Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12507/675

Listeleniyor 1 - 20 / 23

Performance comparison of different regression methods for VO2max ESTIMATION [VO2max tahmini için farkli regresyon yöntemlerinin performans Karsilastirmas]
(2013) Aktürk, Erman; Akay, Mehmet Fatih; Kilitçioğlu, Hasan
The purpose of this paper is to develop maximal oxygen uptake (VO 2max) models by using different regression methods such as Multilayer Feed-Forward Artificial Neural Networks (MFANN's), Support Vector Regression (SVR), Generalized Regression Neural Networks (GRNN's) and Multiple Linear Regression (MLR). The dataset includes data of 439 subjects and the input variables of the dataset are gender, age, body mass index (BMI), percent body fat (BF), respiratory exchange ratio (RER) from treadmill test, self-reported rating of perceived exertion (RPE) from treadmill test, heart rate (HR) and time to exhaustion from treadmill test. The performance of the models is evaluated by calculating their standard error of estimates (SEE) and multiple correlation coefficients (R). The results suggest that MFANN-based VO2max prediction models perform better than other prediction models.
Efficiency of the generalized-difference-based weighted mixed almost unbiased two-parameter estimator in partially linear model
(TAYLOR & FRANCIS INC, 2017) Akdeniz, Fikri; Roozbeh, Mahdi
In this paper, a generalized difference-based estimator is introduced for the vector parameter in partially linear model when the errors are correlated. A generalized-difference-based almost unbiased two-parameter estimator is defined for the vector parameter . Under the linear stochastic constraint r = R + e, we introduce a new generalized-difference-based weighted mixed almost unbiased two-parameter estimator. The performance of this new estimator over the generalized-difference-based estimator and generalized- difference-based almost unbiased two-parameter estimator in terms of the MSEM criterion is investigated. The efficiency properties of the new estimator is illustrated by a simulation study. Finally, the performance of the new estimator is evaluated for a real dataset.
Restricted estimator in two seemingly unrelated regression model
(unıv punjab, 2016) Erdugan, Funda; Akdeniz, Fikri
This article is concerned with the estimation problem of multicollinearity in two seemingly unrelated regression (SUR) equations with linear restrictions. We propose a restricted feasible SUR estimates of the regression coefficients of this model and compare with feasible generalized least squares (FGLS) estimator and the estimator proposed by Revankar (1974) in the matrix mean square error sense. The ideas in the article are evaluated using Monte Carlo simulation.
A search for supernova remnants in the nearby spiral galaxy M 74 (NGC 628)
(2010) Sonbaş, E.; Akyüz, A.; Balman, Ş.; Özel, Mehmet Emin
An optical search was carried out for supernova remnants (SNRs) in the Sc type nearby spiral galaxy M74, using ground-based observations at the TUBITAK National Observatory (TUG, Antalya/Turkey) and the Special Astrophysics Observatory (SAO, Russia). Observations were supplemented by the spectral analysis of archived X-ray data from XMM-Newton and Chandra. The survey of M74 covered ?9 arcmin2 with [S II], H?, and their continuum filters. Interference filter images of M74 were obtained the with the 1.5 m Russian Turkish Telescope (RTT150) at TUG and spectral data taken with the 6 m Bolsoi Azimuthal Telescope (BTA) at SAO. The emission nebulae with continuum-subtracted line ratio values of [S II]??6716,6731 /H? ? 0.4 are identified as SNRs. Followup spectroscopy confirmed optical SNR identifications. We have identified nine new SNR candidates in M74 with [S II]/H? ? 0.4 as the basic criterion. The [S II]/H? ratio ranges from 0.40 to 0.91 and H? intensities from 2.8 × 10 -15 erg cm-2 s-1 to 1.7 × 10 -14 erg cm-2 s-1. We also present spectral follow-up observations of these SNR candidates, however, we are able to spectrally confirm only three of them (SNR2, SNR3, and SNR5). The lack of confirmation for the rest might come from contamination by the nearby H II emission regions, as well as from the inaccurate positioning of the long slit on these objects. In addition, we searched the XMM-Newton and Chandra Observatory archival data for the X-ray counterparts to the optically identified candidates. We find positional coincidence with only three SNR candidates, SNR1, SNR2, and SNR8. The spectrum of SNR2 yields a shock temperature of 10.8 keV with an ionization timescale of 1.6 × 10-10 s cm-3, indicating a relatively young remnant in an early Sedov phase, which is not supported by our optical wavelength analysis. Given the high luminosity of 10-39 erg s-1 and the characteristics of the X-ray spectrum, we favor an ultra luminous X-ray source interpretation for this source associated with an SNR.We calculated an X-ray flux upper limit of 9.0 × 10-15 erg cm-2 s-1 for the rest of the SNRs, including spectroscopically identified SNR3 and SNR5.
A new difference-based weighted mixed Liu estimator in partially linear models
(TAYLOR & FRANCIS LTD, 2018) Akdeniz, Esra; Akdeniz, Fikri; Roozbeh, Mahdi
In this paper, a generalized difference-based estimator is introduced for the vector parameter beta in the partially linear model when the errors are correlated. A generalized difference-based Liu estimator is defined for the vector parameter beta. Under the linear stochastic constraint r = R beta + e, a new generalized difference-based weighted mixed Liu estimator is introduced. The performance of this estimator over the generalized difference-based weighted mixed estimator and the generalized difference-based Liu estimator in terms of the mean squared error matrix criterion is investigated. Then, a method to select the biasing parameter d and non-stochastic weight. is considered. The efficiency properties of the newestimator are illustrated by a simulation study. Finally, the performance of the new estimator is evaluated for a real data set.
Lookıng into the fireball: rotse-ııı and swıft observatıons of early gamma-ray burst afterglows
(IOP PUBLISHING LTD, 2009) Rykoff, E. S.; Aharonian, F.; Akerlof, C. W.; Ashley, M. C. B.; Barthelmy, S. D.; Flewelling, H. A.; Gehrels, N.; Gogus, E.; Guver, T.; Kiziloglu, Ue.; Krimm, H. A.; McKay, T. A.; Özel, Mehmet; Phillips, A.; Quimby, R. M.; Rowell, G.; Rujopakarn, W.; Schaefer, B. E.; Smith, D. A.; Vestrand, W. T.; Wheeler, J. C.; Wren, J.; Yuan, F.; Yost, S. A.
We report on a complete set of early optical afterglows of gamma-ray bursts (GRBs) obtained with the Robotic Optical Transient Search Experiment (ROTSE-III) telescope network from 2005 March through 2007 June. This set is comprised of 12 afterglows with early optical and Swift/X-Ray Telescope observations, with a median ROTSE-III response time of 45 s after the start of gamma-ray emission (8 s after the GCN notice time). These afterglows span 4 orders of magnitude in optical luminosity, and the contemporaneous X-ray detections allow multi-wavelength spectral analysis. Excluding X-ray flares, the broadband synchrotron spectra show that the optical and X-ray emission originate in a common region, consistent with predictions of the external forward shock in the fireball model. However, the fireball model is inadequate to predict the temporal decay indices of the early afterglows, even after accounting for possible long-duration continuous energy injection. We find that the optical afterglow is a clean tracer of the forward shock, and we use the peak time of the forward shock to estimate the initial bulk Lorentz factor of the GRB outflow, and find 100 less than or similar to Gamma(0) less than or similar to 1000, consistent with expectations.
Neural network based VO2max prediction models using maximal exercise and non-exercise data [Maksimal egzersiz ve egzersize dayali olmayan verileri kullanarak sinir agi tabanli VO2MAX tahmin modelleri]
(2013) Aktarla ,Ece; Akay, Mehmet Fatih; Aktürk, Erman; Açikkar, Mustafa
Artificial Neural Network (ANN) models based on maximal and non-exercise (N-Ex) variables are developed to predict maximal oxygen uptake (VO 2max) the input variables of the dataset are gender, age, body mass index (BMI), grade, selfreported rating of perceived exertion (RPE) from treadmill test, heart rate (HR), perceived functional ability (PFA) and physical activity rating (PA-R). The performance of the models is evaluated by calculating their standard error of estimate (SEE) and multiple correlation coefficient (R). The results suggest that the performance of VO2max prediction models based on maximal and standard N-Ex variables (i.e. gender, age, BMI etc) can be improved by including questionnaire variables (PFA and PA-R) in the models.
Generalized difference-based weighted mixed almost unbiased ridge estimator in partially linear models
(Springer New York LLC, 2017) Akdeniz, Fikri; Roozbeh, Mehdi
In this paper, a generalized difference-based estimator is introduced for the vector parameter (Formula presented.) in partially linear model when the errors are correlated. A generalized difference-based almost unbiased ridge estimator is defined for the vector parameter (Formula presented.). Under the linear stochastic constraint (Formula presented.), a new generalized difference-based weighted mixed almost unbiased ridge estimator is proposed. The performance of this estimator over the generalized difference-based weighted mixed estimator, the generalized difference-based estimator, and the generalized difference-based almost unbiased ridge estimator in terms of the mean square error matrix criterion is investigated. Then, a method to select the biasing parameter k and non-stochastic weight (Formula presented.) is considered. The efficiency properties of the new estimator is illustrated by a simulation study. Finally, the performance of the new estimator is evaluated for a real dataset.
Optical parameters of calix[4]arene films and their response to volatile organic vapors
(ELSEVIER SCIENCE SA, 2011) Özbek, Z.; Capan, R.; Göktas, H.; Şen, S.; İnce, F. G.; Özel, Mehmet Emin; Davis, F.
The Langmuir-Blodgett (LB) technique was employed to produce thin LB films using an amphiphilic calix-4-resorcinarene onto different substrates such as quartz, gold coated glass and quartz crystals. The characteristics of the calix LB films are assessed by UV-visible, quartz crystal microbalance (QCM) and surface plasmon resonance (SPR) measurements. UV-vis and QCM measurements indicated that this material deposited very well onto the solid substrates with a transfer ratio of >0.95. Using SPR data, the thickness and refractive index of this LB film are determined to be 1.14 nm/deposited layer and 1.6 respectively. The sensing application of calixarene LB films towards volatile organic vapors such as chloroform, benzene, toluene and ethanol vapors is studied by the SPR technique. The response of this LB film to saturated chloroform vapor is much larger than for the other vapors. The response is fast and fully recoverable. It can be proposed that this sensing material deposited onto gold coated glass substrates has a good sensitivity and selectivity for chloroform vapor. This material may also find potential applications in the development of room temperature organic vapor sensing devices.
Performance comparison of different regression methods for vo(2)max estimation
(IEEE, 2013) Akturk, Erman; Akay, M. Fatih; Kilitcioglu, Hasan
The purpose of this paper is to develop maximal oxygen uptake (VO(2)max) models by using different regression methods such as Multilayer Feed-Forward Artificial Neural Networks (MFANN's), Support Vector Regression (SVR), Generalized Regression Neural Networks (GRNN's) and Multiple Linear Regression (MLR). The dataset includes data of 439 subjects and the input variables of the dataset are gender, age, body mass index (BMI), percent body fat (BF), respiratory exchange ratio (RER) from treadmill test, self-reported rating of perceived exertion (RPE) from treadmill test, heart rate (HR) and time to exhaustion from treadmill test. The performance of the models is evaluated by calculating their standard error of estimates (SEE) and multiple correlation coefficients (R). The results suggest that MFANN-based VO(2)max prediction models perform better than other prediction models.
Grb 081008: from burst to afterglow and the transıtıon phase ın between
(IOP PUBLISHING LTD, 2010) Yuan, F.; Schady, P.; Racusin, J. L.; Willingale, R.; Kruehler, T.; O'Brien, P. T.; Greiner, J.; Oates, S. R.; Rykoff, E. S.; Aharonian, F.; Akerlof, C. W.; Ashley, M. C. B.; Barthelmy, S. D.; Filgas, R.; Flewelling, H. A.; Gehrels, N.; Goegues, E.; Guever, T.; Horns, D.; Kiziloglu, Ue.; Krimm, H. A.; McKay, T. A.; Özel, Mehmet Emin; Phillips, A.; Quimby, R. M.; Rowell, G.; Rujopakarn, W.; Schaefer, B. E.; Vestrand, W. T.; Wheeler, J. C.; Wren, J.
We present a multi-wavelength study of GRB 081008, at redshift 1.967, by Swift, ROTSE-III, and Gamma-Ray Burst Optical/NearInfrared Detector. Compared to other Swift GRBs, GRB 081008 has a typical gamma-ray isotropic equivalent energy output (similar to 10(53) erg) during the prompt phase, and displayed two temporally separated clusters of pulses. The early X-ray emission seen by the Swift X-Ray Telescope was dominated by the softening tail of the prompt emission, producing multiple flares during and after the Swift Burst Alert Telescope detections. Optical observations that started shortly after the first active phase of gamma-ray emission showed two consecutive peaks. We interpret the first optical peak as the onset of the afterglow associated with the early burst activities. A second optical peak, coincident with the later gamma-ray pulses, imposes a small modification to the otherwise smooth light curve and thus suggests a minimal contribution from a probable internal component. We suggest the early optical variability may be from continuous energy injection into the forward shock front by later shells producing the second epoch of burst activities. These early observations thus provide a potential probe for the transition from the prompt phase to the afterglow phase. The later light curve of GRB 081008 displays a smooth steepening in all optical bands and X-ray. The temporal break is consistent with being achromatic at the observed wavelengths. Our broad energy coverage shortly after the break constrains a spectral break within optical. However, the evolution of the break frequency is not observed. We discuss the plausible interpretations of this behavior.
Characterization oflLangmuir-blodgett films of a calix[8]arene and sensing properties towards volatile organic vapors
(ELSEVIER SCIENCE SA, 2010) Çapan, R.; Özbek, Z.; Göktas, H.; Şen, S.; Ince, F. G.; Özel, Mehmet Emin; Stanciu, G. A.; Davis, F.
Within this article, we report the characterization and organic vapor sensing properties of Langmuir-Blodgett (LB) thin films of calix[8]arenes. Surface pressure-area isotherms show that very stable monolayers are formed at the air-water interface. The LB film could be deposited onto different substrates which allowed the films to be characterized by UV, quartz crystal microbalance (QCM), surface plasmon resonance (SPR) and atomic force microscopy (AFM). The results indicate that good quality, uniform LB films can be prepared with transfer ratios of over 0.95. QCM results showed that the deposited mass of calix[8]arene monolayer onto a quartz crystal decreased from 693 to 204 ng as the number of layers is increased. AFM studies showed a smooth, and void free surface morphology with a rms value of 1.202 nm. The sensing abilities of this LB film towards the development of room temperature organic vapor sensing devices are also studied. Responses of the LB films to various vapors are fast, large, and reversible. It was found that the obtained LB film is significantly more sensitive to chloroform than other vapors. It can be concluded that this molecule could have a potential application in the research area of room temperature vapor sensing devices.
Efficiency of the generalized difference-based liu estimators in semiparametric regression models with correlated errors
(TAYLOR & FRANCIS LTD, 2015) Akdeniz, Fikri; Duran, Esra Akdeniz; Roozbeh, Mahdi; Arashi, Mohammad
In this paper, a generalized difference-based estimator is introduced for the vector parameter beta in the semiparametric regression model when the errors are correlated. A generalized difference-based Liu estimator is defined for the vector parameter beta in the semiparametric regression model. Under the linear nonstochastic constraint R beta=r, the generalized restricted difference-based Liu estimator is given. The risk function for the beta(GRD)(eta) associated with weighted balanced loss function is presented. The performance of the proposed estimators is evaluated by a simulated data set.
p-phthalimidobenzoic thin film for volatile organic vapor detection
(2010) Şen, Sibel; Çapan, Rifat; Özel, Mehmet Emin; Hassan A.K.; Namli H.; Turhan O.
Thin films of the molecule of p-phthalimidobenzoic acid (FIBA) have been deposited by spin coating and are studied for application as sensing membrane for the detection of alcohols. Atomic force microscopy (AFM) and surface plasmon resosnance (SPR) were used for the characterisation of the FIBA films. Alcohol sensing properties of the obtained films were examined using SPR measurements. AFM images show that FIBA films have the large surface roughness with an estimated roughness RMS value of 6.3 nm. Films with such compact and granular morphology are believed to provide improved sensitivity when used in sensor applications. The measured SPR curves were analysed by applying a least square fitting procedure using Fresnel's reflection theory. FIBA film used as a sensing element for the detection of saturated 2-propanol, ethanol and methanol vapors. Fast response and recovery for all studied analytes have been obtained. These results show that thin films made with this FIBA molecule are demonstrating good suitability for room temperature vapor application.
Existence of absorbing set for a nonlinear wave equation
(2002) Kurt , Ayfer
We prove the existence of an absorbing set for a Cauchy problem involving a nonlinear wave equation.
On the classical Maki-Thompson rumour model in continuous time
(SPRINGER, 2011) Belen, Selma; Kropat, Erik; Weber, Gerhard-Wilhelm
In this paper, the Maki-Thompson model is slightly refined in continuous time, and a new general solution is obtained for each dynamics of spreading of a rumour. It is derived an equation for the size of a stochastic rumour process in terms of transitions. We give new lower and upper bounds for the proportion of total ignorants who never learned a rumour and the proportion of total stiflers who either forget the rumour or cease to spread the rumour when the rumour process stops, under general initial conditions. Simulation results are presented for the analytical solutions. The model and these numerical results are capable to explain the behaviour of the dynamics of any other dynamical system having interactions similar to the ones in the stochastic rumour process and requiring numerical interpretations to understand the real phenomena better. The numerical process in the differential equations of the model is investigated by using error-estimates. The estimated error is calculated by the Runge-Kutta method and found either negligible or zero for a relatively small size of the population. This pioneering paper introduces a new mathematical method into Operations research, motivated by various areas of scientific, social and daily life, it presents numerical computations, discusses structural frontiers and invites the interested readers to future research.
The distribution of the Liu-type estimator of the biasing parameter in elliptically contoured models
(Taylor & Francıs ınc, 2017) Arashi, M.; Nadarajah, Saralees; Akdeniz, Fikri
We derive the density function of the stochastic shrinkage parameters of the Liu-type estimator in elliptical models. The correctness of derivation is checked by simulations. A real data application is also provided.
Revıvıng some geometrıc aspects of shrınkage estımatıon ın lınear models
(ANKARA UNIV, FAC SCI, 2019) Akdeniz, Fikri; Özturk, Fikri
It is well known that the least squares estimator is the best linear unbiased estimator of the parameter vector in a classical linear model. But, it is 'too long' as a vector and unreliable, confidence intervals are broad for some components especially in the case of multicollinearity. Shrinkage (contraction) type estimators are efficient remedial tools in order to solve problems caused by multicollinearity. In this study, we consider a class of componentwise shrunken estimators with typical members: Mayer and Willke's contraction estimator, Marquardt's principal component estimator, Hoerl and Kennard's ridge estimator, Liu's linear unified estimator and a discrete shrunken estimator. All estimators considered are "shorter" than the least squares estimator with respect to the Euclidean norm, biased, but insensitive to multicollinearity and admissible within the set of linear estimators with respect to unweighted squared error risk. Some behaviors of these estimators are illustrated geometrically by tracing their trajectories as functions of shrinkage factors in a two-dimensional parameter space.
Thin film characterization of novel phthalimide materials
(NATL INST OPTOELECTRONICS, 2011) Şen, Sibel; Capan, Rifat; Ozel, Mehmet Emin; Hassan, A. K.; Turhan, O.; Namli, H.
Spin coating technique is employed to produce thin phthalimide films using novel p-phthalimidobenzoic acid (FIBA) and N-(phthalimido)-p-aminobenzoic acid (FIABA) materials. Several spin speeds and various solution concentrations are chosen to monitor the thin film deposition process of these new materials. The optical properties are studied using UV-visible spectroscopy and spectroscopic ellipsometry methods. The absorption of the FIBA and FIABA films against the spin speed showed an exponential behavior. pi -> pi* transition is occurred. The thicknesses of thin films at 2000 rpm are obtained 15.86 nm for FIBA and 12.99 nm for FIABA using spectroscopic ellipsometry results.
Xmm-newton observatıons of lumınous sources ın nearby galaxıes ngc 4395, ngc 4736, and ngc 4258
(IOP PUBLISHING LTD, 2013) Akyuz, A.; Kayaci, S.; Avdan, H.; Özel, Mehmet Özel; Sonbas, E.; Balman, S.
We present the results of a study of non-nuclear discrete sources in a sample of three nearby spiral galaxies (NGC 4395, NGC 4736, and NGC 4258) based on XMM-Newton archival data supplemented with Chandra data for spectral and timing analyses. A total of 75 X-ray sources have been detected within the D-25 regions of the target galaxies. The large collecting area of XMM-Newton makes the statistics sufficient to obtain spectral fitting for 16 (about 20%) of these sources. Compiling the extensive archival exposures available, we were able to obtain the detailed spectral shapes of diverse classes of point sources. We have also studied temporal properties of these luminous sources. Eleven of them are found to show short-term (less than 80 ks) variation while eight of them show long-term variation within factors of similar to 2-5 during a time interval of similar to 2-12 years. Timing analysis provides strong evidence that most of these sources are accreting X-ray binary systems. One source that has properties different from others was suspected to be a supernova remnant, and our follow-up optical observation confirmed this. Our results indicate that sources within the three nearby galaxies are showing a variety of source populations, including several ultraluminous X-ray sources, X-ray binaries, transients together with a super soft source, and a background active galactic nucleus candidate.

Güncel Gönderiler