WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
38 results
Search Results
Now showing 1 - 10 of 38
Conference Object Citation - Scopus: 2Outage Probability Analysis of Triple-Hybrid Rf/Fso Communication System(Ieee, 2024) Bakirci, Emre Berker; Ahrazoglu, Evla Safahan; Altunbas, Ibrahim; Erdogan, EylemTerahertz (THz) and free space optical (FSO) transmission techniques are considered as alternatives for radio frequency (RF) transmission to meet the requirements for the sixth generation and beyond wireless communication systems. However, these transmission techniques may experience high level of deterioration under different weather conditions. In this study, triple-hybrid RF/FSO/THz system is proposed to enhance the system performance. The results have shown that the proposed system has improved outage probability performance under wide range weather conditions compared to only RF, only FSO, and only THz systems as well as dual-hybrid systems (RF/FSO, RF/THz, and FSO/THz). Theoretical results are validated via computer simulations.Conference Object Improvements on a Multi-Task Bert Model(Ieee, 2024) Agrali, Mahmut; Tekir, SelmaPre-trained language models have introduced significant performance boosts in natural language processing. Fine-tuning of these models using downstream tasks' supervised data further improves the acquired results. In the fine-tuning process, combining the learning of tasks is an effective approach. This paper proposes a multi-task learning framework based on BERT. To accomplish the tasks of sentiment analysis, paraphrase detection, and semantic text similarity, we include linear layers, a Siamese network with cosine similarity, and convolutional layers to the appropriate places in the architecture. We conducted an ablation study using Stanford Sentiment Treebank (SST), Quora, and SemEval STS datasets for each task to test the framework and its components' effectiveness. The results demonstrate that the proposed multi-task framework improves the performance of BERT. The best results obtained for sentiment analysis, paraphrase detection, and semantic text similarity are accuracies of 0.534 and 0.697 and a Pearson correlation coefficient of 0.345.Conference Object Citation - WoS: 1Konteyner Görüntülerini Kullanarak Hasar Tespiti ve Sınıflandırması(IEEE, 2020) Imamoglu, Zeynep Ekici; Tuglular, Tugkan; Bastanlar, YalinIn the logistics sector, digital transformation is of great importance in terms of competition. In the present case, container warehouse entry / exit operations are carried out manually by the logistics personnel including container damage detection. During container warehouse entry / exit process, the process of detecting damaged containers is carried out by the personnel and several minutes are required to upload to the IT system. The aim of our work is to automate the detection of damaged containers. This way, the mistakes made by the personnel will be eliminated and the process will be accelerated. In this work, we propose to use a convolutional neural network (CNN) that takes the container images and classify them as damaged or undamaged. We modeled the problem as a binary classification and employed different CNN models. The result we obtained shows that there is no single best method for the classification. It is shown how the dataset was created and how the parameters used in the layered structures affect the models employed in this study.Conference Object Citation - WoS: 1An Origami-Inspired Low-Cost Waveguide Design, Fabrication and Measurements for X-Band Satellite Communication Systems(IEEE, 2023) Karatay, Anıl; Ataç, Enes; Yaman, FatihIn many applications such as satellite communication, transmission lines are required and waveguides are widely used in these applications. This passive component, which is an indispensable element of microwave systems, is generally not suitable for practical and low-cost applications due to being produced from costly and heavy metals. Therefore, nowadays, the tendency to use low-cost, light and practical components has increased. In this study, origami-inspired waveguide design for X-band satellite communication systems is aimed. This component, which is formed by folding a paper into a three-dimensional structure and covering it with a conductive material, is both practical and fast to produce, portable and adjustable. The obtained simulation results match well with the experimental results, and it has been proven that the paper-based waveguide performs as well as the conventional aluminum waveguide. This makes the proposed method an innovative and cost-effective solution for waveguide fabrication.Article Citation - WoS: 2Evaluation of Malassezia Species by Fourier Transform Infrared (ft-Ir) Spectroscopy(Ankara Microbiology Society, 2011) Ergin, Çağrı; Vuran, M. Emre; Gök, Yaşar; Özdemir, Durmuş; Karaarslan, Aydın; Kaleli, İlnur; Çon, Ahmet HilmiMalassezia species which are lipophilic exobasidiomycetes fungi, have been accepted as members of normal cutaneous flora as well as causative agent of certain skin diseases. In routine microbiology laboratory, species identification based on phenotypic characters may not yield identical results with taxonomic studies. Lipophilic and lipid-dependent Malassezia yeasts require lipid-enriched complex media. For this reason, Fourier transform infrared (FT-IR) spectroscopy analysis focused on lipid window may be useful for identification of Malassezia species. In this study, 10 different standard Malassezia species (M.dermatis CBS 9145, M.furfur CBS 7019, M.japonica CBS 9432, M.globosa CBS 7966, M.nana CBS 9561, M.obtusa CBS 7876, M.pachydermatis CBS 1879, M.slooffiae CBS 7956, M.sympodialis CBS 7222 and M.yamatoensis CBS 9725) which are human pathogens, have been analyzed by FT-IR spectroscopy following standard cultivation onto modified Dixon agar medium. Results showed that two main groups (M1; M.globosa, Robtusa, M.sympodialis, M.dermatis, M.pachydermatis vs, M2; M.furfur, M.japonica, M.nana, M.slooffiae, M.yamatoensis) were discriminated by whole spectra analysis. M.obtusa in M1 by 1686-1606 cm(-1) wavenumber ranges and M.japonicum in M2 by 2993-2812 cm(-1) wavenumber ranges were identified with low level discrimination power. Discriminatory areas for species differentiation of M1 members as M.sympodialis, M.globosa and M.pachydermatis and M2 members as M.furfur and M.yamatoensis could not be identified. Several spectral windows analysis results revealed that FT-IR spectroscopy was not sufficient for species identification of culture grown Malassezia species.Conference Object Consistency Analysis of Kalman Filter for Modal Analysis of Structures(Institute of Electrical and Electronics Engineers Inc., 2009) Tanyer, İlker; Özen, Serdar; Dönmez, Cemalettin; Altınkaya, Mustafa AzizIn this paper, Consistency Analysis of Kalman Filter for Modal Analysis of Structural Systems is made. As a future work, A fundamental Modal Analysis algorithm, Eigensystem Realization Algorithm(ERA) will be used with Kalman filters together to make a modal parameter estimation for a structural system. By applying ERA to the impulse response measurements taken from the structure, a state-space representation will be written. Kalman filter will be used as a state estimator in this study and it will have a critical role on minimizing the measurement noise. Before using Kalman filter with ERA, a consistency analysis of Kalman filter is made for artificial impulse response data of the structural system.Conference Object A Study on Nonlinear Photonic Crystal Optical Switching With Chi((3)) Type Material(Institute of Electrical and Electronics Engineers Inc., 2009) Karakılınç, Özgür Önder; Dinleyici, Mehmet SalihIn this study two dimensional square photonic crystal with line defect waveguide and embedded in nonlinear Kerr type dielectric rods are examined. Depending on the number and location of Kerr type nonlinear rods, power flux and harmonics are investigated. Optical switching of carrier signal is performed with using the control signal.Conference Object Transmit Beamforming Techniques for Multicast Wireless Communication Systems(Institute of Electrical and Electronics Engineers Inc., 2009) Özbek, Berna; Le Ruyet, DidierIn this paperg transmit beamforming algorithm is designed for multicast wireless communication providing only one beam and multiple beams. The reduced complexity algorithms are imyproved the system performance with multiple transmit beamy forming techniques.Conference Object Alpha-Trimmed Means of Multiple Location Estimates(Institute of Electrical and Electronics Engineers Inc., 2013) Altınkaya, Mustafa AzizLocalization by distance measurements is a common technique for solving this contemporary problem. The methods which achieve the theoretically optimum solutions have generally iterative structures. That is why when limited computational load is required, suboptimum methods described by closed form formulas like the one of Coope which depends on orthogonal decomposition of sensor coordinates, are preferred. In this method, when there are more than necessary distance measurements required for localization, the location will be found as the arithmetic average of the estimates obtained using the all three-combinations of distance measurements. In the averaging, eliminating the outlier estimates will increase the performance. In this case discarding the estimates making the ratio of alpha which are farthest away from the arithmetic average, one attains the socalled alpha-trimmed mean of the estimates. Applying this technique, the disturbing effects of impulsive mixture of Gaussian contamination are eliminated and similar performances as in the case of Gaussian distance measurements are attained in localization.Conference Object The Effect of Convolutional Encoder Memory on the Sphere Decoding Search Radius in Mimo Systems(Institute of Electrical and Electronics Engineers Inc., 2013) Karakuş, Oktay; Altınkaya, Mustafa Aziz; Kılıçaslan, KağanIn the new generation communication systems Multiple-Input-Multiple-Output systems are frequently used. The processing load of the Maximum Likelihood (ML) Detector which is the optimum detector for these systems, increases exponentially as a function of system dimension and memory due to testing all possible points. Sphere Decoding (SD) method which tests only the probable points, decreases the processing load dramatically. System memory changes by system dimensions and length of the convolutional encoder. This, in turn, affects the radius of the hyper sphere centered at the observation in the observation space at which SD attains the performance of the ML detector. This effect is investigated via simulation studies. In these simulations, it is observed that the radius of the SD is relatively smaller than the one in ML, and the ratio between the radius values varies from 6,61 in the case of memoryless 2x2 MIMO system to 1,02 in the case of 8x8 MIMO system with memory K=10 according to increased antenna numbers and system memory. In addition to these, it is observed that the radius of the hyper sphere is directly proportional to the memory of the encoder.