Browsing by Author "Zoral, E. Yesim"

Now showing 1 - 8 of 8

Application of dielectric resonator based metamaterial in waveguide coupler
(Institute of Electrical and Electronics Engineers Inc., 2016) Gizem Kalender; Emine Yeşim Zoral; Mustafa Seçmen; Zoral, E. Yesim; Secmen, Mustafa; Kalender, Gizem
In this study an implementation of the metamaterial structure is used in a waveguide directional coupler. For this purpose a four-hole waveguide directional coupler in X-band is designed. Then the block of dielectric-resonator array is inserted between isolation port and holes of the coupler and the performances of the coupler with and without dielectric resonators are compared in terms of the coupling and isolation. The obtained results show that the coupler with dielectric resonators significantly improves the coupling and isolation performances at a new operation frequency band at which the traditional coupler does not work. Therefore the metamaterial structure attains multi-band characteristics to the coupler. Besides this new frequency band can be shifted by arranging the distance between the dielectric resonators and holes. Finally it is also observed that the bandwidth of the new frequency band can be increased by using more dielectric resonators in the array. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 4
Comparison of Scattered Signal Waveform Recovery Techniques Under Low SNR for Target Identification
(IEEE, 2017) M. Alper Selver; Mustafa Secmen; E. Yesim Zoral; Selver, M. Alper; Zoral, E. Yesim; Secmen, Mustafa
Target identification from scattered electromagnetic waves is a difficult problem especially at low SNR levels which prevents extraction of distinguishable information. When a scattered signal is corrupted by noise it should be recovered before further processing such as feature extraction and classification. This recovery can be performed in time domain frequency domain or via time-frequency analysis. In this study three important techniques are used for distortion correction and their performances are compared. The analyses are performed with both simulated and measured data from various conducting and dielectric targets having different size geometry and material type.
Real Time Classification of Targets Using Waveforms in Resonance Scattering Region
(IEEE, 2015) M. Alper Selver; E. Yesim Zoral; Mustafa Secmen; Selver, M. Alper; Zoral, E. Yesim; Secmen, Mustafa
The classification of similar shaped objects from scattered electromagnetic waves is a difficult problem as it heavily depends on the aspect angle. The reduction of the adverse effects of the aspect angle is possible by extracting distinguishable features from the scattered signals. In this paper we propose a target identification method in resonance scattering region using a novel structural feature set based on scattered signal waveform. The feature set carries out a triangularization process to model the hills and valleys of the scattered signal. Once these sub-waveforms are identified their peaks widths increase and decrease rates are calculated for each of them. Together with the inter-distance between the sub-waves feature vector is constructed. Then cross validation strategies are used to design a classifier using multi-layer perceptron network. The simulations performed by two different target libraries, dielectric rods with different permittivity and small scale aircraft models show very high accuracy of the proposed system in real time.
Real time classification of targets using waveforms in resonance scattering region
(Institute of Electrical and Electronics Engineers Inc., 2015) Alper Mustafa Selver; Emine Yeşim Zoral; Mustafa Seçmen; Selver, M. Alper; Zoral, E. Yesim; Secmen, Mustafa
The classification of similar shaped objects from scattered electromagnetic waves is a difficult problem as it heavily depends on the aspect angle. The reduction of the adverse effects of the aspect angle is possible by extracting distinguishable features from the scattered signals. In this paper we propose a target identification method in resonance scattering region using a novel structural feature set based on scattered signal waveform. The feature set carries out a triangularization process to model the hills and valleys of the scattered signal. Once these subwaveforms are identified their peaks widths increase and decrease rates are calculated for each of them. Together with the inter-distance between the sub-waves feature vector is constructed. Then cross validation strategies are used to design a classifier using multi-layer perceptron network. The simulations performed by two different target libraries, dielectric rods with different permittivity and small scale aircraft models show very high accuracy of the proposed system in real time. © 2017 Elsevier B.V. All rights reserved.
The effects of geometric scattered signal waveform modeling on target identification performance
(Institute of Electrical and Electronics Engineers Inc., 2017) Alper Mustafa Selver; Mustafa Seçmen; Emine Yeşim Zoral; Selver, M. Alper; Zoral, E. Yesim; Secmen, Mustafa
Target identification from scattered signals using time domain techniques depend significantly on the waveform. Recently a novel feature set is proposed which encounter structural properties of the waveform and collects local extrema points to model the scattered signal via triangularization. Then using this piecewise model it extracts several morphological features and employs them for target identification through classification. This study expands that approach by modeling the scattered signal with other geometric shapes and accordingly by enriching the feature set. Such an approach requires careful representation of the waveform model since more than one morphology is considered to represent sub-waves of the waveform. The effects of the proposed approach are observed by applications on spherical targets having different size and material type. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 5
Citation - Scopus: 5
Transferring Synthetic Elementary Learning Tasks to Classification of Complex Targets
(Institute of Electrical and Electronics Engineers Inc., 2019) Alper Mustafa Selver; Tugce Toprak; Mustafa Seçmen; Emine Yeşim Zoral; Toprak, Tugce; Zoral, E. Yesim; Selver, M. Alper; Secmen, Mustafa
Deep learning has a promising impact on target classification performance at the expense of huge training data requirements. Therefore the use of simulated data is inevitable for convergence of deep models (DMs). However generating synthetic data for real-life complex targets can be quite tedious and is not always possible. In this study DMs trained with synthetic one-dimensional scattered data of elementary targets are transferred to classify complex targets from measured signals for the first time. For this purpose a novel system is proposed by combining three strategies: first initial training of DMs using analytical and simulated time domain scattered data obtained from the basic targets, second the last layers of initial DMs are fine-tuned by transfer learning using measured signals of the real targets, and third an ensemble model is developed to generate a model that can completely represent real target characteristics by combining diverse and complementary properties of the fine-tuned DMs. The proposed system provides higher accuracy sensitivity and specificity performances compared to the existing methods. © 2019 Elsevier B.V. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 1
Utilizing Resonant Scattering Signal Characteristics of Magnetic Spheres via Deep Learning for Improved Target Classification
(IEEE, 2019) M. Alper Selver; Tugce Toprak; Mustafa Secmen; E. Yesim Zoral; Toprak, Tugce; Zoral, E. Yesim; Selver, M. Alper; Secmen, Mustafa
Object classification using LAte-time Resonant Scattering Electromagnetic Signals (LARSESs) is a significant problem found in different areas of application. Due to their special properties spherical objects play an important role in this field both as a challenging target and analytical LARSES source. Although many studies focus on their detailed analysis the challenges associated with target classification by resonant LARSESs from multi-layer spheres have not been investigated in detail. Moreover existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and coatings. However especially for metamaterials magneto-dielectric inclusions require consideration of magnetic properties as well as dielectric ones. In this respect this study shows that the utilization LARSESs of magnetic spheres provides diverse information and features which result with superior object classification performance. For this purpose first time domain LARSESs are generated numerically for single and multi-layer radially symmetrical dielectric and magnetic spheres. Then by using emerging deep learning tools particularly Convolutional Neural Network (CNNs) which are trained with spheres having different material properties a high multi-layer object classification performance is achieved. Moreover by extending the proposed strategy to measured data via modern data augmentation and transfer learning techniques an improved classification performance is also obtained for more complex targets.
Citation - WoS: 2
Citation - Scopus: 2
Utilizing resonant scattering signal characteristics via deep learning for improved classification of complex targets
(Turkiye Klinikleri, 2021) Tugce Toprak; Alper Mustafa Selver; Mustafa Seçmen; E. Yesim Zoral; Toprak, Tugce; Zoral, E. Yesim; Yesim Zoral, E.; Alper Selver, M.; Selver, M. Alper; Secmen, Mustafa
Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and coatings. However especially for metamaterials magneto-dielectric inclusions require consideration of magnetic properties as well as dielectric ones. In this respect this study shows that the utilization late-time resonant scattering electromagnetic signals of magnetic spheres provide diverse information and features which result in superior object classification performance. For this purpose first time-domain late-time resonant scattering electromagnetic signals are generated numerically for single and multilayer radially symmetrical dielectric and magnetic spheres. Then by using emerging deep learning tools particularly convolutional neural networks trained with spheres having different material properties a high multilayer object classification performance is achieved. Furthermore by incorporating the frequency characteristics of the late-time resonant scattering electromagnetic signals to the classification process through Fourier transform and convolutional neural network layers for feature extraction a convolutional neural network with long short term memory algorithm is developed. The outcome of the proposed algorithm design is shown to be particularly successful even in the case of limited available data on challenging targets. This extended strategy is also shown to outperform modern data augmentation and transfer learning techniques in terms of accuracy as well as the computational cost. © 2021 Elsevier B.V. All rights reserved.