Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
12 results
Search Results
Publication Metadata only Wide Angle Frequency Scanning Antenna for X-Band Applications(Institute of Electrical and Electronics Engineers Inc., 2020) Karamzadeh, Saeid; Rafiei, Vahid; Karamzadeh, Saeid, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Rafiei, Vahid, Microwave and Antenna Group, GraphenePi Company, Istanbul, TurkeyBeam Steering antennas are a significant part of the communication systems applications requiring tracking or frequent repositioning. In this work, a new high gain broadband leaky-wave antenna is presented for X-band applications. The impedance bandwidth of the proposed Antenna is 32.65% and the scanning angle is 160 degrees. The fabricated antenna results are in good agreement with the simulation results. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Circularly Polarized MTS Based Antenna Design for C Band Applications, C Band Uygulamalar icin Dairesel Polarize MTS Tabanl Anten Tasarm(Institute of Electrical and Electronics Engineers Inc., 2020) Karamzadeh, Saeid; Rafiei, Vahid; Karamzadeh, Saeid, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Rafiei, Vahid, Microwave and Antenna Group, GraphenePi Company, Istanbul, TurkeyA new broadband metasurface (MTS) circularly polarized (CP) patch array utilizing a sequential-phase feeding network is presented. In this study, the MTS method is used to increase the 3-dB axial ratio (AR) and impedance bandwidths. The prototype of the proposed array has been fabricated to validate designed parameters. The measured S11<-10dB is 2.1 GHz (4.5-6.6 GHz), and the measured 3-dB AR bandwidth is 1.3 GHz (4.9-6.2 GHz). The measured peak gain is about 16.4dBic and the gain variation is less than 3 dB within the AR bandwidth. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Faster Wi-Fi Fingerprinting Using Feature Selection(Institute of Electrical and Electronics Engineers Inc., 2020) Aydin, Hurkan M.; Ali, Muhammad Ammar; Gelal, Ece; Aydin, Hurkan M., Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ali, Muhammad Ammar, Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Gelal, Ece, Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyWi-Fi fingerprinting has been widely used for indoor positioning, as Wi-Fi technology is easily deployed and supported. In fingerprinting, a database is created using the received signal strength indicator (RSSI) values in the area of interest, position prediction is performed by finding the best match for a measured RSSI among the values in the database. As location positioning gains importance for continuous interactive (CI) applications in large indoor spaces such as malls and airports, the fingerprinting databases become larger, making it computationally more difficult to position targets in real-time. On the other hand, CI applications such as Augmented Reality (AR) require low-latency positioning for a good user experience. In this work, we propose to use feature selection methods along with the K-nearest neighbors (KNN) classification and regression algorithms in order to create a simple and swift location positioning system. Our evaluation of various feature selection methods shows that computation times for positioning can be reduced by 75% using feature selection. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Forecasting Electricity Consumption Using Deep Learning Methods with Hyperparameter Tuning, Hiperparametre Ayarl Derin Orenme Yontemleri ile Elektrik Tuketiminin Tahmini(Institute of Electrical and Electronics Engineers Inc., 2020) Ayvaz, Serkan; Onur Arslan; Ayvaz, Serkan, Department of Software Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Onur Arslan, null, Department of Software Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study, it is tried to estimate one-day electricity consumption by using deep learning methods with a dataset which includes the change in time-dependent electricity consumption. After explaining the time series components and machine learning concepts, general information about previous studies on electricity consumption estimation is given. Since the dataset used is a time series, all the features are emphasized in detail and necessary operations like resample and differencing are performed before proceeding to the modeling. Tuning was applied on hyperparameters which significantly affect the performance of the algorithms used in the modeling stage and the most suitable parameters were searched for each method. Then the best results were compared with each other and the method with the lowest error rate was determined. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Reliable Image Transmission in Wireless Sensor Networks for Smart Grid Applications(Institute of Electrical and Electronics Engineers Inc., 2020) Jassim, Mostafa Shamil; Boluk, Pinar Sarisaray; Jassim, Mostafa Shamil, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Boluk, Pinar Sarisaray, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyWith the rapid development of Smart Grids over wireless sensor networks, the reliable image and video transmission has become more imperative and faces many challenges in wireless harsh environment. Transmission of the image data may experience distortions that decrease the quality of the image due to noise, interference and path loss. In this paper, we show the effect of two error correction algorithms (Static and Adaptive RS) in order to increase the perceptual quality of the transmitted images. Here, as Static Reed-Solomon (RS) coding utilizes additional bits to the information transmitted to correct errors at the receiver side. Unlike Static RS, Adaptive RS is a derived version of the Reed-Solomon that sets the error correction codes of the algorithm based on the distance between the nodes adaptively. Performance results obtained from numerous simulations indicate that the Adaptive RS exhibits much better performance results in terms of PSNR, BER, and Throughput than Static RS. It is good candidate for providing application layer perceptual quality requirements for Smart Grid applications. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Ultrasonic evaluation of surface-breaking crack depth in steel-fiber reinforced concrete(International Society for Structural Health Monitoring of Intelligent Infrastructure, ISHMII, 2021) Kirlangiç, Ahmet Serhan; Kirlangiç, Ahmet Serhan, Department of Civil Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn practice, the commonly used P-wave based ultrasonic inspection tests for concrete are adequate to evaluate either material thickness or its elastic properties. In general, the test configurations of such methods are not suitable for the estimation of the depth of surface-breaking cracks, which is crucial to predict the residual load capacity of a structural member. The methods based on the ultrasonic surface waves (UWS), on the other hand, have the potential to realize such inspection. Since the surface waves propagating in a medium display variation when they encounter with a vertically aligned crack, it is possible to estimate its depth by monitoring the changes in the wave characteristics. Based on this principle, hereby a UWS based diagnostic procedure is presented for the estimation of depth of surface-breaking cracks in concrete elements. The diagnosis is demonstrated on six lab-scale steel-fiber reinforced concrete (SFRC) beam specimens, which are subjected to the crack-controlled three-point bending test in order to create a specific crack depth in each one. The beams are then examined by implementing a multi-channel ultrasonic test configuration. The recorded surface waves propagating in the beams are processed by utilizing the signal processing techniques, including wavelet transform and two-dimensional Fourier transform to extract two diagnostic features related to the wave attenuation and dispersion in phase velocity. Finally, the reliability of these two features are demonstrated by examining their sensitivities with respect to the visually measured crack depths. © 2022 Elsevier B.V., All rights reserved.Publication Metadata only The analysis of feature selection with machine learning for indoor positioning(Institute of Electrical and Electronics Engineers Inc., 2021) Aydin, Hurkan M.; Ali, Muhammad Ammar; Gelal, Ece; Aydin, Hurkan M., Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ali, Muhammad Ammar, Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Gelal, Ece, Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyIndoor positioning is useful in various venues including warehouses, convention centers, malls, airports, nursing homes. In these scenarios, reducing the complexity of location estimation both improves responsiveness and helps to elongate battery life of the mobile device. In this work, we carry out a detailed analysis of the impact of Principal Component Analysis (PCA) on the computational complexity and accuracy with different machine learning algorithms on a large data set containing 520 APs. We compare the algorithms' training and testing times, as well as their accuracies in the presence and absence of PCA. Our results show that (i) PCA significantly reduces both the training and testing times for classification and regression using k-nearest neighbor (kNN) and support vector machine (SVM) algorithms while preserving if not improving accuracy, (ii) PCA slightly improves the training/testing times for regression using multi-layer perceptron (MLP), (iii) random forest (RF) does not perform well with PCA. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Ensemble based feature selection with hybrid model, Hibrit model ile topluluk tabanli öznitelik seçimi(Institute of Electrical and Electronics Engineers Inc., 2021) Demir, Ceylan; Akyüz, Süreyya; Göksel, Izzet; Demir, Ceylan, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey, Matematik Bölümü, İstanbul Teknik Üniversitesi, Istanbul, Turkey; Akyüz, Süreyya, Uygulamali Matematik Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Göksel, Izzet, Matematik Bölümü, İstanbul Teknik Üniversitesi, Istanbul, TurkeyIn this study, a new mathematical model established with an ensemble-based approach, is proposed and applied to a large-scale data set consisting of three classes, whose features were extracted, obtained from birthday tweets. In this model, bagging method, which is one of the data variation methods, was applied first, and then a hybrid model combining the two approaches was created by applying the function variation approach obtained by using more than one feature selection method together. The resulting hybrid ensemble was first classified with the multi-class Support Vector Machines (SVM) algorithm, and then pruned with the ensemble pruning approach we propose in this study. By comparing the prediction success of the proposed model with the studies in the literature, it is observed that higher estimation success is obtained in comparison to those studies. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Modeling and simulation of the control performance of a reaction wheel pendulum(Institute of Electrical and Electronics Engineers Inc., 2021) Aghaei, Vahid Tavakol; Komurcu, Buse Ilayda; Saka, Didar; Aydogan, Bahar; Kizilca, Gizem; Erener, Seda; Aghaei, Vahid Tavakol, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Komurcu, Buse Ilayda, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Saka, Didar, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Aydogan, Bahar, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kizilca, Gizem, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Erener, Seda, Mechatronics Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyThe reaction wheel pendulum system is an underactuated system with a nonlinear structure that is used for both academic research as a benchmark and real-time control applications. The open-loop unstability of this system draws the attention of experts in the field of control. They use different classical and modern control algorithms to stabilize it. In this paper, a mathematical nonlinear model of the reaction wheel pendulum system is derived by using the Lagrangian method. After the linearization of the structure of the obtained model, two classical control methods as PID and full state-feedback controller have been used to stabilize it. To show the efficiency of the designed controllers, time responses of the system in a simulation-based environment considering noise-free and noisy conditions have been presented. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only A dynamic recurrent neural networks-based recommendation system for banking customers, Bankacilik müşterileri için dinamik tekrarlayan sinir aǧlari tabanli bir tavsiye sistemi(Institute of Electrical and Electronics Engineers Inc., 2021) Hasan, Avci; Sakar, C. Okan; Hasan, Avci, Bilgisayar Mühendisliõi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Sakar, C. Okan, Bilgisayar Mühendisliõi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn recent years, machine learning approaches are replacing traditional methods in many industries. In parallel with these developments, marketing operations in banking started to be supported with machine learning based applications. In this study, a highly applicable product recommendation approach for banking customers was implemented using deep learning techniques. For this purpose, the dynamic recurrent neural network (DREAM) architecture, which was previously applied to e-commerce data, has been applied to banking customer data for recommendation system design. Comparative experiments with long short term memory and multilayer perceptron-based solutions have shown that the DREAM based recommendation approach has significant potential to be used in product proposal in the banking sector. © 2022 Elsevier B.V., All rights reserved.