Yazar "Menguc, Engin Cemal" seçeneğine göre listele
Listeleniyor 1 - 20 / 24
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A generalized Lyapunov stability theory-based adaptive FIR filter algorithm with variable step sizes(Springer London Ltd, 2017) Menguc, Engin Cemal; Acir, NurettinThis paper presents a novel approach to Lyapunov stability theory-based adaptive filter (LAF) design. The proposed design is based on the minimization of the Euclidean norm of the difference weight vector under negative definiteness constraint defined over a novel linear Lyapunov function. The proposed fixed step size LAF (FSS-LAF) algorithm is first obtained by using the method of Lagrangian multipliers. The FSS-LAF satisfying asymptotic stability in the sense of Lyapunov provides a significant performance gain in the presence of a measurement noise. The stability of the FSS-LAF algorithm is also statistically analyzed in this study. Moreover, gradient variable step size (VSS) algorithms are adapted to the FSS-LAF algorithm to further enhance the performance for the first time in this paper. These VSS algorithms are Benveniste (BVSS), Mathews and Farhang-Ang (FVSS) algorithms. Simulation results on system identification problems show that the bounds of step size for the FSS-LAF algorithm are verified, and especially, the BVSS-LAF and FVSS-LAF algorithms provide a better trade-off between steady-state mean square deviation error and convergence rate than other proposed algorithms.Öğe A Modified Neural Filtering Algorithm for Tracking of Chaotic Signals(IEEE, 2014) Menguc, Engin Cemal; Acir, Nurettin; AlDabass, D; Orsoni, A; Cant, R; Yunus, J; Ibrahim, Z; Saad, IIn this study, a modified neural filtering algorithm is presented for tracking of chaotic signals. A multilayer neural network (MLNN) structure is used in proposed design as a nonlinear adaptive filtering tool. Initially, the MLNN is linearized using Taylor series expansion and then the weight vector update rule is designed by using Lyapunov stability theory (LST) to adaptively update the weights of the MLNN. The tracking capability of the proposed algorithm is improved by using adaptation gain rate parameter "a(k)" which is iteratively adjusted itself depending on sequential tracking errors rate. The tracking ability of the proposed algorithm is tested on two chaotic signals and compared with conventional algorithms. The simulation results have supported that the proposed neural filtering algorithm achieved better performance.Öğe A New Approach to Channel Equalization Problem(IEEE, 2015) Menguc, Engin Cemal; Acir, NurettinIn this study, a new approach based on Lyapunov stability theory (LST) is proposed for channel equalization problem. For the first time, the convergence capability of the proposed algorithm is presented on the channel equalization problem. The proposed approach is compared with normalized least mean square (NLMS) algorithm. Simulation results show that the convergence capability of the proposed algorithm is better than NLMS algorithm. As a result, the proposed approach can effectively be used for the channel equalization problem.Öğe A novel adaptive filter design using Lyapunov stability theory(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY, 2015) Menguc, Engin Cemal; Acir, NurettinThis paper presents a new approach to design an adaptive filter using Lyapunov stability theory. The design procedure is formulated as an inequality constrained optimization problem. Lagrange multiplier theory is used as an optimization tool. Lyapunov stability theory is integrated into the constraint function to satisfy the asymptotic stability of the proposed filtering system. The tracking capability is improved by using a new analytical adaptation gain rate, which has the ability to adaptively adjust itself depending on a sequential tracking square error rate. The fast and robust convergence ability of the proposed algorithm is comparatively examined by simulation examples.Öğe Adaptive Fourier Linear Combiner based on Modified Least Mean Kurtosis Algorithm(IEEE, 2018) Menguc, Engin CemalIn this study, we propose an adaptive Fourier linear combiner (FLC) based on a modified least mean kurtosis (LMK) algorithm for canceling the sinusoidal noise signals from the desired signals. In the proposed framework, the weight coefficients of the FLC are adjusted by using the modified LMK algorithm instead of the conventional least mean square (LMS) algorithm. The fundamental reasons for using the proposed LMK algorithm in the FLC are that it provides a fast convergence rate, a lower steady-state error and a robust behavior against sinusoidal noise distributions. The performance of the proposed FLC algorithm is assessed on the noise canceling problem by comparing that of the conventional FLC based on the LMS algorithm. The simulation results demonstrate that the proposed FLC based the modified LMK algorithm outperforms its conventional LMS algorithm in terms of the convergence rate and the steady-state error.Öğe Adaptive Fourier linear combiner based on modified least mean Kurtosis algorithm for the processing of sinusoidal signals(Sage Publications Ltd, 2021) Menguc, Engin CemalThis study introduces an adaptive Fourier linear combiner (FLC) based on a modified least mean kurtosis (LMK) algorithm in order to effectively process sinusoidal signals, which we call FLC-LMK algorithm. In the design procedure of the proposed FLC-LMK algorithm, the classical kurtosis-based cost function is first modified for only sinusoidal signal distributions instead of Gaussian. Then, the FLC-LMK algorithm is derived from the minimization of this cost function and thus updates the weight coefficients of the FLC structure so as to directly process sinusoidal signals. Moreover, in this study, the convergence in the mean of the proposed FLC-LMK algorithm is analysed in order to determine the lower and upper bounds of its step size parameter. The most important contributions of the use of the proposed algorithm in the FLC structure are that it increases the convergence rate, decreases the steady-state error level and also has a robust behaviour against sinusoidal signal distributions due to its modified cost function. The performance of the proposed FLC-LMK algorithm is evaluated on the synthetic and real-world pathological hand tremor data by comparing with that of the FLC based on the classical least mean square (LMS) (FLC-LMS) algorithm. The simulation results support the mentioned properties of the proposed FLC-LMK algorithm.Öğe An augmented complex-valued Lyapunov stability theory based adaptive filter algorithm(Elsevier, 2017) Menguc, Engin Cemal; Acir, NurettinA novel augmented complex-valued Lyapunov stability theory (LST) based adaptive filter (ACLAF) algorithm is proposed for the widely linear adaptive filtering of noncircular complex-valued signals. After a candidate Lyapunov function is determined, the design procedure is formulated as an inequality constrained optimization problem by using augmented statistics and LST. Thus, the proposed algorithm has improved the adaptive filtering of noncircular complex-valued signals by a unified framework of the LST and augmented complex statistics. Moreover, we statistically show that the ACLAF algorithm converges to the optimal Wiener solution under stationary environments, the required condition of the step size for the stability of the ACLAF algorithm is obtained by convergence in mean analysis and a new approach. In addition, the variance of the ACLAF algorithm is statically analysed in this study. The performance of the ACLAF algorithm is tested on circular and noncircular benchmark signals and on a real-world non circular wind signal. Simulation results verify that the ACLAF algorithm outperforms complex-valued LST based adaptive filter (CLAF), complex-valued least mean square (CLMS), complex-valued normalized least mean square (CNLMS), augmented CLMS (ACLMS) and augmented CNLMS (ACNLMS) algorithms for adaptive prediction of noncircular signals in terms of prediction gain, convergence rate and mean square error (MSE). Also, the ACLAF algorithm enhances the prediction gain by more than 25% when compared to the other augmented algorithms. (C) 2017 Elsevier B.V. All rights reserved.Öğe Automatic Removal of Ocular Artefacts in EEG Signal by Using Independent Component Analysis and Artificial Neural Network(IEEE, 2017) CInar, Salim; Menguc, Engin Cemal; Acir, NurettinOcular artefacts caused by eye movements can distort Electroencephalogram (EEG) recordings. It is important to obtain clean EEG signals in diagnosing and interpreting diseases. Meaningful EEG signals should not be distorted during the removal of artefacts. In this study, Independent Component Analysis and Artificial Neural Network were used together to remove ocular artefacts. The method was tested by using the real dataset. The Relative Error (RE) and Correlation Coefficient (CC) was used to test the performance of the method. Relative error = 0.227 0.229 and correlation coefficient = 0.941 0.088 was calculated in the performance analysis. According to the results, the proposed method is successful in removing ocular artefacts in EEG signals.Öğe Comparative evaluation of different statistical tools for the prediction of uniaxial compressive strength of rocks(Elsevier, 2020) Teymen, Ahmet; Menguc, Engin CemalIn this study, uniaxial compressive strength (UCS), unit weight (UW), Brazilian tensile strength (BTS), Schmidt hardness (SHH), Shore hardness (SSH), point load index (Is(50)) and P-wave velocity (V-p) properties were determined. To predict the UCS, simple regression (SRA), multiple regression (MRA), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and genetic expression programming (GEP) have been utilized. The obtained UCS values were compared with the actual UCS values with the help of various graphs. Datasets were modeled using different methods and compared with each other. In the study where the performance indice PIat was used to determine the best performing method, MRA method is the most successful method with a small difference. It is concluded that the mean PIat equal to 2.46 for testing dataset suggests the superiority of the MRA, while these values are 2.44, 2.33, and 2.22 for GEP, ANFIS, and ANN techniques, respectively. The results pointed out that the MRA can be used for predicting UCS of rocks with higher capacity in comparison with others. According to the performance index assessment, the weakest model among the nine model is P7, while the most successful models are P2, P9, and P8, respectively. (C) 2020 Published by Elsevier B.V. on behalf of China University of Mining & Technology.Öğe Comparison of Split Complex-Valued Metaheuristic Optimization Algorithms for System Identification Problem(IEEE, 2018) Menguc, Engin Cemal; Peker, Murat; Cinar, SalimSince some of the real world problems include phase and amplitude information, complex modeling is more suitable. In this study, the well-used particle swarm optimization, simulated annealing and genetic algorithm are designed in a split form in order to process complex-valued signals. The performances of the algorithms are comparatively tested on two different system identification problems for different noise levels. Simulation results show that the split complex-valued metaheuristic algorithms produce results which are almost close to the weights of both unknown systems.Öğe Complex-Valued Least Mean Kurtosis Adaptive Filter Algorithm(IEEE, 2016) Menguc, Engin Cemal; Acir, NurettinIn this study, a complex-valued least mean Kurtosis (CLMK) adaptive filter algorithm is designed for processing complex-valued signals. The performance of the designed algorithm is tested on a complex-valued system identification and compared the complex-valued least mean square (CLMS) and complex-valued normalized least mean square (CNLMS) algorithms. As a result, the CLMK algorithm shows a higher performance than the other algorithms in terms of the convergence rate, mean square error (MSE) and mean square deviation (MSD).Öğe Complex-Valued Model Reference Adaptive Systems for Speed Estimation of Induction Motor(IEEE, 2019) Zerdali, Emrah; Menguc, Engin CemalIn this study, two novel complex-valued model reference adaptive systems (MRASs) based on rotor flux and stator current are performed for speed-sensorless control of squirrel cage induction motor (SCIM) and tested under different operating conditions for a wide speed range. Nowadays, the complex-valued methods have become popular and provided significant advantages in some important applications where the signal or system can be defined in the complex domain. The reasons why these MRAS types are selected are that these structures are suitable to be defined in the complex domain, do not require external flux estimator, and are two of the most popular MRAS types. Finally, satisfactory estimation performances for both novel complex-valued MRAS algorithms have been obtained under simulations.Öğe Data-Adaptive Censoring for Short-Term Wind Speed Predictors Based on MLP, RNN, and SVM(IEEE-Inst Electrical Electronics Engineers Inc, 2022) Sarp, Ali Ogun; Menguc, Engin Cemal; Peker, Murat; Guvenc, Buket ColakThis study introduces novel short-term wind speed predictors based on multilayer perceptron (MLP), recurrent neural network (RNN), and support vector machine (SVM) by combining them with the data-adaptive censoring (DAC) strategy. Taking into account the multistep ahead prediction mode, we design a DAC strategy based on the least mean square (LMS) algorithm, which iteratively obtains a new training dataset consisting of the most informative input-output wind data from all training set for MLP, RNN, and SVM structures. This enables us to censor less informative training data with high accuracy and thereby the training costs of the MLP, RNN, and SVM are reduced without a considerably adverse effect on their prediction performances in testing processes. The conducted simulation results on real-life large-scale short-term wind speed data verify the mentioned attractive features of the proposed predictors.Öğe Design of quaternion-valued second-order Volterra adaptive filters for nonlinear 3-D and 4-D signals(Elsevier, 2020) Menguc, Engin CemalIn this paper, the quaternion-valued second-order Volterra adaptive filters (QSOVAFs) are designed for the processing of nonlinear three-dimensional (3-D) and four-dimensional (4-D) signals. In the proposed frameworks, the structure of the strictly nonlinear (SNL), semi-widely nonlinear (SWNL), and widely nonlinear (WNL) QSOVAFs are primarily constructed in the quaternion domain. Then, their loss functions defined by the instantaneous error signals are minimized in the quaternion domain by using the recent generalized Hamilton-real (GHR) calculus. Thus, novel weight update equations are obtained for training the proposed SNL-QSOVAF, SWNL-QSOVAF, and WNL-QSOVAF. Furthermore, the stability bounds for each quaternion-valued kernel functions of them are derived from the convergence in the mean analysis. The comprehensive simulations on the nonlinear system identification and one-step-ahead prediction experiments support that the proposed SWNL-QSOVAF and WNL-QSOVAF can be effectively used in the processing of nonlinear noncircular quaternion signals, whereas that their SNL version can produce optimal results for nonlinear circular quaternion signals. (C) 2020 Elsevier B.V. All rights reserved.Öğe Estimation of Pathological Hand Tremor Signals by Fourier Linear Combiner Based Online Censoring LMS Algorithm(IEEE, 2019) Menguc, Engin Cemal; Rezayi, NeamatallahIn this paper, the FLC based OCLMS algorithm is proposed for the estimation of pathological hand tremor signals. The proposed FLC-OCLMS algorithm has been tested on the well-known pathological hand tremor signals in the literature and its convergence and computational complexity performances are compared with that of the classical FLC-LMS algorithm. Simulation results show that the proposed FLC-OCLMS algorithm has significantly reduced computational complexity because it does not use unnecessary data in the update rule thanks to the online data censoring technique and has a similar convergence with the conventional LMS algorithm.Öğe Lyapunov Stability Theory Based Adaptive Filter Algorithm for Noisy Measurements(IEEE, 2013) Menguc, Engin Cemal; Acir, Nurettin; AlDabass, D; Orsoni, A; Yunus, J; Cant, R; Ibrahim, ZThis paper presents a Lyapunov stability theory based adaptive filter algorithm with a determined step size. The proposed algorithm thanks to its step size leads to a faster convergence rate and a lover misadjustment error in case of the noisy measurement environments. Also the proposed algorithm ensures to estimate the best optimal unknown weight vector by using a step size. Simulations on white and non-white Gaussian input signals justify the proposed algorithm for the noisy environments. The simulation results demonstrate good tracking capability and low misalignment error of the proposed algorithm in case of the noisy measurement environments for system identification problems.Öğe LYAPUNOV STABILITY THEORY BASED COMPLEX VALUED ADAPTIVE FILTER DESIGN(IEEE, 2014) Menguc, Engin Cemal; Acir, NurettinIn this study, a novel complex valued adaptive filter algorithm is proposed satisfying stability in the sense of Lyapunov. The prediction capability of the proposed algorithm is presented by using complex valued autoregressive process and wind signal in the literature. The proposed complex valued adaptive filter algorithm is compared with standard complex normalized least mean square algorithm and performed in a high performance.Öğe LYAPUNOV THEORY BASED ADAPTIVE LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS(ACAD SCIENCES CZECH REPUBLIC, INST COMPUTER SCIENCE, 2014) Acir, Nurettin; Menguc, Engin CemalThis paper presents a novel weight updating algorithm for training of multilayer neural network (MLNN). The MLNN system is first linearized and then the design procedure is proposed as an inequality constraint optimization problem. A well selected Lyapunov function is suitably determined and integrated into the constraint function for satisfying asymptotic stability in the sense of Lyapunov. Thus, the convergence capability of training algorithm is improved by using a new analytical adaptation gain rate which has the ability to adaptively adjust itself depending on a sequential square error rate. The proposed algorithm is compared with two types of backpropagation algorithms and a Lyapunov theory based MLNN algorithm on three benchmark problems which are XOR, 3-bit parity, and 8-3 encoder. The results are compared in terms of number of learning iterations and computational time required for a specified convergence rate. The results clearly indicate that the proposed algorithm is much faster in convergence than other three algorithms. The proposed algorithm is also comparatively tested on a real iris image database for multiple-input and multiple-output classification problem and the effect of adaptation gain rate for faster convergence and higher performance is verified.Öğe Novel error variance estimation rule for nonparametric VSS-NLMS algorithm(Springer London Ltd, 2020) Menguc, Engin CemalThis paper presents a robust error variance estimation rule for the nonparametric variable step-size normalized least mean square (NPVSS-NLMS) algorithm. The proposed variance estimation rule accurately estimates the variance of the error signal. This is achieved by the variable exponential windowing parameter depending on the standard deviations of the sequential error signals. The accurate estimation of the error signal variance in the NPVSS-NLMS algorithm considerably improves the performance of the adaptive filter when compared to the classical NPVSS-NLMS algorithm. Moreover, the convergence and steady-state performances of the NPVSS-NLMS based on the proposed rule are analyzed in this study. The performance of the proposed algorithm is evaluated on system identification and acoustic echo canceling experiments and compared with that the classical NPVSS-NLMS algorithm. As a result, simulations show that the proposed algorithm with the help of the novel robust error variance estimation rule not only yields a dramatically reduced steady-state error but also achieves a faster convergence rate as compared with the classical counterparts. Furthermore, the theoretical results of the variable exponential windowing parameter used in the proposed rule are in very good agreement with its simulation results.Öğe Online Censoring Based Weighted-Frequency Fourier Linear Combiner for Estimation of Pathological Hand Tremors(IEEE-Inst Electrical Electronics Engineers Inc, 2021) Menguc, Engin Cemal; Cnar, Salim; Xiang, Min; P. Mandic, DaniloAn online censoring (OC) based weighted-frequency Fourier linear combiner (OC-WFLC) adaptive filtering structure is proposed to reduce data processing costs in the estimation of pathological hand tremor (PHT) measurements. The proposed OC-WFLC is combined with the Fourier linear combiner (FLC) to effectively separate the PHT and voluntary movement from the hand tremor signal. The OC-WFLC is shown to adaptively extract the most informative frequency information, that is readily employed within the FLC to adaptively decompose the measurement signal into its PHT and voluntary movement components. The utilization of the OC strategy in the proposed framework is shown to significantly reduce data processing costs without adverse effects on the performance. Simulation results on real-world PHT data demonstrate the ability of the proposed OC-WFLC to yield a dramatic reduction of the processing time, a prerequisite for real-time rehabilitative, wearable, and assistive technology designed for PHT patients.
