Yazar "Kavuran, Gurkan" seçeneğine göre listele
Listeleniyor 1 - 16 / 16
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Adaptive Control of Nonlinear TRMS Model by Using Gradient Descent Optimizers(Ieee, 2018) Alagoz, Baris Baykant; Tepljakov, Aleksei; Kavuran, Gurkan; Alisoy, HafizThis study demonstrates an application of direct gradient descent control for adaptively control of a nonlinear stable system models. The approach is based on utilization of gradient descent optimization techniques for the synthesis of control signals to control a specific plant model. In a former work, gradient descent optimizers were designed by considering a first degree instant input-output relation model assumption of the controlled system and this can allow model independent adaptive control of a class of plant models that can approximate to first order stable plant dynamics. The current study is an extension of this scheme for the purpose of nonlinear adaptive control. Here, we consider a higher degree polynomial assumption of instant input-output relations of the controlled system to obtain gradient descent optimizers that can be applied for adaptive control of a class of nonlinear systems. For evaluation of control performance of gradient descent optimizers, it is applied for the control of nonlinear TRMS model and the results are compared with performance of conventional PID control.Öğe Computation of Limit Cycles in Nonlinear Feedback Loops with Fractional Order Plants(Ieee, 2014) Atherton, Derek P.; Tan, Nusret; Yeroglu, Celaleddin; Kavuran, Gurkan; Yuce, AliThe paper deals with an aspect of the analysis of nonlinear feedback control systems with a fractional order transfer function. A review of the classical describing function (DF) method is given and its application to a control system with a fractional order plant is demonstrated. Unlike the DF method the frequency domain approach of Tsypkin is known to give exact results for limit cycles in relay systems and it is shown that this approach extends to systems with fractional order transfer functions. The formulation is done in terms of A loci which are related to and more general than the Tsypkin loci. Programs have been developed in MATLAB to compute the limit cycle frequency and also to show the results graphically. Examples are provided to illustrate the approach for a relay with no dead zone.Öğe COVID-19 and human development: An approach for classification of HDI with deep CNN(Elsevier Sci Ltd, 2023) Kavuran, Gurkan; Gokhan, Seyma; Yeroglu, CelaleddinThe measures taken during the pandemic have had lasting effects on people's lives and perceptions of the ability of national and multilateral institutions to drive human development. Policies that changed people's behavior were at the heart of containing the spread of the virus. As a result, it has become a systemic human development crisis affecting health, the economy, education, social life, and accumulated gains. This study shows how the relationship of the Human Development Index (HDI), which has combined effects on health, education, and the economy, should be considered in the context of pandemic factors. First, COVID-19 data of the countries received from a public and credible source were extracted and organized into an acceptable structure. Then, we applied statistical feature selection to determine which variables are closely related to HDI and enabled the Deep Con-volutional Neural Network (DCNN) model to give more accurate results. The Continuous Wavelet Transform (CWT) and scalogram methods were used for the time-series data visualization. Three different images of each country are combined into a single image to penetrate each other for ease of processing. These images were made suitable for the input of the ResNet-50 network, which is a pre-trained DCNN model, by going through various preprocessing processes. After the training and validation processes, the feature vectors in the fc1000 layer of the network were drawn and given to the Support Vector Machine Classifier (SVMC) input. We achieved total performance metrics of specificity (88.2%), sensitivity (96.5%), precision (99%), F1 Score (94.9%) and MCC (85.9%).Öğe Detection of RR Interval Alterations in ECG Signals by Using First Order Fractional Filter(Ieee, 2016) Alagoz, Baris Baykant; Yeroglu, Celaleddin; Kavuran, Gurkan; Ates, AbdullahSleep apnea syndrome deteriorates sleeping quality and daily performance of many individuals. This study presents utilization of fractional-order low pass filtering for the detection of RR interval alteration from electrocardiogram (ECG) signals. In the case of sleeping apnea, cardiac interbeat intervals prolong and it is viewed as an indication of obstructive sleep apnea state. The prolonged interbeat intervals manifest themselves as the decrease of R peak frequency (increase of RR intervals) in ECG signals. It results in shifting of spectral components composing R peaks towards lower frequencies in energy signal of ECG. In order to detect prolonging interbeat intervals, energy signal calculated from ECG is applied to low-pass fractional-order filter. Transition band of the low-pass filter is used as a ramp filter in order to detect frequency variations in the energy of R peaks. We compare results of the first order fractional-order and integer order low-pass filters and demonstrate that the fractional-order filter can improve the detection performance of low-pass filtering by modifying transition band slope of low-pass filters.Öğe An Experimental Study on Model Reference Adaptive Control of TRMS by Error-Modified Fractional Order MIT Rule(Romanian Soc Control Tech Informatics, 2017) Kavuran, Gurkan; Ates, Abdullah; Alagoz, Baris Baykant; Yeroglu, CelaleddinModel Reference Adaptive Control (MRAC) strategies find application in flight control because of changes in dynamics of flight conditions. This paper demonstrates an application of Fractional Order Adjustment Rule MRAC (FOAR-MRAC) with the modification of model error dead zone for adaptive control of Twin Rotor Multi-input multi-output System (TRMS). Here, we implement FOAR-MRAC structure with feedforward and feedback MIT rules by using a fractional order integrator. Previously, Vinage et al. have reported that MIT with fractional order integrator can improve tracking performance of MRAC. In the current experimental study, we modified model approximation error by using a piecewise linear, near-zero dead zone function and manage stability of adaptation process in practical application. Accordingly, when the control system response approximates to response of reference model, adaptation process is interrupted. This modification improves quasi-stabilization of updating rule by omitting low level errors and contributes to applicability of MRAC in real applications. An adaptive PID rotor control system is developed by integating the proposed FOAR-MRAC structure. Simulation and experimental results, obtained for TRMS setup, are presented to show effectiveness of the proposed method.Öğe Fine-Tuning of Feedback Gain Control for Hover Quad Copter Rotors by Stochastic Optimization Methods(Springer International Publishing Ag, 2020) Ates, Abdullah; Alagoz, Baris Baykant; Kavuran, Gurkan; Yeroglu, CelaleddinThree degree of freedom (3 DOF) Hover Quad Copter (HQC) platforms are implemented for various missions in diverse scales from the micro to macro platforms. As HQC platforms scale down, micro platform requires rather robust and effective control techniques. This study investigates applicability of some stochastic optimization methods for tuning feedback gain control of HQC rotors and compares optimization results with results of linear quadratic regulator (LQR) method that has been widely used analytical method for optimal feedback gain control of HQCs. This study considers the utilization of two stochastic methods for tuning of HQCs. These methods are stochastic multi-parameter divergence optimization method (SMDO) and discrete stochastic optimization method (DSO). These methods are employed to optimize feedback gain coefficients of an experimental HQC test platform. Simulation and experimental results of SMDO and DSO methods are reported and compared with results of LQR method.Öğe Image processing based object tracking application with fractional-order model reference controller(Pamukkale Univ, 2016) Kavuran, Gurkan; Ates, Abdullah; Alagoz, B. Baykant; Yeroglu, CelaleddinIn this paper, position control application of DC servo motor is investigated by using conventional model reference adaptive control structure with fractional order integrator. Modification of the controller is achieved by fractional order integrator in adaptation rule. Object position for reference input of control system is updated in real time by the values obtained from camera of object tracking system. Results obtained for integer order integrator and fractionalorder integrator for model reference adaptive control system are compared and it is observed that the fractional-order integrator can provide faster adaptation for the system.Öğe Implementation of fractional order filters discretized by modified Fractional Order Darwinian Particle Swarm Optimization(Elsevier Sci Ltd, 2017) Ates, Abdullah; Alagoz, Baris Baykant; Kavuran, Gurkan; Yeroglu, CelaleddinDigital systems are placed at the core of information technology and they are used extensively in electronics. The digital filter realization has become a central topic of signal processing studies. This paper presents a discrete IIR filter design method for approximate realization of fractional order continuous filters in digital systems. For this purpose, Fractional Order Darwinian Particle Swarm Optimization (FODPSO) method is modified to provide better fitting of a discrete IIR filter function to a fractional order continuous filter and we implemented a hybrid version of FODPSO method, where the initial particle generation is carried out by arithmetical candidate point selection technique of the Base Optimization Algorithm (BaOA). This modification expands the search range of the FODPSO and thus the optimized discrete IIR filter can provide better approximation to amplitude response of fractional order continuous filter functions. In the paper, several illustrative examples are presented to demonstrate the performance of proposed methods. (C) 2017 Elsevier Ltd. All rights reserved.Öğe Improvement of IIR Filter Discretization for Fractional Order Filter by Discrete Stochastic Optimization(Ieee, 2016) Ates, Abdullah; Kavuran, Gurkan; Alagoz, Baris Baykant; Yeroglu, CelaleddinFractional calculus has many implications for the field of signal processing, particularly in filter design. Fractional order filter functions are generalization of all rational filter structures including integer-order filter functions and it provides more options in term of frequency selectivity property. This study presents application of stochastic optimization methods for the improvement of IIR filter discretization of fractional order continuous filter structures. We used results of well-known fractional order discretization methods as initial filter model and improved the amplitude response of discrete filter for a better fitting to the continuous fractional-order filters. Illustrative examples demonstrate that it is possible to further improve amplitude responses of IIR filter discretization obtained for the fractional order differentiators, the first and second order continuous fractional-order filter structures by using basic random search algorithms. Digital filter design is very essential for digital signal processing applications and findings of this paper may contribute to digital filter design field in practice.Öğe Investigation of Periodic Modes in Nonlinear Systems with Fractional Order Integrator(Ieee, 2015) Kavuran, Gurkan; Yeroglu, CelaleddinThis paper investigates the effect of fractional order integrator on the nonlinear feedback systems. The effect of fractional order integrator, which is proposed to place in front of relay with dead zone on the second order system, is analysed comparatively using Describing Function method and simulation results. Since the proposed approach provides the opportunity for the selection of a wide phase range, it can be considered as an effective method to select relevant sampling frequency and to investigate limit cycles in modulators and demodulators that are used for signal conversion applications.Öğe Limit Cycles in Nonlinear Systems with Fractional Order Plants(Mdpi, 2014) Atherton, Derek P.; Tan, Nusret; Yeroglu, Celaleddin; Kavuran, Gurkan; Yuce, AliIn recent years, there has been considerable interest in the study of feedback systems containing processes whose dynamics are best described by fractional order derivatives. Various situations have been cited for describing heat flow and aspects of bioengineering, where such models are believed to be superior. In many situations these feedback systems are not linear and information on their stability and the possibility of the existence of limit cycles is required. This paper presents new results for determining limit cycles using the approximate describing function method and an exact method when the nonlinearity is a relay characteristic.Öğe MTU-COVNet: A hybrid methodology for diagnosing the COVID-19 pneumonia with optimized features from multi-net(Elsevier Science Inc, 2022) Kavuran, Gurkan; In, Erdal; Geckil, Aysegul Altintop; Sahin, Mahmut; Berber, Nurcan KiriciPurpose: The aim of this study was to establish and evaluate a fully automatic deep learning system for the diagnosis of COVID-19 using thoracic computed tomography (CT). Materials and methods: In this retrospective study, a novel hybrid model (MTU-COVNet) was developed to extract visual features from volumetric thoracic CT scans for the detection of COVID-19. The collected dataset consisted of 3210 CT scans from 953 patients. Of the total 3210 scans in the final dataset, 1327 (41%) were obtained from the COVID-19 group, 929 (29%) from the CAP group, and 954 (30%) from the Normal CT group. Diagnostic performance was assessed with the area under the receiver operating characteristic (ROC) curve, sensitivity, and specificity. Results: The proposed approach with the optimized features from concatenated layers reached an overall accuracy of 97.7% for the CT-MTU dataset. The rest of the total performance metrics, such as; specificity, sensitivity, precision, F1 score, and Matthew Correlation Coefficient were 98.8%, 97.6%, 97.8%, 97.7%, and 96.5%, respectively. This model showed high diagnostic performance in detecting COVID-19 pneumonia (specificity: 98.0% and sensitivity: 98.2%) and CAP (specificity: 99.1% and sensitivity: 97.1%). The areas under the ROC curves for COVID-19 and CAP were 0.997 and 0.996, respectively. Conclusion: A deep learning-based AI system built on the CT imaging can detect COVID-19 pneumonia with high diagnostic efficiency and distinguish it from CAP and normal CT. AI applications can have beneficial effects in the fight against COVID-19.Öğe Obstructive Sleep Apnea Detection Using Lomb-Scargle Periodogram Method(Ieee, 2018) Kavuran, Gurkan; Yeroglu, CelaleddinIn this study, the power spectral density of the heart rate signal was investigated by the Lomb-Scargle Periodogram method for obstructive sleep apnea (OSA) estimation. Sleep apnea, which occurs as a result of respiratory failure during sleep, is interpreted by scoring polysomnographic signals. One of these signals, Electrocardiogram (ECG), contains noise in its structure and exhibits irregular alteration. In this study, the power spectrum of the heart rate variability (HRV) was obtained based on filtered ECG signals. Analyzes in the presence of OSA and in the absence of OSA have shown that deviations occur in the high and low frequency components of the HRV.Öğe Reference-shaping adaptive control by using gradient descent optimizers(Public Library Science, 2017) Alagoz, Baris Baykant; Kavuran, Gurkan; Ates, Abdullah; Yeroglu, CelaleddinThis study presents a model reference adaptive control scheme based on reference-shaping approach. The proposed adaptive control structure includes two optimizer processes that perform gradient descent optimization. The first process is the control optimizer that generates appropriate control signal for tracking of the controlled system output to a reference model output. The second process is the adaptation optimizer that performs for estimation of a time-varying adaptation gain, and it contributes to improvement of control signal generation. Numerical update equations derived for adaptation gain and control signal perform gradient descent optimization in order to decrease the model mismatch errors. To reduce noise sensitivity of the system, a dead zone rule is applied to the adaptation process. Simulation examples show the performance of the proposed Reference-Shaping Adaptive Control (RSAC) method for several test scenarios. An experimental study demonstrates application of method for rotor control.Öğe A theoretical demonstration for reinforcement learning of PI control dynamics for optimal speed control of DC motors by using Twin Delay Deep Deterministic Policy Gradient Algorithm(Pergamon-Elsevier Science Ltd, 2023) Tufenkci, Sevilay; Alagoz, Baris Baykant; Kavuran, Gurkan; Yeroglu, Celaleddin; Herencsar, Norbert; Mahata, ShibenduTo benefit from the advantages of Reinforcement Learning (RL) in industrial control applications, RL methods can be used for optimal tuning of the classical controllers based on the simulation scenarios of operating con-ditions. In this study, the Twin Delay Deep Deterministic (TD3) policy gradient method, which is an effective actor-critic RL strategy, is implemented to learn optimal Proportional Integral (PI) controller dynamics from a Direct Current (DC) motor speed control simulation environment. For this purpose, the PI controller dynamics are introduced to the actor-network by using the PI-based observer states from the control simulation envi-ronment. A suitable Simulink simulation environment is adapted to perform the training process of the TD3 algorithm. The actor-network learns the optimal PI controller dynamics by using the reward mechanism that implements the minimization of the optimal control objective function. A setpoint filter is used to describe the desired setpoint response, and step disturbance signals with random amplitude are incorporated in the simu-lation environment to improve disturbance rejection control skills with the help of experience based learning in the designed control simulation environment. When the training task is completed, the optimal PI controller coefficients are obtained from the weight coefficients of the actor-network. The performance of the optimal PI dynamics, which were learned by using the TD3 algorithm and Deep Deterministic Policy Gradient algorithm, are compared. Moreover, control performance improvement of this RL based PI controller tuning method (RL-PI) is demonstrated relative to performances of both integer and fractional order PI controllers that were tuned by using several popular metaheuristic optimization algorithms such as Genetic Algorithm, Particle Swarm Opti-mization, Grey Wolf Optimization and Differential Evolution.Öğe Using artificial intelligence to improve the diagnostic efficiency of pulmonologists in differentiating COVID-19 pneumonia from community-acquired pneumonia(Wiley, 2022) In, Erdal; Geckil, Aysegul A.; Kavuran, Gurkan; Sahin, Mahmut; Berber, Nurcan K.; Kuluozturk, MutluCoronavirus disease 2019 (COVID-19) has quickly turned into a global health problem. Computed tomography (CT) findings of COVID-19 pneumonia and community-acquired pneumonia (CAP) may be similar. Artificial intelligence (AI) is a popular topic among medical imaging techniques and has caused significant developments in diagnostic techniques. This retrospective study aims to analyze the contribution of AI to the diagnostic performance of pulmonologists in distinguishing COVID-19 pneumonia from CAP using CT scans. A deep learning-based AI model was created to be utilized in the detection of COVID-19, which extracted visual data from volumetric CT scans. The final data set covered a total of 2496 scans (887 patients), which included 1428 (57.2%) from the COVID-19 group and 1068 (42.8%) from the CAP group. CT slices were classified into training, validation, and test datasets in an 8:1:1. The independent test data set was analyzed by comparing the performance of four pulmonologists in differentiating COVID-19 pneumonia both with and without the help of the AI. The accuracy, sensitivity, and specificity values of the proposed AI model for determining COVID-19 in the independent test data set were 93.2%, 85.8%, and 99.3%, respectively, with the area under the receiver operating characteristic curve of 0.984. With the assistance of the AI, the pulmonologists accomplished a higher mean accuracy (88.9% vs. 79.9%, p < 0.001), sensitivity (79.1% vs. 70%, p < 0.001), and specificity (96.5% vs. 87.5%, p < 0.001). AI support significantly increases the diagnostic efficiency of pulmonologists in the diagnosis of COVID-19 via CT. Studies in the future should focus on real-time applications of AI to fight the COVID-19 infection.
