Ilhan Usta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ilhan Usta has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Yeliz Mert Kantar
14 shared publicationsIbrahim Arik
6 shared publicationsIsmail Yenilmez
6 shared publications- Aladdin Shamilov
Baku State University
2 shared publications Cigdem Giriftinoglu
Anadolu University, Faculty of Science, Department of Statistics, 26470 Eskisehir, Turkey
1 shared publicationHasan Ocak
Kocaeli Univ, Dept Mechatron Engn, Kocaeli, Turkey
1 shared publication
Latest Publications
- 3 May 2022
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 53 (5) , 2527-2553
Bayesian estimation for geometric process with the Weibull distribution
In this paper, we focus on Bayesian estimation of the parameters in the geometric process (GP) in which the first occurrence time of an event is assumed to have Weibull distribution. The Bayesian estimators are derived based on both symmetric (Squared Error) and asymmetric (General Entropy, LINEX) loss functions. Since the Bayesian estimators of unknown parameters cannot be obtained analytically, Lindley’s approximation and the Markov Chain Monte Carlo (MCMC) methods are applied to compute the Bayesian estimates. Furthermore, by using the MCMC methods, credible intervals of the parameters are constructed. Maximum likelihood (ML) estimators are also derived for unknown parameters. The confidence intervals of the parameters are obtained based on an asymptotic distribution of ML estimators. Moreover, the performances of the proposed Bayesian estimators are compared with the corresponding ML, modified moment and modified maximum likelihood estimators through an extensive simulation study. Finally, analyses of two different real data sets are presented for illustrative purposes.
- 3 May 2022
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 53 (5) , 2527-2553
Bayesian estimation for geometric process with the Weibull distribution
In this paper, we focus on Bayesian estimation of the parameters in the geometric process (GP) in which the first occurrence time of an event is assumed to have Weibull distribution. The Bayesian estimators are derived based on both symmetric (Squared Error) and asymmetric (General Entropy, LINEX) loss functions. Since the Bayesian estimators of unknown parameters cannot be obtained analytically, Lindley’s approximation and the Markov Chain Monte Carlo (MCMC) methods are applied to compute the Bayesian estimates. Furthermore, by using the MCMC methods, credible intervals of the parameters are constructed. Maximum likelihood (ML) estimators are also derived for unknown parameters. The confidence intervals of the parameters are obtained based on an asymptotic distribution of ML estimators. Moreover, the performances of the proposed Bayesian estimators are compared with the corresponding ML, modified moment and modified maximum likelihood estimators through an extensive simulation study. Finally, analyses of two different real data sets are presented for illustrative purposes.
- 1 January 2022
- Published by Kare Publishing in Sigma Journal of Engineering and Natural Sciences
- Vol. 40 (1) , 27-44
Image processing based package volume measurement system using kinect sensor
In this study, an image processing based volume measurement system is presented. The proposed scheme provides high accuracy, low cost and ease of calibration. There are no additional requirements such as alignment of objects during measurement, positioning the objects at a certain position in the measuring field, and these advantages reduce the labor effort in real-time. In the first stage, a problem-specific calibration process was performed and then Hough transform was applied in the image processing phase. Although the proposed method has been developed primarily to measure the volume of box-type objects, it also provides an approximate volume measurement for objects of random geometry. The system tested under various external disturbances has produced satisfactory results.
- 1 January 2022
- Published by Kare Publishing in Sigma Journal of Engineering and Natural Sciences
- Vol. 40 (1) , 27-44
Image processing based package volume measurement system using kinect sensor
In this study, an image processing based volume measurement system is presented. The proposed scheme provides high accuracy, low cost and ease of calibration. There are no additional requirements such as alignment of objects during measurement, positioning the objects at a certain position in the measuring field, and these advantages reduce the labor effort in real-time. In the first stage, a problem-specific calibration process was performed and then Hough transform was applied in the image processing phase. Although the proposed method has been developed primarily to measure the volume of box-type objects, it also provides an approximate volume measurement for objects of random geometry. The system tested under various external disturbances has produced satisfactory results.
- 13 October 2020
- Published by River Publishers in Journal of Reliability and Statistical Studies
- Vol. 13 (1) , 87–112
Approximate Bayes Estimators of the Parameters of the Inverse Gaussian Distribution Under Different Loss Functions
Inverse Gaussian is a popular distribution especially in the reliability and life time modelling, and thus the estimation of its unknown parameters has received considerable interest. This paper aims to obtain the Bayes estimators for the two parameters of the inverse Gaussian distribution under varied loss functions (squared error, general entropy and linear exponential). In Bayesian procedure, we consider commonly used non-informative priors such as the vague and Jeffrey’s priors, and also propose using the extension of Jeffrey’s prior. In the case where the two parameters are unknown, the Bayes estimators cannot be obtained in the closed-form. Hence, we employ two approximation methods, namely Lindley and Tierney Kadane (TK) approximations, to attain the Bayes estimates of the parameters. In this paper. the effects of considered loss functions, priors and approximation methods on Bayesian parameter estimation are also presented. The performance of Bayes estimates is compared with the corresponding classical estimates in terms of the bias and the relative efficiency throughout an extensive simulation study. The results of the comparison show that Bayes estimators obtained by TK method under linear exponential loss function using the proposed prior outperform the other estimators for estimating the parameters of inverse Gaussian distribution most of the time. Finally, a real data set is provided to illustrate the results.
- 13 October 2020
- Published by River Publishers in Journal of Reliability and Statistical Studies
- Vol. 13 (1) , 87–112
Approximate Bayes Estimators of the Parameters of the Inverse Gaussian Distribution Under Different Loss Functions
Inverse Gaussian is a popular distribution especially in the reliability and life time modelling, and thus the estimation of its unknown parameters has received considerable interest. This paper aims to obtain the Bayes estimators for the two parameters of the inverse Gaussian distribution under varied loss functions (squared error, general entropy and linear exponential). In Bayesian procedure, we consider commonly used non-informative priors such as the vague and Jeffrey’s priors, and also propose using the extension of Jeffrey’s prior. In the case where the two parameters are unknown, the Bayes estimators cannot be obtained in the closed-form. Hence, we employ two approximation methods, namely Lindley and Tierney Kadane (TK) approximations, to attain the Bayes estimates of the parameters. In this paper. the effects of considered loss functions, priors and approximation methods on Bayesian parameter estimation are also presented. The performance of Bayes estimates is compared with the corresponding classical estimates in terms of the bias and the relative efficiency throughout an extensive simulation study. The results of the comparison show that Bayes estimators obtained by TK method under linear exponential loss function using the proposed prior outperform the other estimators for estimating the parameters of inverse Gaussian distribution most of the time. Finally, a real data set is provided to illustrate the results.
- 1 May 2018
- Published by Elsevier in Energy Conversion and Management
- Vol. 164, 570-578
A new estimation approach based on moments for estimating Weibull parameters in wind power applications
- 1 May 2018
- Published by Elsevier in Energy Conversion and Management
- Vol. 164, 570-578
A new estimation approach based on moments for estimating Weibull parameters in wind power applications
- 1 April 2018
- Published by Elsevier in Renewable Energy
- Vol. 118, 1024-1030
Wind speed analysis using the Extended Generalized Lindley Distribution
- 1 April 2018
- Published by Elsevier in Renewable Energy
- Vol. 118, 1024-1030
Wind speed analysis using the Extended Generalized Lindley Distribution
- 17 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Distributions of wind speed at different heights
In this study, the parameters of different distributions such as the Weibull, Rayleigh, Lognormal, Gamma and Generalized Gamma, which are used for modelling wind speed, at the different heights 10 and 30 m, have been evaluated. The monthly and annual variations of the scale parameters of the distributions and performances of the distributions for the wind speed over these different heights have been analyzed. The results have revealed that, the best distribution at 10 m also provides good fit to wind speed observation at 30 m. Moreover, it is observed from results that according to goodness-of-fit tests, the Gamma, Generalized Gamma and Weibull distributions are found to be more suitable than the other considered distributions for representing the actual wind speed data for both heights.
- 17 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Distributions of wind speed at different heights
In this study, the parameters of different distributions such as the Weibull, Rayleigh, Lognormal, Gamma and Generalized Gamma, which are used for modelling wind speed, at the different heights 10 and 30 m, have been evaluated. The monthly and annual variations of the scale parameters of the distributions and performances of the distributions for the wind speed over these different heights have been analyzed. The results have revealed that, the best distribution at 10 m also provides good fit to wind speed observation at 30 m. Moreover, it is observed from results that according to goodness-of-fit tests, the Gamma, Generalized Gamma and Weibull distributions are found to be more suitable than the other considered distributions for representing the actual wind speed data for both heights.
- 17 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A statistical investigation on wind energy potential of Northwest of Turkey
The northwest of Turkey is an important region which is a rapidly developing industrial center. Thus, energy analysis of this region has a high importance for the region's geopolitical, economic and demographic structure. In this study, wind energy potential of three regions in northwest of Turkey is evaluated using wind speed data collected from three stations. The Weibull, Rayleigh and generalized Gamma distributions are used for modeling wind speed data and estimating wind power. It is concluded from analyses that one of the mentioned regions has moderate level wind power potential which can be adequate for mechanical energy applications such as local consumption, agricultural applications and water pumping, other two regions are fairly good locations in terms of wind generation potential.
- 17 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A statistical investigation on wind energy potential of Northwest of Turkey
The northwest of Turkey is an important region which is a rapidly developing industrial center. Thus, energy analysis of this region has a high importance for the region's geopolitical, economic and demographic structure. In this study, wind energy potential of three regions in northwest of Turkey is evaluated using wind speed data collected from three stations. The Weibull, Rayleigh and generalized Gamma distributions are used for modeling wind speed data and estimating wind power. It is concluded from analyses that one of the mentioned regions has moderate level wind power potential which can be adequate for mechanical energy applications such as local consumption, agricultural applications and water pumping, other two regions are fairly good locations in terms of wind generation potential.
- Open Access
- 24 September 2015
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Analysis of the Modified Weibull Distribution for Estimation of Wind Speed Distribution
Finding suitable wind speed distribution is one of the most important tasks for the correct estimation of wind energy potential of the specified region. The Weibull distribution is the well-known and suggested distribution in estimating wind energy potential. However, in order to predict wind energy more correctly, new and flexible statistical distributions have been proposed in the last decade. In this study, we introduce a new modified Weibull distribution (MWD) for modelling wind speed and estimating wind power density and also we test MWD versus the classical Weibull distribution on real wind speed data measured in various regions of Turkey. The results of the analysis indicate that MWD suits well for most of the examined wind data cases. Therefore, MWD can be alternatively used for assessment of wind energy potential.
- 24 September 2015
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessAnalysis of the Modified Weibull Distribution for Estimation of Wind Speed Distribution
Finding suitable wind speed distribution is one of the most important tasks for the correct estimation of wind energy potential of the specified region. The Weibull distribution is the well-known and suggested distribution in estimating wind energy potential. However, in order to predict wind energy more correctly, new and flexible statistical distributions have been proposed in the last decade. In this study, we introduce a new modified Weibull distribution (MWD) for modelling wind speed and estimating wind power density and also we test MWD versus the classical Weibull distribution on real wind speed data measured in various regions of Turkey. The results of the analysis indicate that MWD suits well for most of the examined wind data cases. Therefore, MWD can be alternatively used for assessment of wind energy potential.