MF - Makale Koleksiyonu | Elektrik-Elektronik Mühendisliği Bölümü / Department of Electrical-Electronics Engineering
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Deri lezyonlarının evrişimsel yapay sinir ağları ile sınıflandırılması(Pamukkale Univ, 2022-07-10) Bilginer, Onur; Tunga, Burcu; Demirer, Rüştü MuratBu çalışmada Uluslararası Deri Görüntüleme Birliği tarafından 2019 yılında yayınlanan ve 25000’den fazla dermoskopik deri görüntüsü içeren ISIC 2019 veri seti kullanılarak 4 çeşit (Melanom, Melanositik Nevüs, Bazal Hücreli Karsinom, İyi Huylu Keratoz) deri pigmentasyonu Evrişimsel Sinir Ağları yöntemi yardımıyla sınıflandırılmıştır. Sınıflandırma yapılırken InceptionV3 yapay sinir ağı mimarisi kullanılmıştır. Deri görüntülerine önişlem olarak Hilbert Dönüşümü ve Yüksek Boyutlu Model Gösterilimi uygulanmıştır. Elde edilen sonuçlara göre test verisi üzerinde Hilbert Dönüşümü uygulanmış görüntülerde Bazal Hücreli Karsinom hastalığının sınıflandırılmasında %89 başarı oranı elde edilmiştir. Yüksek Boyutlu Model Gösterilimi ile Kontrast Artırımı uygulanan görsellerde ise Melanomun sınıflandırılmasında %78 başarı oranı elde edilmiştir.Öğe CNN-Based deep learning architecture for electromagnetic imaging of rough surface profiles(IEEE, 2022-10) Aydın, İzde; Budak, Güven; Sefer, Ahmet; Yapar, AliA convolutional neural network (CNN) based deep learning (DL) technique for electromagnetic imaging of rough surfaces separating two dielectric media is presented. The direct scattering problem is formulated through the conventional integral equations and the synthetic scattered field data is produced by a fast numerical solution technique which is based on Method of Moments (MoM). Two different special CNN architectures are designed and implemented for the solution of the inverse rough surface imaging problem wherein both random and deterministic rough surface profiles can be imaged. It is shown by a comprehensive numerical analysis that the proposed deep-learning (DL) inversion scheme is very effective and robust.Öğe Recovery of impenetrable rough surface profiles via CNN-based deep learning architecture(Taylor and Francis Ltd., 2022-08-18) Aydın, İzde; Budak, Güven; Sefer, Ahmet; Yapar, AliIn this paper, a convolutional neural network (CNN)-based deep learning (DL) architecture for the solution of an electromagnetic inverse problem related to imaging of the shape of the perfectly electric conducting (PEC) rough surfaces is addressed. The rough surface is illuminated by a plane wave and scattered field data is obtained synthetically through the numerical solution of surface integral equations. An effective CNN-DL architecture is implemented through the modelling of the rough surface variation in terms of convenient spline type base functions. The algorithm is numerically tested with various scenarios including amplitude only data and shown that it is very effective and useful.Öğe Enabling 5G indoor services for residential environment using VLC technology(Elsevier B.V., 2022-03-10) Miramirkhani, Farshad; Karbalayghareh, Mehdi; Zeydan, Engin; Mitra, RangeetVisible light communication (VLC) has emerged as a viable complement to traditional radio frequency (RF) based systems and as an enabler for high data rate communications for beyond-5G (B5G) indoor communication systems. In particular, the emergence of new B5G-based applications with quality of service (QoS) requirements and massive connectivity has recently led to research on the required service-levels and the development of improved physical (PHY) layer methods. As part of recent VLC standards development activities, the IEEE has formed the 802.11bb “Light Communications (LC) for Wireless Local Area Networking” standardization group. This paper investigates the network requirements of 5G indoor services such as virtual reality (VR) and high-definition (HD) video for residential environments using VLC. In this paper, we consider such typical VLC scenarios with additional impairments such as light-emitting diode (LED) nonlinearity and imperfect channel feedback, and propose hyperparameter-free mitigation techniques using Reproducing Kernel Hilbert Space (RKHS) methods. In this context, we also propose using a direct current biased optical orthogonal frequency division multiplexing (DCO-OFDM)-based adaptive VLC transmission method that uses precomputed bit error rate (BER) expressions for these RKHS-based detection methods and performs adaptive BER-based modulation-order switching. Simulations of channel impulse responses (CIRs) show that the adaptive transmission method provides significantly improved error rate performance, which makes it promising for high data rate VLC-based 5G indoor services.Öğe Inductor saturation compensation in three-phase three-wire voltage-source converters via inverse system dynamics(Institute of Electrical and Electronics Engineers Inc., 2022-05-01) Özkan, Ziya; Hava, Ahmet MasumIn three-phase three-wire (3P3W) voltage-source converter (VSC) systems, utilization of filter inductors with deep saturation characteristics is often advantageous due to the improved size, cost, and efficiency. However, with the use of conventional synchronous frame current control methods, the inductor saturation results in significant dynamic performance loss and poor steady-state current waveform quality. This article proposes an inverse dynamic model-based compensation (IDMBC) method to overcome these performance issues. For this purpose, two-phase exact modeling of the 3P3W VSC control system is obtained. Based on the modeling, the inverse system dynamic model of the nonlinear system is obtained and employed such that the nonlinear plant is converted to a virtual linear inductor system for linear current regulators to perform satisfactorily. Further, to control phase currents in the synchronous frame, a two-phase coordinate transformation is proposed. The IDMBC method is tested via dynamic command response and waveform quality simulations and experiments that employ saturable inductors reaching down from full inductance at zero current to 1/9th inductance at full current. The results obtained demonstrate the suitability of the method for 3P3W VSCs employing saturable inductors.Öğe Image recovery of inaccessible rough surfaces profiles having impedance boundary condition(IEEE, 2022) Sefer, Ahmet; Yapar, AliThis letter addresses a reconstruction algorithm of locally rough inaccessible surface profiles via the knowledge of the scattered field data under the consideration of the impedance boundary condition (IBC). To this aim, first, the synthetic scattered field data are obtained through the solution of the conventional surface integral equation (SIE) written on the rough surface. Then, the same SIE together with the data equation is solved iteratively via Newton's method to obtain the image of the rough surface profile. In the numerical implementation, the nonlinear ill-posed inverse problem is linearized in an iterative fashion via the Newton method and regularized by Tikhonov in the least-squares sense. The feasibility of the algorithm is provided via numerical examples, which shows that the method is effective and promising.Öğe Reconstruction algorithm for impenetrable rough surface profile under Neumann boundary condition(Taylor and Francis Ltd., 2022-05-24) Sefer, Ahmet; Yapar, AliIn this paper, an algorithm to reconstruct one-dimensional impenetrable rough surface from the knowledge of scattering field is presented. The rough surface is considered as locally perturbed and the scattering field data are collected above the roughness in a simple non-magnetic medium considering Neumann boundary condition. First, the surface integral equation constituted via the Neumann boundary condition is solved and scattering field data are observed synthetically. Then, the same surface integral equation together with the data equation are solved in an iterative fashion to reconstruct the surface variation. In the numerical implementation, the so-called ill-posed inverse problem is regularized with Tikhonov method and a least-squares solution is obtained by using Gaussian-type basis function. Finally, numerical examples are carried out to illustrate effectiveness of the method.Öğe Channel modeling and characterization for VLC-based medical body sensor networks: trends and challenges(IEEE, 2021-11-15) Dönmez, Barış; Mitra, Rangeet; Miramirkhani, FarshadOptical Wireless Communication (OWC) refers to transmission in unguided propagation media through the use of optical carriers, i.e., visible, Infrared (IR), and Ultraviolet (UV) bands. In this paper, we focus on indoor Visible Light Communication (VLC)-based Medical Body Sensor Networks (MBSNs) which allow the Light Emitting Diodes (LEDs) to communicate between on-body sensors/subdermal implants and on-body central hubs/monitoring devices while also serving as a luminaire. Since the Quality-of-Service (QoS) of the communication systems depends heavily on realistic channel modeling and characterization, this paper aims at presenting an up-to-date survey of works on channel modeling activities for MBSNs. The first part reviews existing IR-based MBSNs channel models based on which VLC channel models are derived. The second part of this review provides details on existing VLC-based MBSNs channel models according to the mobility of the MBSNs on the patient’s body. We also present a realistic channel modeling approach called site-specific ray tracing that considers the skin tissue for the MBSNs channel modeling for realistic hospital scenarios.Öğe A novel biometric identification system based on fingertip electrocardiogram and speech signals(Elsevier Inc., 2022-03) Güven, Gökhan; Güz, Ümit; Gürkan, HakanIn this research work, we propose a one-dimensional Convolutional Neural Network (CNN) based biometric identification system that combines speech and ECG modalities. The aim is to find an effective identification strategy while enhancing both the confidence and the performance of the system. In our first approach, we have developed a voting-based ECG and speech fusion system to improve the overall performance compared to the conventional methods. In the second approach, we have developed a robust rejection algorithm to prevent unauthorized access to the fusion system. We also presented a newly developed ECG spike and inconsistent beats removal algorithm to detect and eliminate the problems caused by portable fingertip ECG devices and patient movements. Furthermore, we have achieved a system that can work with only one authorized user by adding a Universal Background Model to our algorithm. In the first approach, the proposed fusion system achieved a 100% accuracy rate for 90 people by taking the average of 3-fold cross-validation. In the second approach, by using 90 people as genuine classes and 26 people as imposter classes, the proposed system achieved 92% accuracy in identifying genuine classes and 96% accuracy in rejecting imposter classes.Öğe Effect of scattering phase function on underwater visible light communication channel models(Elsevier Ltd, 2021-10) Miramirkhani, Farshad; Karbalayghareh, Mehdi; Uysal, MuratNon-sequential ray tracing simulations are commonly employed to model underwater visible light communication (VLC) channels. The accuracy of such simulations highly depends on how well the optical properties of water (i.e., absorption and scattering) as well as scattering phase function (SPF) are modeled in the simulation. Existing empirical models are only a function of chlorophyll concentration and particle composition and are independent of refractive index, size and concentration of particles. In this paper, we carry out an underwater VLC channel modeling study using the Mie SPF which provides a full description of the scattering from phytoplankton particles which dominate the optical properties of most oceanic waters. We obtain the channel impulse response (CIR) based on an extensive non-sequential ray tracing study and calculate the fundamental channel parameters such as channel gain and delay spread. Comparison of CIRs reveals out that deployment of simplified SPF models results in the overestimation of path loss with respect to Mie SPF. Our results clearly demonstrate the importance of selecting realistic SPF models for an accurate underwater VLC channel modeling. While highlighting the channel models, we discuss adaptive modulation technique to maximize the data rate under the constraint of a targeted bit error rate. Besides, the maximum achievable distance is also determined both in terms of analytical guarantees and computer simulations. The results reveal that larger transmission distances can be achieved through Mie SPF channel model.Öğe A fractional-order transitional Butterworth-Butterworth filter and its experimental validation(IEEE, 2021) Mahata, Shibendu; Herencsar, Norbert; Kubanek, David; Kar, Rajib; Mandal, Durbadal; Göknar, İzzet CemThis paper introduces the generalization of the classical Transitional Butterworth-Butterworth Filter (TBBF) to the Fractional-Order (FO) domain. Stable rational approximants of the FO-TBBF are optimally realized. Several design examples demonstrate the robustness and modeling efficacy of the proposed method. Practical circuit implementation using the current feedback operational amplifier employed as an active element is presented. Experimental results endorse good agreement (R-2 = 0.999968) with the theoretical magnitude-frequency characteristic.Öğe Circuits and Systems in Turkey [CAS in the World](IEEE, 2021) Yarman, Bekir Sıddık Binboğa; Göknar, İzzet CemReports on the activities of CASS chapters.Öğe IEEE CAS Activities In Central America And Mexico(IEEE, 2021) Yarman, Bekir Sıddık Binboğa; Göknar, İzzet CemReports on CASS chapter activities in Central America and Mexico.Öğe A path loss model for link budget analysis of indoor visible light communications(Istanbul Univ-Cerrahpasa, 2021-05) Miramirkhani, FarshadIn the context of beyond 5G indoor communication systems, visible light communications (VLC) has emerged as a viable supplement for existing radio frequency based systems and as an enabler for high data rate communications. However, the existing indoor VLC systems are limited by detrimental outages caused by fluctuations in the VLC channel gain because of user mobility. In this study, we proposed a tractable path loss model for indoor VLC that reflects the effect of room size and coating material of surfaces. We performed an extensive advanced ray tracing simulation to obtain the channel impulse responses within a room and presented a path loss model as a function of distance, room size, and coating material through curve fitting. In addition, path loss parameters such as the path loss exponent and the standard deviation of the shadowing component were determined. The simulation results indicate that path loss is a linear function of distance, path loss exponent is a function of room size and coating material, and shadowing follows a log normal distribution.Öğe Least minimum symbol error rate based post-distortion for adaptive mobile VLC transmission with receiver selection(Elsevier B.V., 2021-08) Miramirkhani, Farshad; Karbalayghareh, Mehdi; Mitra, RangeetIn the context of beyond-5G indoor communication systems, visible light communication (VLC) has emerged as a viable supplement for existing RF-based systems and as an enabler for high datarate communications. However, the existing indoor VLC systems are limited by detrimental outages caused by fluctuations in the VLC channel-gain due to user-mobility. Furthermore, the nonlinear characteristics of the light-emitting diode (LED) degrade the performance of VLC systems in the highpower regime by warping the input constellation. Additional performance-limits are introduced by inter-symbol interference (ISI) due to finite modulation-bandwidth of LEDs, and reflections from walls. In this paper, a random Fourier feature (RFF) based post-distorter is considered for mitigating the LED nonlinearity, and relevant expressions for the signal to noise ratio (SNR) are derived for a direct current biased optical orthogonal frequency division multiplexing (DCO-OFDM) system. Based on the derived expressions for SNR, the effects of user-mobility and ISI are mitigated by a DCO-OFDM based adaptive VLC transmission technique, which varies the transmission-rate/modulation-order under a specified error-rate constraint. Simulations are presented over channels obtained by ray-tracing, which indicates that the proposed algorithm achieves superior data-rates with a significantly lower error-rate.Öğe Generic BER analysis of VLC channels impaired by 3D user-mobility and imperfect CSI(Institute of Electrical and Electronics Engineers Inc., 2021-07) Reddy Sekhar, K.; Miramirkhani, Farshad; Mitra, Rangeet; Turlapaty, Anish ChandVisible light communications (VLC) has emerged as a high-speed, low-cost, and green supplement for the existing radio frequency (RF) based infrastructures. However, the performance of VLC based systems is found to degrade significantly due to detrimental outages caused by non-negligible variations in the VLC channel-gain, that are jointly induced by radial user-mobility and random photodetector-orientation (together designated as 3D mobility in this letter). In addition to the 3D user-mobility mentioned above, the performance of VLC based systems is further limited by imperfect channel-state information (CSI). Such degradations in the VLC-link caused by the aforementioned factors necessitate the quantification of performance-metrics for further benchmarking/receiver-design. In this work, an analytical expression for bit-error rate (BER) is derived for a single LED indoor VLC system considering the radial user-mobility, random receiver orientation, and imperfect CSI altogether. Further, the derived BER expressions are validated using computer-simulations using typical VLC channel models from the literature. A close agreement between the analytical and the simulated BER is observed, which verifies the accuracy of the presented analysis.Öğe Low pass filter design with improved stop-band suppression and synthesis with transformer-free ladders(John Wiley and Sons Inc, 2021-09) Yıldız, Serkan; Aksen, Ahmet; Kılınç, Sedat; Yarman, Bekir Sıddık BinboğaA new method to design transformer-free low pass (LP) ladder network with improved stop-band suppression performance is introduced. The parametric representation of back-end impedance of LP filter network is established with minimum impedance part and a Foster reactance part. The constructed impedance function is optimized by using real frequency technique. It has been shown that the proposed method provides LP filters which have superior stop-band suppression in comparison with classical transfer function-based filters with same complexity. The synthesis of the LP filter is obtained with the proposed element extraction procedure and resulted with fully realizable network elements in ladder form. An LP filter design and application by employing the proposed technique is provided. The measurement results of the prototyped filter are presented.Öğe FSRFT Based broadband double matching via passband extremums determination(Bajece (İstanbul Teknik Ünv), 2018-07-23) Köprü, RamazanFast simplified real frequency technique (FSRFT) is a numerical solver used to solve microwave broadband doublematching (DM) circuit design problems in a much faster and effective manner. Recently, it has been reported that an FSRFT based Matlab code can complete the design of a order lowpass lumped element double matching network to match a given generator and load impedance within an optimization time of only 0.6 seconds, a 47 fold less time than that of the same design done using the classical simplified real frequency technique (SRFT). FSRFT owes this superior speed performance to the fact that it tracks only (system unknowns plus 1) number of passband extremum points selected from among the number of gain data ( ). This work introduces a simple numerical technique called PED (passband extremums determination technique) to be used in determination of these passband extremum points (PEs). An exemplary order microwave bandpass DM circuit design using FSRFT based Matlab (of Mathworks Inc.) code and the simulation of this design via MWO (of AWR Corp.) has yielded the same circuit performance with an exact agreement. Thus, FSRFT, equipped with the PED, newly proposed hereby, might be used as a powerful solver in designing broadband circuits in many fields such as RF/microwave, radar, and communications.Öğe Optimisation of pedestrian detection system using FPGA-CPU hybrid implementation for vehicle industry(Inderscience Enterprises Ltd., 2019) Özcan, Ahmet Remzi; Tavşanoǧlu, Ahmet VedatImproved image processing and developing technologies are rapidly expanding the application areas of image processing systems. In recent years, pedestrian detection systems have become one of the major safety technologies used in the automotive industry. This paper presents an optimised real-time pedestrian detection system using an FPGA-CPU based hybrid design. The histograms of oriented gradients (HOG) algorithm, which is extensively used for feature extraction in pedestrian detection applications, was implemented on a low-end FPGA. In the study, the original HOG descriptors are designed in low complexity without sacrificing performance. The obtained features were classified on a low-power single board computer with support vector machine (SVM). Tests with the INRIA pedestrian database show that the proposed model has high potential for use as a real-time low-cost pedestrian detection system in practice.Öğe Low complexity least minimum symbol error rate based post-distortion for vehicular VLC(Institute of Electrical and Electronics Engineers Inc., 2020-10-22) Mitra, Rangeet; Miramirkhani, Farshad; Bhatia, Vimal; Uysal, MuratVehicular visible light communications (VLC) has emerged as a viable supplement for high speed next-generation vehicle to vehicle (V2V) communication systems. However, performance of a V2V-VLC link is impaired due to nonlinear transfer-characteristics of light emitting diodes (LEDs), and inter-symbol interference (ISI). In this article, a low-complexity least-squares based post-distortion algorithm is formulated over reproducing kernel Hilbert space (RKHS) for a multi-hop V2V-VLC link. The impairments encountered in V2V-VLC channels are mitigated in RKHS by a minimum symbol error-rate post-distorter using a low dimensional approximation of random Fourier features (RFF) (which is a soft approximation of the feature-map to RKHS), that facilitates computationally simple post-distortion under finite memory-budget. The convergence and the BER-performance of the proposed post-distorter is analyzed over realistic V2V VLC channels obtained via ray-tracing. From the analysis, and the presented computer-simulations, the proposed post-distorter is found to exhibit equivalent convergence characteristics and error-rate over reasonable distances, with much lower computational complexity.
