other major problems in geotechnical earthquake engineering. This chapter adopts Minimax Probability Machine (MPM) for prediction of seismic liquefaction potential of soil based on Shear Wave Velocity (Vs) data. MPM has been used as a classification technique. Two models (MODEL I and MODEL II) have been adopted. In MODEL I, input variables are Cyclic Stress Ratio (CSR), and Vs MODEL II uses Peck Ground Acceleration (PGA) and Vs as input variables. The developed MPM has been compared with the Artificial Neural Network (ANN) and Support Vector Machine (SVM) models. The developed MPM is a robust tool for determination of liquefaction susceptibility of soil.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2015Site characterization using GP, MARS and GPR
Samui, Pijush; Dalkiliç, Yildirim; Jagan, J.
This article examines the capability of Genetic Programming (GP), Multivariate Adaptive Regression Spline (MARS) and Gaussian Process Regression (GPR) for developing site characterization model of Bangalore (India) based on corrected Standard Penetration Test (SPT) value (Nc). GP, MARS and GPR have been used as regression techniques. GP is developed based on genetic algorithm. MARS does not assume any functional relationship between input and output variables. GPR is a probabilistic, non-parametric model. In GPR, different kinds of prior knowledge can be applied. In three dimensional analysis, the function.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2014Modeling of wind speed profile using soft computing techniques
Samui, Pijush; Dalkiliç, Yildirim
This chapter examines the capability of three soft computing techniques (Genetic Programming [GP], Support Vector Machine [SVM], and Multivariate Adaptive Regression Spline [MARS]) for prediction of wind speed in Nigeria. Latitude, longitude, altitude, and the month of the year have been used as inputs of GP, RVM, and MARS models. The output of GP, SVM, and MARS is wind speed. GP, SVM, and MARS have been used as regression techniques. To develop GP, MARS, and SVM, the datasets have been divided into the following two groups: 1) Training Dataset - this is required to develop GP, MPMR, and RVM models. This study uses 18 stations' data as a training dataset. 2) Testing Dataset - this is required to verify the developed GP, MPMR, and RVM models. The remaining 10 stations data have been used as testing dataset. Radial basis function has been used as kernel functions for SVM. A detailed comparative study between the developed GP, SVM, and MARS models is performed in this chapter.
RDL Kalıcı Kaydıİncele - Book ChapterYalnız künye2014GPR and RVM-based predictions of surface and hole quality in drilling of AISI D2 cold work tool steel
Samui, Pijush; Yildirim Dalkilic, H.
This chapter examines the capability of Gaussian Process Regression (GPR) and Relevance Vector Machine (RVM) for prediction of surface and hole quality in drilling of AISI D2 cold work tool steel. This chapter uses GPR and RVM as regression techniques. The database contains information about cutting tool, feed rate, cutting speed, surface roughness, and roundness error. Cutting tool, feed rate, and cutting speed are considered inputs of GPR and RVM. The outputs of GPR and RVM are surface roughness and roundness error. In RVM, radial basis function is adopted as kernel function. GPR uses radial basis function as covariance function. The obtained variance can be used to determine uncertainty. A sensitivity analysis is also carried out. This chapter gives robust models based on RVM and GPR for prediction of surface and hole quality in drilling of AISI D2 cold work tool steel.
RDL Kalıcı Kaydıİncele