Murat Sari

Prof. Murat Sari

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 April 2024 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
MSMurat Sari
Murat Sari
SDSerbay Duran
Serbay Duran
HKHuseyin Kutlu
Huseyin Kutlu
BGBulent Guloglu
Bulent Guloglu
ZAZehra Atik
Zehra Atik
Recent increases in global food demand have made this research and, therefore, the prediction of agricultural commodity prices, almost imperative. The aim of this paper is to build efficient artificial intelligence methods to effectively forecast commodity prices in light of these global events. Using three separate, well-structured models, the commodity prices of eleven major agricultural commodities that have recently caused crises around the world have been predicted. In achieving its objective, this paper proposes a novel forecasting model for agricultural commodity prices using the extreme learning machine technique optimized with the genetic algorithm. In predicting the eleven commodities, the proposed model, the extreme learning machine with the genetic algorithm, outperforms the model formed by the combination of long short-term memory with the genetic algorithm and the autoregressive integrated moving average model. Despite the fluctuations and changes in agricultural commodity prices in 2022, the extreme learning machine with the genetic algorithm model described in this study successfully predicts both qualitative and quantitative behavior in such a large number of commodities and over such a long period of time for the first time. It is expected that these predictions will provide benefits for the effective management, direction and, if necessary, restructuring of agricultural policies by providing food requirements that adapt to the dynamic structure of the countries.

19 August 2019 in Mathematics
Verified
Journal Article
Open access
PDF file
SGSeda Gulen
Seda Gulen
Catalin PopescuCatalin Popescu
Catalin Popescu
MSMurat Sari
Murat Sari
Since financial engineering problems are of great importance in the academic community, effective methods are still needed to analyze these models. Therefore, this article focuses mainly on capturing the discrete behavior of linear and nonlinear Black–Scholes European option pricing models. To achieve this, this article presents a combined method; a sixth order finite difference (FD6) scheme in space and a third–order strong stability preserving Runge–Kutta (SSPRK3) over time. The computed results are compared with available literature and the exact solution. The computed results revealed that the current method seems to be quite strong both quantitatively and qualitatively with minimal computational effort. Therefore, this method appears to be a very reliable alternative and flexible to implement in solving the problem while preserving the physical properties of such realistic processes.

11 December 2021 in Applied Artificial Intelligence
Verified
Journal Article
Open access
MSMurat Sari
Murat Sari
TCTahir Cosgun
Tahir Cosgun
IYIBRAHIM ERTUGRUL YALCIN
IBRAHIM ERTUGRUL YALCIN
MTMahmut Taner
Mahmut Taner
IOIbrahim Ilker Ozyigit
Ibrahim Ilker Ozyigit
The aim of this paper is to decide on heavy metal levels based on ecological parameters by effectively eliminating common disadvantages such as high cost and serious time-consuming laboratory procedures via an effective artificial intelligence approach. Therefore, this study is hinged on an artificial intelligence technique, ANN, because of its low cost and high accuracy in overcoming the mentioned limitations and obstacles in the determination process of the amounts of elements. The ANNs have thus been employed to determine essential heavy metals, such as Fe, Mn, and Zn depending on Ca, K, and Mg concentrations of soil samples obtained from different altitudes in Mount Ida. To the best knowledge of the authors, this is the first study in the literature in which altitude was considered as a parameter in the prediction of nutrient heavy metals. The computed relative errors are significantly low for each of the considered elements (Fe, Mn, and Zn); and are found to be between 1.0–4.1%, 1.0–4.2%, 1.5–7.1%, respectively, for the training, testing, and holdout data. The findings indicate that the relative errors could still be decreased further by assuming the altitude as a factor variable.

9 April 2022 in International Journal of Phytoremediation
Verified
Journal Article
Closed access
MSMurat Sari
Murat Sari
IYIBRAHIM ERTUGRUL YALCIN
IBRAHIM ERTUGRUL YALCIN
MTMahmut Taner
Mahmut Taner
TCTahir Cosgun
Tahir Cosgun
IOIbrahim Ilker Ozyigit
Ibrahim Ilker Ozyigit
This research is to predict heavy metal levels in plants, particularly in Robinia pseudoacacia L., and soils using an effective artificial intelligence approach with some ecological parameters, thereby significantly eliminating common defects such as high cost and seriously tedious and time-consuming laboratory procedures. In this respect, the artificial neural network (ANN) is employed to estimate the concentrations of essential heavy metals such as Fe, Mn and Ni, depending on the Cu and Zn concentrations of plant and soil samples collected from five different locations. The derived relative errors for the constructed ANN model have been computed within the ranges 0.041–0.051, 0.017–0.025, and 0.026–0.029 for the training, testing and holdout data regarding Fe, Mn, and Ni, respectively. In addition, it has been realized that the relative errors could be diminished up to 0.007 for Fe, 0.014 for Mn and 0.022 for Ni by considering the Cu, Zn, location and plant parts as independent variables during the analysis. The results produced seem instructive and pioneering for environmentalists and scientists to design optimal study programs to leave a livable ecosystem. The levels of essential heavy metals, Fe, Mn, Ni, based on Zn and Cu in plant and soil samples have been predicted through an AI-based prediction model, a class of feedforward artificial neural networks (ANNs) with a multilayer perceptron (MLP). Thereby common drawbacks such as high cost and severely time-consuming laboratory procedures have been significantly eradicated. In the evaluation of different pollution levels at locations, it has been shown that the ANN method can overcome several disadvantages of analytical element analyzers to monitor the amounts of heavy metals such as Fe, Mn, and Ni in soil and plants.

9 July 2023 in An International Journal of Optimization and Control: Theories & Applications (IJOCTA)
Verified
Journal Article
Open access
PDF file
AAArshed A. Ahmad
Arshed A. Ahmad
KSKhalid M. Saffer
Khalid M. Saffer
MSMurat Sari
Murat Sari
HUHande Uslu
Hande Uslu
Healthcare enables the maintenance of health through some physical and mental care for the prevention, diagnosis and treatment of disease. Diagnosis of anemia, one of the most common health problems of the age, is also very ambitious. Whereas, pathological individuals could be predicted through various biomedical variables using some appropriate methods. In order to estimate these individuals just by taking into account biological data, particle swarm optimization (PSO) and support vector machine (SVM) clustering techniques have been merged (PSO-SVM). In this respect, the dataset provided has been divided into five clusters based on anemia types consisting of 539 subjects in total, and the anemia values of each subject have been recorded according to corresponding biomedical variables taken as independent parameters. The findings of the PSO-SVM method have been compared to the results of the SVM algorithm. The hybrid PSO-SVM method has proven to be quite effective, particularly in terms of the high predictability of clustered disease types. it is possible to lead the successful creation of appropriate treatment programs for diagnosed patients without overlooking or wasting time during treatment.

7 January 2019 in International Journal of Numerical Methods for Heat & Fluid Flow
Verified
Journal Article
Closed access
UEUtku Erdoğan
Utku Erdoğan
MSMurat Sari
Murat Sari
HKHuseyin Kocak
Huseyin Kocak
Purpose: The purpose of this study is to propose a non-classical method to obtain efficient and accurate numerical solutions of the advection–diffusion–reaction equations. Design/methodology/approach: Unlike conventional numerical methods, this study proposes a numerical scheme using outer Newton iteration applied to a time-dependent PDE. The linearized time dependent PDE is discretized by trapezoidal rule, which is second order in time, and by spline-based finite difference method of fourth order in space. Findings: Using the proposed technique, even when relatively large time step sizes are used in computations, the efficiency of the proposed procedure is very clear for the numerical examples in comparison with the existing classical methods. Originality/value: This study, unlike these classical methods, proposes an alternative approach based on linearizing the nonlinear problem at first, and then discretizing it by an appropriate scheme. This technique helps to avoid considering the convergence issues of Newton iteration applied to nonlinear algebraic system containing many unknowns at each time step if an implicit method is used in time discretization. The linearized PDE can be solved by implicit time integrator, which enables the use of large time step size.