Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Conference Object Machine Learning-Based Antenna Selection and Secrecy Capacity Analysis(Institute of Electrical and Electronics Engineers Inc., 2025) Erdurak, Burak; Erdoǧan, Eylem; Gürkan, Filiz; 01. Izmir Institute of TechnologyThe performance of machine learning methods was analyzed to optimize antenna selection in wireless communication systems, and system's secrecy performance was observed. To enhance the antenna selection process, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), and the KNearest Neighbors (KNN) algorithm were utilized. Channel vectors were used as model inputs, aiming to select the most optimal transmission path among N possible candidates. During the training phase, the antenna with the highest Signal-to-Noise Ratio (SNR) was selected for data labeling. The performance of Single-Input Multiple-Output (SIMO), Multiple-Input SingleOutput (MISO), and Multiple-Input Multiple-Output (MIMO) system architectures was evaluated using model accuracy and the F1-score. Additionally, the secrecy capacity corresponding to the selected antennas was computed, demonstrating the feasibility of secure communication. The results indicate that deep learningbased methods achieved higher accuracy, with the CNN model emerging as the most successful approach, reaching an accuracy of over 95% across all system configurations. © 2025 Elsevier B.V., All rights reserved.Article Citation - WoS: 8Citation - Scopus: 9Dynamic Shared Spectrum Allocation for Underlaying Device-To Communications(Institute of Electrical and Electronics Engineers Inc., 2017) Özbek, Berna; Özbek, Berna; Le Ruyet, Didier; 03.05. Department of Electrical and Electronics Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyThis article provides an overview on spectrum sharing in D2D underlaying communications for 5G and beyond 5G applications. Various spectrum sharing algorithms are summarized within a framework of underlaying D2D communications in cellular networks to increase spectrum efficiency. Dynamic spectrum sharing algorithms in the frequency, power, and spatial dimensions are proposed for underlaying D2D communications with both single antenna and multiple antennas at the base station. Performance evaluations show the effectiveness of the proposed algorithms in terms of average data rate per D2D pair.Conference Object Citation - Scopus: 2Resource Allocation for User-Relay Assisted Miso-Ofdma Networks(Institute of Electrical and Electronics Engineers Inc., 2015) Baştürk, İlhan; Özbek, Berna; 03.05. Department of Electrical and Electronics Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyThe next generation cellular networks request higher capacity and coverage that user-relay assisted Orthogonal Frequency Division Multiple Access (OFDMA) networks are costeffective solutions to meet these demands. These networks can be enriched with multiple antennas in order to obtain a diversity gain to combat signal fading and to achieve more capacity gain without increasing the bandwidth or transmit power. However, radio resource management (RRM) such as relay selection and resource allocation (RA) is important in such a multi-user, multirelay and multi-antenna environment to fully take advantage of multiple-input single-output (MISO)-OFDMA based user-relay assisted cellular networks. Thus, we propose a RA algorithm for these networks to reveal the benefits of the combination of userrelaying and multiple antennas technologies and compare the proposed scheme with existing schemes in terms of percentage of satisfied users and cell-edge users' data rate.Conference Object Citation - WoS: 2Citation - Scopus: 2A novel square-spiral strip antenna(Institute of Electrical and Electronics Engineers Inc., 2007) Saynak, Uğur; Kuştepeli, Alp; Kuştepeli, Alp; 03.05. Department of Electrical and Electronics Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyA square-spiral strip antenna is designed considering the procedure used to obtain log-periodic antennas. Simulation results of the new design are compared with those of the well known and widely used Archimedean spiral antenna in terms of the frequency dependency. The effect of dielectric substrate used to support the antennas is also investigated.