Yazar "Hardalac, Firat" seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Application of an adaptive neuro-fuzzy inference system for classification of Behcet disease using the fast Fourier transform method(Blackwell Publishing, 2007) Barisci, Necaattin; Hardalac, FiratIn this study, ophthalmic arterial Doppler signals were obtained from 200 subjects, 100 of whom suffered from ocular Behcet disease while the rest were healthy subjects. An adaptive neuro-fuzzy inference system (ANFIS) was used to detect the presence of ocular Behcet disease. Spectral analysis of the ophthalmic arterial Doppler signals was performed by the fast Fourier transform method for determining the ANFIS inputs. The ANFIS was trained with a training set and tested with a testing set. All these data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ocular Behcet disease. Performance indicators and statistical measures were used for evaluating the ANFIS. The correct classification rate was 94% for healthy subjects and 90% for unhealthy subjects suffering from ocular Behcet disease. The classification results showed that the ANFIS was effective at detecting ophthalmic arterial Doppler signals from subjects with Behcet disease.Öğe Comparison of MLP neural network and neuro-fuzzy system in transcranial doppler signals recorded from the cerebral vessels(Springer, 2008) Hardalac, FiratTranscranial Doppler signals recorded from cerebral vessels of 110 patients were transferred to a personal computer by using a 16 bit sound card. Spectral analyses of Transcranial Doppler signals were performed for determining the Multi Layer Perceptron (MLP) neural network and neuro Ankara-fuzzy system inputs. In order to do a good interpretation and rapid diagnosis, FFT parameters of Transcranial Doppler signals classified using MLP neural network and neuro-fuzzy system. Our findings demonstrated that 92% correct classification rate was obtained from MLP neural network, and 86% correct classification rate was obtained from neuro-fuzzy system.Öğe Examination of static and 50 Hz electric field effects on tissues by using a hybrid genetic algorithm and neural network(Wiley, 2008) Hardalac, Firat; Guler, GoknurThe effects of electric fields on tissue are the main subject of many investigations. The importance of this subject comes from the electrical properties of the cell membrane and its sensitivity to changes in electrical conditions. Permeability of membranes to various ions can change by the effect of an electric field depending on their conductivity. The performances of cells and tissues change due to differences between the membrane's permeability to various ions and molecules. The aim of this study was to determine lipid peroxidation and superoxide dismutase (SOD) levels in spleen and testis tissues exposed to different intensities and exposure periods of static and 50 Hz alternating electric fields. The increase in SOD and thiobarbituric acid reactive substance levels of spleen and testis tissues was found to depend significantly on the type of electric field and the exposure period. The experimental results are applied to a hybrid genetic algorithm and neural network as learning data and the training of the feedforward neural network is realized. At the end of this training, without applying electric field to tissues, the determination of the effects of the electric field on tissues by using a computer is predicted by the neural network. After the experiments, the prediction of the hybrid genetic algorithm and neural network approach is on average 99.25%-99.99%.Öğe Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines(Elsevier Sci Ltd, 2015) Kaytez, Fazil; Taplamacioglu, M. Cengiz; Cam, Ertugrul; Hardalac, FiratAccurate electricity consumption forecast has primary importance in the energy planning of the developing countries. During the last decade several new techniques are being used for electricity consumption planning to accurately predict the future electricity consumption needs. Support vector machines (SVMs) and least squares support vector machines (LS-SVMs) are new techniques being adopted for energy consumption forecasting. In this study, the LS-SVM is implemented for the prediction of electricity energy consumption of Turkey. In addition to the traditional regression analysis and artificial neural networks (ANNs) are considered. In the models, gross electricity generation, installed capacity, total subscribership and population are used as independent variables using historical data from 1970 to 2009. Forecasting results are compared using diverse performance criteria in this study with each other. Receiver operating characteristic (ROC) analysis is realized for determining the specificity and sensitivity of the empirical results. The results indicate that the proposed LS-SVM model is an accurate and a quick prediction method. (C) 2014 Elsevier Ltd. All rights reserved.Öğe Propagation of modified Bessel-Gaussian beams in turbulence(Elsevier Sci Ltd, 2008) Eyyuboglu, Halil Tanyer; Hardalac, FiratWe investigate the propagation characteristics of modified Bessel-Gaussian beams traveling in a turbulent atmosphere. The source beam formulation comprises a Gaussian exponential and the summation of modified Bessel functions. Based on an extended Huygens-Fresnel principle, the receiver plane intensity is formulated and solved down to a double integral stage. Source beam illustrations show that modified Bessel-Gaussian beams, except the lowest order case, will have well-like shapes. Modified Bessel-Gaussian beams with summations will experience lobe slicing and will display more or less the same profile regardless of order content. After propagating in turbulent atmosphere, it is observed that a modified Bessel-Gaussian beam will transform into a Bessel-Gaussian beam. Furthermore it is seen that modified Bessel-Gaussian beams with different Bessel function combinations, but possessing nearly the same profile, will differentiate during propagation. Increasing turbulence strength is found to accelerate the beam transformation toward the eventual Gaussian shape. (c) 2007 Elsevier Ltd. All rights reserved.
