Search

An artificial neural network model trained by using various learning algorithms is designed to classify the electrocardiographic signals in this study. The model of artificial neural network is constructed on the structure consisting of a multilayered perceptron based on the feed forward back propagation. A data pool is built by using a dataset consists of 66 electrocardiographic data’s taken from the MIT BIH arrhythmia database to perform the training and testing processes of artificial neural network model. The training process of artificial neural network model is performed with 46 electrocardiographic data and then the accuracy of the model is tested via 20 electrocardiographic data. The artificial neural network is trained by 3 different learning algorithms to achieve a robust model. The performance of the learning algorithms used for training the model of the artificial neural network is evaluated according to percentage error. It illustrates that the artificial neural network model trained by Levenberg–Marquardt learning algorithm obtains the better classification result than other learning algorithms. The proposed artificial neural network model can be successfully used to classify the electrocardiographic signals., Bu çalışmada elektrokardiyografik sinyalleri sınıflandırmak için çeşitli öğrenme algoritmaları kullanılarak eğitilmiş bir yapay sinir ağı modeli tasarlanmıştır. Yapay sinir ağı modeli, ileri beslemeli geri yayılıma dayalı çok katmanlı bir algılayıcıdan oluşan yapı üzerine kurulmuştur. Yapay sinir ağı modelinde kullanılmak üzere 66 elektrokardiyografik veri kullanılmıştır. Yapay sinir ağı modelinin eğitim süreci 46 adet elektrokardiyografik veri ile gerçekleştirilmekte ve ardından 20 adet elektrokardiyografik veri ile modelin doğruluğu test edilmektedir. Yapay sinir ağı, sağlam bir model elde etmek için 3 farklı öğrenme algoritması ile eğitilmiştir. Yapay sinir ağı modelinin eğitiminde kullanılan öğrenme algoritmalarının performansı hata yüzdesine göre değerlendirilmiştir. Levenberg–Marquardt öğrenme algoritması ile eğitilen yapay sinir ağı modelinin diğer öğrenme algoritmalarına göre daha iyi sınıflandırma sonucu elde ettiğini göstermektedir. Önerilen yapay sinir ağı modeli, elektrokardiyografik sinyalleri sınıflandırmak için başarıyla kullanılabilir.

In this study, deep neural network (DNN) is implemented to soft computation of the resonant frequency of E–shaped patch antenna (ESPA). A DNN model is built on a 5-layer framework using an adaptive learning rate algorithm though a simulated database of 144 ESPAs. The framework and hyperparameters of the DNN model are optimized by exploiting K–fold cross validation method in the training phase. In order to generate the database for training and testing the model, 144 ESPAs with different geometrical and electrical parameters are simulated in terms of the resonant frequency using a precise electromagnetic analysis platform. The DNN model is trained on the dataset#130 with an average percentage error (APE) of 0.269 between the simulated and computed frequency values. For corroboration of the proposed DNN model is tested and verified by comparing with previously applied traditional neural networks on the remainder dataset#14, and even verified on a fabricated ESPA operating at 2.4 GHz. The DNN model computes the resonant frequency of the testing dataset#14 with the highest accuracy of 0.285 APE. The results show that the proposed deep neuro-computing model for the resonant frequency is a powerful and helpful technique as an easy alternative to prohibitive measurement and simulation.

In this study, a novel UWB antenna with dual band–rejection is designed by using a new hybrid optimization algorithm based artificial bee colony algorithm (ABC) and differential evolution (DE). The hybrid performance of ABC and DE (H–ABCDE) is tested on well–known benchmark functions. To show its performance on a design problem, an optimization interface (OI) which simultaneously communicates with H–ABCDE and an electromagnetic simulation tool is developed. Hence OI integrating H–ABCDE and HyperLynx® 3D EM is used to design and optimize an antenna. A low profile UWB monopole antenna operating over the frequency range of 2.9–13.0 GHz is then designed through OI. In order to achieve band–rejection operation, various slits and strips have been loaded on the antenna. It thus rejects the dual–band of 3.3–3.6 GHz and 5.15–5.825 GHz corresponds to the operation bands of WLAN and WiMAX. Furthermore, the optimized antenna is prototyped to investigate the measurement performance and it is compared with several designs in the literature. Therefore, H–ABCDE can successfully adapt to the extended electromagnetic problem as well as engineering optimization tasks.

In this paper, a novel, computationally efficient and simple closed-form expression has been derived to accurately calculate the pull-in voltage value of fixed-fixed micro-actuator. At first, microelectromechanical systems actuators with various physical parameters have been simulated by a software that employs the finite element method, the pull-in voltage expression has been derived by using the artificial bee colony optimization algorithm together with the simulation data. Since the formula is derived from the simulation data, it implicitly contains the fringing field, mid-plane stretching and size effects. In order to verify the accuracy and robustness, the predictions of closed-form formula proposed in this work have been compared with those of the theoretical ones through the simulation and experimental studies previously presented in the literature. The key advantage of the presented method is delivering a satisfying estimation of the pull-in voltage with a simple and easy way.

In this study, a dual-wideband monopole antenna has been designed and developed for the universal mobile telecommunications system (UMTS), wireless local area network (WLAN), and worldwide interoperability for microwave access (WiMAX) applications. A novel approach integrating artificial bee colony (ABC) with the HyperLynx® 3D electromagnetic platform based on the method of moments has been employed to calculate the design parameters of the monopole antenna performance for the respective target frequencies and return loss. The proposed dual-wideband antenna operates in the dual-frequency ranges of 1.69–3.99 and 4.75–6.22 GHz applicable for the UMTS, WLAN, and WiMAX applications and it is fabricated on the flame resistant-4 substrate plate of 42 × 51 × 1.6 mm3. The performance of the presented monopole antenna is analyzed in terms of gain, radiation pattern, and s-parameter. The input reflection coefficient (S11) parameter and radiation pattern of the antenna are verified through the measurements. The measured values of the antenna parameters are found to match well within tolerable limits with the simulation results. The results illustrate that the presented dual-wideband monopole antenna obtained by using the ABC algorithm exhibits better performance in point of operating bands and s-parameter as compared with the multi-band antennas previously published in the literature.

In this paper, an application of artificial neural network (ANN) using bayesian regularization (BR) learning algorithm based on multilayer perceptron (MLP) model is presented for computing the operating frequency of C-shaped patch antennas (CPAs) in UHF band. Firstly, the operating frequencies of 144 CPAs having varied dimensions and electrical parameters were simulated by the XFDTD software package based on the finite-difference time domain (FDTD) method in order to generate the data set for the training and testing processes of the ANN-BR model. Then ANN-BR model was built with data set and while 129 simulated CPAs and remaining 15 simulated CPAs were employed for ANN-BR model training and testing respectively. In order to demonstrate its validity and accuracy, the proposed ANN-BR model was also tested over the simulation data given in the literature. The obtained results show that ANN-BR technique can be successfully used to compute the operating frequency of CPAs without involving any sophisticated methods. © 2016 ASTES Publishers. All rights reserved.

In this study, a feed-forward backpropagation (FFBP) artificial neural network (ANN) model based on multilayer perceptron (MLP) for computing the pull-in voltage value of fixed–fixed micro-actuators is presented. The proposed ANN model is trained using the numerous pull-in voltage value results of clamped–clamped actuators, which have various physical properties, simulated by a software that employs the finite element method (FEM). As the presented ANN model has been trained for the simulation data, it implicitly takes into account the fringing field, mid-plane stretching and size effects. The accuracy and robustness of the results obtained by the proposed ANN model are verified by comparing with those of the theoretical ones through the simulation and experimental studies previously presented in the literature. The average percentage errors for training and testing data are found to be 0.30 and 0.40 %, respectively, while the maximum percentage error for literature data is calculated as 1.96 %. These results show that the main advantage of the presented ANN model gives satisfying pull-in voltage results over solution space of the simulations with effortless way.

A compact multiple-input multiple-output (MIMO) antenna with a small size of 26 × 55 mm 2 and low correlation has been proposed for the ultra-wide-band (UWB) applications operating over a frequency range of 3.1-12.3 GHz at �10 dB. The MIMO antenna consists of two identical elements each of which has a planar radiator with microstrip-fed over half- sized ground plane. The antenna elements are placed orthogonally to achieve a good isolation between the two input ports. The antenna's characteristics such as the bandwidth, isolation, radiation pattern, peak gain and surface current distributions have been investigated. Moreover, diversity performance in terms of envelope correlation coefficient and mean effective gain has been analysed. Furthermore, a parametric study has been carried out to provide more design information. An arrangement with quad-elements has been designed for MIMO operations, as well. The simulation and measurement results show that the proposed antenna has an impedance bandwidth larger than the frequency range of UWB with low correlation and high diversity performance. The proposed MIMO antenna has been compared in detail with the previous works reported elsewhere in terms of antenna size, geometric complexity, bandwidth, mutual coupling and use of additional structure to obtain more isolation. From this point of views, the antenna is more preferable than other suggestions.

This paper deals with the application of two robust methods, namely the adaptive neuro-fuzzy inference system (ANFIS) and the support vector machine (SVM), to predict the resonant frequency of E-shaped compact microstrip antennas (ECMAs) operating at UHF band. Firstly, the resonant frequencies of 144 ECMAs with varied dimensions and electrical parameters were simulated with $$\hbox {IE3D}^\mathrm{TM}$$IE3DTM based on method of moment (MoM).The ANFIS and SVM models for computing the resonant frequency were then built by considering the simulation data. 130 simulated ECMAs were utilized for training and the remaining 14 ECMAs were used for testing the ANFIS and SVM models. The average percentage errors (APE) regarding the computed resonant frequencies for training by ANFIS and SVM were obtained as 0.105 and 0.387 %, respectively. The constructed models were then tested over the test data and APE values were achieved as 0.361 % for ANFIS and 0.480 % for SVM. Additionally, agreement between ANFIS and SWM results was investigated with $$r^{2}$$r2 method. The results of both ANFIS and SWM were compared with those of the methods previously published in the literature, and a very good agreement between the models proposed and the simulations was obtained. Also, the validity and accuracy of these models were verified on the fabricated ECMA operating at 2.4 GHz. The results achieved in this work show us that both ANFIS and SVM models can be used to predict the resonant frequency of ECMAs as the useful and versatile methods without involving any sophisticated methods.

At the present time, nanomaterials are used in the medicine and biology applications such as drug and gene delivery, bio-detection of pathogens, MRI contrast enhancement, tumor destruction via heating, and protein detection. Tissue engineering which is another of these applications is being increasingly popular. Because extracellular matrix (ECM) consists nano-sized structure; the usage of nanomaterials in tissue engineering enables to produce of tissue scaffolds that are more closely resemble the ECM form. Thus, the success rate increases in tissue engineering as it is provided a more favorable environment for the growth of cells. Electrospinning is a popular method among nanomaterial production ones. The diameter of the fiber produced by electrospinning technique depends on the various parameters like process, solution, and environmental parameters. In this study, an ANN model based on multilayer perceptron (MLP) is presented for predicting the average fiber diameter (AFD) of electrospun gelatin/bioactive glass (Gt/BG) scaffold. The experimental results previously published in the literature, which include one solution parameter (BG content) as well as two process parameters (tip to collector distance and solution flow rate) related to producing of electrospun Gt/BG nanofiber, have been used. The values of average percentage error between the predicted average fiber diameters and experimental ones are achieved as 3.27 %. The results obtained from the proposed model have also been confirmed by comparing with results of AFD expression reported elsewhere. It is illustrated that the AFD of electrospun Gt/BG can be accurately predicted by the model proposed here without requiring any complicated or sophisticated knowledge of the mathematical and physical background.

Nowadays, the attraction of the optimization techniques based on artificial intelligence has increased the due to obtaining the its successful results on the difficult optimization problems in various areas. The artificial bee colony (ABC) algorithm based on swarm intelligence and the differential evolution (DE) algorithm improved by inspiring the natural biological evolution mechanism is the most popular of the artificial intelligence optimization methods. The exploration ability of these optimization techniques is generally very good. However, there is a disadvantage of these algorithms for the difficult optimization problem. The exploitation capability of the algorithms is usually not sufficient. In this study, the investigation results of the performance for an improved hybrid optimization method (HOM) to overcome their disadvantages occurred in optimization process of the difficult problems by combining ABC with DE algorithms are presented. While the improved algorithm keeps the exploration ability by retaining their standard updating strategy in the employed bees step, it enhances the exploitation skill by using powerful mutation and crossover strategies of the DE algorithm into onlooker bees step. The HOM having very high convergence speed and performance is a novel and robust optimization method based on meta-heuristic approach. In order to appraise the performance of the HOM in the testing step, a sequence of the classical benchmark function has been utilized and the performance results of the proposed method are compared with the performance of the standard DE, ABC algorithms. The reached numerical results in this study illustrated that the search performance of the presented HOM is better than the standard ABC, DE algorithms.

WOS: 000415695400013, This contribution presents an approach for the modeling and prediction of surface roughness in the turning of AZ91D magnesium alloys using an artificial neural network. The experiments were conducted with CCGT, DCGT and VCGT cutting tools under minimum quantity lubrication and dry machining conditions. AZ91D alloys were machined at different cutting speeds and feed rates, and the depth of cut was kept constant. 15 out of 18 experimental data points were used for the training of the artificial neural network model and the remaining 3 were used for the testing process. The average percentage error was calculated as 0.000815 % and 0.663 % for training and testing, respectively. The model and target results were found to have extremely low error rates.

An annular ring compact microstrip antenna (ARCMA) constructed by loading a circular slot in the center of the circular patch antenna is a popular microstrip antenna due to its favorable properties. In this study, a method based artificial neural networks (ANNs) has been firstly applied for the computing the resonant frequency of ARCMAs. Multilayered perceptron model based on feed forward back propagation ANN has been utilized, and the constructed model have been separately trained with 8 different learning algorithms to achieve the best results regarding the resonant frequency of ARCMAs at dominant mode. To this end, the resonant frequencies of 80 ARCMAs with varied dimensions and electrical parameters in accordance with UHF band covering GSM, LTE, WLAN and WiMAX applications were simulated with a robust numerical electromagnetic computational tool, $$\hbox {IE3D}^\mathrm{TM}$$IE3DTM, which is based on method of moment. Then, ANN model was constructed with the simulation data, by using 70 ARCMAs for training and the remaining 10 for test. As the performances of the 8 learning algorithms are compared with each other, the best result is obtained with Levenberg---Marquardt algorithm. The proposed ANN model were confirmed by comparing with the suggestions reported elsewhere via measurement data published earlier in the literature, and they have further validated on an ARCMA fabricated in this study. The results achieved in this study show that ANN model learning with LM algorithm can be successfully used to compute the resonant frequency of ARCMAs without involving any sophisticated methods.

In this paper, a novel design of compact wideband multiple-input multiple-output (MIMO) antenna operating over a frequency range of 1.8–4.0 GHz at 10 dB is presented for mobile terminals. The MIMO antenna design consists of two symmetrical and orthogonal radiating elements with a small size of 15.5 × 16.5 mm2 printed on the corners of a mobile circuit board. The radiating element is composed of four meandered monopole branches with a strip-line fed by a probe. By triangularly trimming the corners of the common ground plane beneath the radiating elements, not only the mutual coupling is reduced, but also impedance bandwidth is increased. Although, the antenna in this form has sufficient correlation level between the radiating elements for MIMO operation, a novel design of plus-shaped parasitic element is inserted to the ground plane between those radiating elements in order to further enhance the isolation. The performance of the MIMO antenna is investigated in terms of s-parameters, radiation pattern, gain, envelope correlation coefficient (ECC), and total active reflection coefficient (TARC), and is verified through the measurements. The results demonstrate that the proposed MIMO antenna has good characteristics of wideband, isolation, gain, radiation pattern, and is compatible with LTE, WiMAX, and WLAN, besides it is small, compact, and embeddable in mobile terminals.

Inverse synthetic aperture radar (ISAR) imaging is an efficient technique to generate two-dimensional spatial distributions of radar cross-section of a target. The received signal of ISAR contains interphase errors resulting in blurring problem in the images due to motion effects of the target. In this study, a simple, stable, and robust method based on artificial bee colony (ABC) algorithm has been proposed for motion compensation (MoComp) to overcome the blurring problem in ISAR images. The minimum entropy was used as objective function in the ABC algorithm for optimally determining the parameters of velocity and acceleration. The proposed method was implemented to four different scenarios based on the two air target models to show performance of the ABC algorithm. The radar signal of the target without MoComp was given as inputs to the ABC algorithm to determine velocity and acceleration values so as to provide the clearest ISAR image. The proposed method was compared with a suggestion reported elsewhere using particle swarm optimization (PSO), PSO with island model, genetic algorithm. It is pointed out that the proposed method is more successful, stable and efficient in terms of the image quality, entropy values, and standard deviation. © 2014 Wiley Periodicals, Inc. Microwave Opt Technol Lett 56:2691–2698, 2014

This paper proposes a novel and simple expression for effective radius of annular-ring microstrip antennas (ARMAs) obtained using a recently emerged optimization algorithm of artificial bee colony (ABC) in calculating the resonant frequency at dominant mode (TM11). A total of 80 ARMAs having different parameters related to antenna dimensions and dielectric constants was simulated in terms of the resonant frequency with the help of an electromagnetic simulation software called IE3D™ based on method of moment. The effective radius expression was constructed and the unknown coefficients belonging to the expression were then optimally determined with the use of ABC algorithm. The proposed expression was verified through comparisons with the methods of resonant frequency calculation reported elsewhere. Also, it was further validated on an ARMA fabricated in this study. The superiority of the presented approach over the other methods proposed in the literature is that it does not need any sophisticated computations while achieving the most accurate results in the resonant frequency calculation of ARMAs.

In this work, the resonant frequency of C-shaped compact microstrip antennas (CCMAs) operating at UHF band is computed by using the adaptive neuro-fuzzy inference system (ANFIS). For this purpose, 144 CCMAs with various relative dielectric constants and different physical dimensions were simulated by the XFDTD software package based on the finite-difference time domain (FDTD) method. One hundred and twenty-nine CCMAs were employed for training, while the remaining 15 CCMAs were used for testing of the ANFIS model. Average percentage error (APE) values were obtained as 0.8413% and 1.259% for training and testing, respectively. In order to demonstrate its validity and accuracy, the proposed ANFIS model was also tested over the simulation data given in the literature, and APE was obtained as 0.916%. These results show that ANFIS can be successfully used to compute the resonant frequency of CCMAs.

WOS: 000326056100008, An application of artificial neural network (ANN) based on multilayer perceptrons (MLP) to compute the resonant frequency of E-shaped compact microstrip antennas (ECMAs) is presented in this paper. The resonant frequencies of 144 ECMAs with different dimensions and electrical parameters were firstly determined by using IE3D((tm)) software based on the method of moments (MoM), then the ANN model for computing the resonant frequency was built by considering the simulation data. The parameters and respective resonant frequency values of 130 simulated ECMAs were employed for training and the remaining 14 ECMAs were used for testing the model. The computed resonant frequencies for training and testing by ANN were obtained with the average percentage errors (APE) of 0.257% and 0.523%, respectively. The validity and accuracy of the present approach was verified on the measurement results of an ECMA fabricated in this study. Furthermore, the effects of the slots loading method over the resonant frequency were investigated to explain the relationship between the slots and resonant frequency.

This article presents new and accurate approximations for the Gaussian Q-function, which is an important tool in the field of communication theory. A genetic algorithm was employed to find the optimum coefficients of the proposed approximations. The accuracy of the new approximations was examined and compared with those of previous works in the literature. It was shown that the presented high-order exponential approximations provide better accuracy compared to the previously introduced approximations, in general, at the cost of slightly increased mathematical complexity., This article presents new and accurate approximations for the GaussianQ-function, which is an important tool in the field of communication theory. Agenetic algorithm was employed to find the optimum coefficients of the proposedapproximations. The accuracy of the new approximations was examined andcompared with those of previous works in the literature. It was shown that thepresented high-order exponential approximations provide better accuracycompared to the previously introduced approximations, in general, at the costof slightly increased mathematical complexity.

In this article, simple but efficient expressions for determining the dual-frequencies of equilateral triangular compact microstrip antennas (ETCMA) with a shorting-pin are presented. Two expressions related to offset factor functions were derived with the use of a differential evolution optimization algorithm. The dual-frequencies of an ETCMA with a shorting-pin were then calculated by multiplying the offset factor functions with the single resonant frequency formulation of a conventional equilateral triangular microstrip antenna. The proposed approach was demonstrated through successful comparison with simulated and measured data. © 2013 Wiley Periodicals, Inc. Microwave Opt Technol Lett 55:1227–1230, 2013; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.27580

A new microstrip-fed printed monopole antenna which is simple in design and compact in size is presented for simultaneously satisfying wireless local area network (WLAN) and worldwide interoperability for microwave access (WiMAX) bands. A simulation software package, CST Microwave Studio, has been used to model the proposed antenna, whose electrical characteristics and radiation performance are thoroughly analyzed as well. The proposed antenna, with small size of 28 × 51 mm2 on Rogers RT/Duroid® 5870 substrate with permittivity 2.33, was designed and fabricated. It was demonstrated that the measured 10 dB bandwidth for return loss is from 1.76 to 2.59 GHz, 3.44 to 3.89 GHz and 5.18 to 5.99 GHz, covering all the 2.4/5.2/5.8 GHz WLAN and 2.5/3.5/5.5 GHz WiMAX bands.

Simple and accurate closed-form formulas obtained by using a differential evolution algorithm are presented for the synthesis of coplanar waveguides (CPW). The results of the synthesis formulas proposed in this article are compared with those of the quasi-static analysis, the synthesis formulas reported by the other researchers and also the experimental works available in the literature. The accuracy of the proposed synthesis formulas is found to be better than 0.75% for 9256 CPWs samples. (C) 2008 Wiley Periodicals, Inc.

In this article, an application of clutter modeling and reduction techniques to synthetic aperture radar (SAR) images of moving and stationary target acquisition and recognition data is presented. Statistical modeling of the clutter signal within these particular SAR images is demonstrated. Lognormal, Weibull, and K-distribution models are analyzed for the amplitude distribution of high-resolution land clutter data. Higher-order statistics (moments and cumulants) are utilized to estimate the appropriate statistical distribution models for the clutter. Also, Kolmogorov-Smirnov (K-S) goodness-of-fit test is employed to validate the accuracy of the selected models. With the use of the determined clutter model, constant false-alarm rate detection algorithm is applied to the SAR images of several military targets. Resultant SAR images obtained by using the proposed method show that target signatures are reliably differentiated from the clutter background. © 2008 Wiley Periodicals, Inc. Microwave Opt Technol Lett 50: 1514–1520, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.23413

In this paper, a method based on clonal selection algorithm (CLONALG) is proposed for null steering of linear antenna arrays by controlling only the positions of selected elements. The CLONALG is a relatively novel population-based evolutionary algorithm inspired by the clonal selection principle of the human immune system. In order to illustrate the accuracy and flexibility of the proposed algorithm, several numerical examples of Chebyshev pattern with the single and double nulls imposed at the directions of interference are given.

This paper presents a simple method for determining the dielectric constant of microwave PCB substrates. In the presented method, a bandpass microstrip filter designed on the PCB substrate with a user-predicted dielectric constant value is implemented for a given center frequency. The simulation results of the designed bandpass filter are obtained by the help of microwave design software; XFDTD®. Experimental results regarding the filter frequency characteristic are accomplished by means of a vector network analyzer. The simulation results of the designed filter are modified to overlap with the experimental ones by varying the dielectric constant value. When the simulation and experimental results are overlapped, the value of dielectric constant is accurately selected. In order to illustrate the validity of proposed method, the dielectric constant values of flame resistant-4 (FR4) substrates are acquired at IEEE 802.11b/g and IEEE 802.11a wireless local area network (WLAN) application frequencies. The results obtained by using the presented method agree with the previous studies in the literature.

This letter presents a novel effective radius expression for determining the resonant frequency of circular microstrip patch antennas. The effective patch radius expression is constructed by using differential evolution algorithm and is valid for both electrically thin and thick circular microstrip antennas (MSAs). It is well suited to be used in the development of fast computer aided design algorithms. Numerical results obtained for the resonant frequencies of circular MSAs are in good agreement with the experimental results reported by several scientists. © 2007 Wiley Periodicals, Inc. Microwave Opt Technol Lett 49: 2395–2398, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.22767

In this paper, a clonal selection algorithm (CLONALG) based on clonal selection principle of immune system has been used for null steering in the antenna radiation pattern by controlling only the element positions of a linear array. Numerical examples of Chebyshev pattern with the single, multiple and broad nulls imposed at the directions of interference are given to show the accuracy and flexibility of the CLONALG. The sensitivity of the achieved patterns due to small variations of the element positions is also investigated by truncating the element positions.

A new and accurate expression for the edge extension in accurately predicting the resonant frequency of electrically thin and thick rectangular microstrip antennas is presented. First, a closed-form model for the edge extension is constructed by utilizing a differential evolution algorithm, the resonant frequency of rectangular microstrip antennas is then calculated by means of this edge extension expression. The calculations were carried out on 46 antennas with a range of different dimensions built on various substrates. The resonant frequency results presented in this letter show the better agreement with the experimental results as compared with those reported by the several researchers. A comparison between calculated and experimental resonant frequencies demonstrates that the edge extension model provides less than 0.7% errors on average. © 2007 Wiley Periodicals, Inc. Microwave Opt Technol Lett 49: 1848–1852, 2007; Published online in Wiley Inter-Science (www.interscience.wiley.com). DOI 10.1002/mop.22572

This paper presents a simple empirical model for the edge extension in accurately calculating the resonant frequency of electrically thin and thick rectangular microstrip antennas. Based on the experimental results available in literature, a closed-form formula for edge extension is constructed by utilizing the simplex search method; then the resonant frequency of rectangular microstrip antennas is calculated by using this edge extension expression. A comparison between the calculated and experimental resonant frequency values demonstrates that the edge extension expression provides less than 0.51% errors on average. The resonant frequency results presented in this work also show the better agreement with the experimental results as compared to those predicted by several researchers.

This letter presents the closed-from formulas for determining the patch dimensions of electrically thin and thick rectangular microstrip antennas. The presented formulas constructed by utilizing a differential evolution algorithm become very useful as computer-aided design (CAD) models for patch antenna design. A comparison between the calculated and experimental results derived from 33 patch antennas demonstrates that the proposed CAD formulas provide

In this study, three robust predicting methods, namely artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and support vector machine (SVM) were used for computing the resonant frequency of A-shaped compact microstrip antennas (ACMAs) operating at UHF band. Firstly, the resonant frequencies of 144 ACMAs with various dimensions and electrical parameters were simulated with the help of IE3D™ based on method of moment (MoM). The ANN, ANFIS and SVM models for computing the resonant frequency were then built by considering the simulation data. 124 simulated ACMAs were utilized for training and the remaining 20 ACMAs were used for testing the ANN, ANFIS and SVM models. The performance of the ANN, ANFIS and SVM models are compared in the training and test process. The average percentage errors (APE) regarding the computed resonant frequencies for training of the ANN, ANFIS and SVM were obtained as 0.457%, 0.399% and 0.600%, respectively. The constructed models were then tested and APE values as 0.601% for ANN, 0.744% for ANFIS and 0.623% for SVM were achieved. The results obtained here show that ANN, ANFIS and SVM methods can be successfully applied to compute the resonant frequency of ACMAs, since they are useful and versatile methods that yield accurate results., {"references":["K. L. Wong, \"Compact and broadband microstrip antennas,\" Wiley,\nInterscience, 2002.","A. A. Deshmukh and G. Kumar, \"Formulation of resonant frequency for\ncompact rectangular microstrip antennas,\" Microw Opt Techn Let, vol.\n49 no. 2, pp. 498 – 501, 2007.","A. Toktas, A. Akdagli, M.B. Bicer and A. Kayabasi, \"Simple formulas\nfor calculating resonant frequencies of C and H shaped compact\nmicrostrip antennas obtained by using artificial bee colony algorithm,\"\nJournal of Electromagnetic Waves and Applications, vol. 25, pp. 1718-\n1729, 2011.","A. Akdagli, M.B. Bicer and S. Ermis, \"A novel expression for resonant\nlength obtained by using artificial bee colony algorithm in calculating\nresonant frequency of C-shaped compact microstrip antennas,\" Turkish\nJournal of Electrical Engineering and Computer Sciences, vol. 19, pp.\n597-606, 2011.","A. Akdagli, A. Kayabasi and Đ. Develi, \"Computing Resonant Frequency\nof C-Shaped Compact Microstrip Antennas by Using ANFIS,\"\nInternational Journal of Electronics, vol. 102, no. 3, pp. 407-417, 2015.","B. L. Ooi and Q. Shen, \"A novel E-shaped broadband microstrip patch\nantenna,\" Microwave Opt TechnolLett, vol. 27, no. 5, pp. 348-352,\n2000.","A. A. Deshmukh and G. Kumar, \"Compact broadband E-shaped\nmicrostrip antennas,\" Electronics Letters, vol. 41, no. 18, 2005.","A. Khidre, K. F. Lee, F. Yang and A. Elsherbeni, \"Wideband Circulary\nPolarized E-shaped Patch Antenna for Wireless Application,\" IEEE\nTrans Antennas Propagat, vol. 52 no. 5, pp. 219-229, 2010.","A. Toktas and A. Akdagli, \"Computation of resonant frequency of Eshaped\ncompact microstrip antennas,\" Journal of the Faculty of\nEngineering and Architecture of Gazi University, vol. 27, pp. 847-854,\n2012.\n[10] A. Akdagli, A. Toktas, A. Kayabasi and Đ. Develi, \"An Application of\nArtificial Neural Network to Compute the Resonant Frequency of EShaped\nCompact Microstrip Antennas,\" Journal of Electrical\nEngineering- Elektrotechnicky Casopis, vol. 64, no. 5, pp. 317-322,\nSeptember 2013.\n[11] A.F. Sheta, A. Mohra, and S.F. Mahmoud, \"Multi-band operation of a\ncompact H-shaped microstrip antenna,\" Microw Opt Techn, vol. 35, pp.\n363-367, 2002.\n[12] A. Akdagli and A. Toktas, \"A novel expression in calculating resonant\nfrequency of H-shaped compact microstrip antennas obtained by using\nartificial bee colony algorithm,\" J Electromagnet Wave, vol. 24, no. 14-\n15, pp. 2049-4061, 2010.\n[13] A. Kayabasi, M. B. Bicer, A. Akdagli and A. Toktas, \"Computing\nResonant Frequency of H-Shaped Compact Microstrip Antennas\nOperating at UHF Band by Using Artificial Neural Networks,\" Journal\nof the Faculty of Engineering and Architecture of Gazi University, vol.\n26, no. 4, pp. 833-840, December 2011.\n[14] Z. N. Chen, \"Radiation pattern of a probe fed L-shaped plate antenna,\"\nMicrow OptTechnLet, vol. 27, pp. 410-413, 2000.\n[15] A. Kayabasi, A. Toktas, A. Akdagli, M. B. Bicer and D. Ustun,\n\"Applications of ANN and ANFIS to Predict the Resonant Frequency of\nL-shaped Compact Microstrip Antennas,\" Applied Computational\nElectromagnetic Society Journal - ACES, vol. 29, no. 6, pp. 460-469,\nJune 2014.\n[16] W. Chew, \"A broad-band annular-ring microstrip antenna,\" Antennas\nand Propagation, IEEE Transactions on, vol. 30, no. 5, pp. 918-922,\n1982.\n[17] A. Toktas, A. Akdagli, A. Kayabasi, D. Ustun and M. B. Bicer, \"A\nSimple and Accurate Expression for Resonant Frequency Calculation of\nAnnular-Ring Microstrip Antennas,\" International Journal of Microwave\nand Wireless Technologies, 1-7, 2014. DOI:\n0.1017/S1759078714000890.\n[18] A. Akdagli and A. Kayabasi, \"An Accurate Computation Method Based\non Artificial Neural Networks with Different Learning Algorithms for\nResonant Frequency of Annular Ring Microstrip Antennas,\" Journal of\nComputational Electronics, vol. 13, pp. 1014-1019, 2014.\n[19] A. Kayabasi and A. Akdagli, \"A Novel Method of Support Vector\nMachine to Compute the Resonant Frequency of Annular Ring Compact\nMicrostrip Antennas,\" Cogent Engineering, vol. 2, no. 1, 6 January\n2015.\n[20] A. Akdagli, A. Toktas, M. B. Bicer, A. Kayabasi, D. Ustun and K. Kurt,\n\"ANFIS Model for Determining Resonant Frequency of Rectangular\nRing Compact Microstrip Antennas,\" International Journal of Applied\nElectromagnetics Mechanics, vol. 46, no. 3, pp. 483-490, 27 February\n2014.\n[21] W. F. Richards, Y.T. Lo and D. D. Harrisson, \"An improved theory for\nmicrostrip antennas and applications,\" IEEE T. Antenn. Propag. vol. 29,\npp. 38-46, 1981.\n[22] K. Bhattacharyya and R. Garg, \"A generalized transmission line model\nfor microstip patches,\" IEE Proc. Microwave Antennas Propag. vol. 132,\npp. 93-98, 1985\n[23] A. Taflove, \"Computational electrodynamics: The finite-difference time\ndomain method,\" Boston, Artech House, 1995.\n[24] R. F. Harrington, \"Field computation by moment methods,\" Piscataway,\nNJ, IEEE Press, 1993.\n[25] S. Haykin, \"Neural networks: A comprehensive foundation,\" Macmillan\nCollege Publishing Company, New York, A.B.D., 1994.\n[26] C. G. Christodoulou and M. Georgiopoulos, \"Application of Neural\nNetworks in Electromagnetics,\" Artech House, MA, USA, 2001.\n[27] K. Guney, and S. S. Gultekin, \"Artificial neural networks for resonant\nfrequency calculation of rectangular microstrip antennas with thin and\nthick substrates,\" International Journal of Infrared and Millimeter\nWaves, vol. 25, no. 9, 2004.\n[28] J. S. R. Jang, \"ANFIS: Adaptive-network-based fuzzy inference\nsystem,\" IEEE T. Syst. Man. Cy. vol. 23, pp. 665-685, 1993. \n[29] K. Guney and N. Sarikaya, \"Adaptive neuro-fuzzy inference system for\ncomputing the resonant frequency of circular microstrip antennas,\"\nACES JOURNAL, vol. 19, no. 3, 2004.\n[30] K. Guney and N. Sarikaya, \"Computation of resonant frequency for\nequilateral triangular microstrip antennas using the adaptive neuro-fuzzy\ninference system,\" International Journal of RF and Microwave\nComputer-Aided Engineering, vol. 14, pp. 134-143, 2003.\n[31] N. V. Vapnik and A. Y. Chervonenkis, \"The necessary and sufficient\nconditions for consistency in the empirical risk minimization method,\"\nPattern Recognition and Image Analysis, vol. 1, no. 3, pp. 283-305,\n1991.\n[32] N. T. Tokan and F. Gunes, \"Support vector characterization of the\nmicrostrip antennas based on measurements,\" Progress In\nElectromagnetics Research B, vol. 5, pp. 49-61, 2008."]}

23nd Signal Processing and Communications Applications Conference (SIU) -- MAY 16-19, 2015 -- -- Inonu Univ, Malatya, TURKEY, WOS: 000380500900030, Heuristic algorithms which are artificial bee colony (ABC), differential evolution algorithm (DEA) and particle swarm optimization (PSO) algorithms are powerful evolutionary computation techniques for electronic circuit design. In this work, usage of ABC, FGA and PSO algorithms in the design of tenth orders Butterworth, and 1-dB Chebyshev low-pass filters are investigated and the obtained comparative results are presented. PSO algorithm obtained the effective and efficient design parameter results for Butterworth and 1-dB Chebyshev low-pass filters., Dept Comp Engn & Elect & Elect Engn, Elect & Elect Engn, Bilkent Univ