Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
13 results
Search Results
Conference Object Citation - WoS: 1Citation - Scopus: 1Dengesiz Epilepsi Veri Seti İçin Sınıflandırmada Farklı SMOTE Yöntemlerinin Etkileri(Institute of Electrical and Electronics Engineers Inc., 2025) Calis, Ahmet Gokay; Ergezer, HalitIn this study, the effects of different SMOTE methods on machine learning algorithms for the imbalanced epilepsy dataset were investigated. After filtering, the imbalanced dataset was balanced with 5 different SMOTE methods and classified with various machine learning algorithms. Coarse-K-Nearest Neighbor, Bagged Trees, and Artificial Neural Networks models were evaluated in epilepsy detection. The performance of these different models was compared with Matthews Correlation Coefficient (MCC) and F1 Score metrics. The results showed that the Borderline-SMOTE algorithm had the highest F1 Score and MCC values among all machine learning algorithms. © 2025 Elsevier B.V., All rights reserved.Conference Object AviBERT: Transformer Tabanlı Hava Aracı Metni Sınıflandırma(Institute of Electrical and Electronics Engineers Inc., 2025) Unal, Muhammed Cihat; Yurtalan, Gokhan; Karatas, Yahya Bahadir; Karamanlioglu, Alper; Demirel, BerkanIn recent years, transformer-based models pre-trained on extensive corpora have played a critical role in the advancement of Natural Language Processing methodologies. Particularly, methods based on BERT have demonstrated remarkable performance across various tasks by offering robust capabilities in deeply understanding texts semantically. However, despite these advancements, there is a notable scarcity of studies applying these technologies in the aviation sector. This paper develops a multi-class classification model for aviation-specific texts using variants of BERT. The study encompasses the processes of collecting web content related to aircraft, labeling and model training. The details of the dataset are explained and the outcomes of the study are assessed based on the macro F1-score and accuracy of different models. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 13Predicting Flight Delays With Artificial Neural Networks: Case Study of an Airport(Ieee, 2017) Demir, Engin; Demir, Vahap BurhanAir transportation has an important place among transportation systems and it is indispensable for the flights to perform their voyages in scheduled time in order to ensure the comfort of passengers and controllability of operational costs. There are several reasons for flight delays like weather conditions, excessive intensity in air traffic, accidents or closed airfields, conditions that will lead to an increase in distances between planes and operational delays in ground services. In this study, using the data collected from the sensors located in the airport and the information about the flight, the goal is develop a machine learning model to estimate departure delays of flights using artificial neural networks.Conference Object Parallelization of Sparsity-Driven Change Detection Method(Ieee, 2017) Ozgur, Atilla; Saran, Ayse Nurdan; Nar, FatihIn this study, Sparsity-driven Change Detection (SDCD) method, which has been proposed for detecting changes in multitemporal synthetic aperture radar (SAR) images, is parallelized to reduce the execution time. Parallelization of the SDCD is realized using OpenMP on CPU and CUDA on GPU. Execution speed of the parallelized SDCD is shown on real-world SAR images. Our experimental results show that the computation time of the parallel implementation brings significant speed-ups.Conference Object Citation - Scopus: 1Localization of Semantic Category Classification in Fmri Images(Ieee, 2014) Alkan, Sarper; Yarman-Vural, Fatos T.In this study, we provide a methodology to localize the brain regions that contribute to semantic category classification. For this purpose we first cluster the data using spectral clustering. Then we extract local features within each cluster by using mesh-arc descriptors. Finally, we test the classification accuracy of each cluster against a hypothesis testing measure we provide here. We have found that, for the experimental task at hand, calcerine fissure and angular gyrus were most effective in classification. These results are shown to be match well with the nature of the experiment. Thus the validity of our approach is confirmed.Conference Object Evaluation of 3d High Resolution Images Using Inexpensive Distributed Parallel System: Application Fields on Medical Images(Ieee, 2007) Eren, H.; Çelik, Ü.; Poyraz, M.In the telesurgery operations, images should be high resolution and processed in real time. It seems difficult to accomplish this process in real time using only one computer. In our study, we propose to get 3d scene images inside and outside of surgery environment in real time and transfer them into different places. As known, 3d reconstruction needs intensive calculations. Nowadays, using distributed parallel systems are getting increase. Therefore, we investigate the performance rates using a group of inexpensive inert computers which work as a distributed parallel system supposed to be established in a medical environment.Conference Object Hierarchical Decision Making and Decision Fusion(Ieee, 2007) Beldek, Ulas; Leblebicioglu, KemalIn this study, a hierarchical decision making structure possessing a decision fusion technique is proposed in order to solve decision making problems efficiently. The proposed structure mainly depends on effects of the decisions made in the lower levels to decisions in the upper levels up to an activation degree. The proposed hierarchical structure is used for detecting the fault degrees for single and multiple fault scenarios artifically generated in a four tank system. The results obtained demonstrate the effectiveness of the proposed hierarchical decision making structure.Conference Object Citation - Scopus: 2Approaches on the Selection of Web Cameras and Calibration Targets for Stereo Vision(Ieee, 2006) Eren, Haluk; Celik, Umit; Poyraz, MustafaIn this paper, it is studied on the calibration by using specified web cameras. The performance of 3D computer vision depends on the accuracy of camera parameters. Therefore, camera calibration is very crucial in stereo vision. In this study, the options and selection of the target object that is used by the process of camera calibration are reviewed and evaluated some results obtained by web cameras. Webcams' costs are low relatively to the other digital consumer cameras but cannot be acquired a high resolution image.Conference Object Citation - WoS: 1Citation - Scopus: 1A Fast and Optimal Static Segment Scheduling Method for Flexray V3.0(Institute of Electrical and Electronics Engineers Inc., 2017) Cakmak, C.; Schmidt, E.G.; Schmidt, K.W.We propose a novel and fast frame scheduling method for the Static Segment (SS) of the new in-vehicle network standard FlexRay v3.0 in this paper. The proposed methods assigns frames to the SS using the minimum number of time slots based on an Integer Linear Programming formulation. Different from the existing method in the literature, the proposed method computes optimal frame schedules within miliseconds. © 2017 IEEE.Conference Object A Configurable Can Fd Controller: Architecture and Implementation(Institute of Electrical and Electronics Engineers Inc., 2017) Afsin, M.E.; Schmidt, K.W.; Schmidt, E.G.CAN FD is a new standard which provides fast data rate while preserving the compatibility with CAN (controller area network). In this paper, a Configurable IP core architecture (A-CAN) which is compatible with the CAN FD standard, is proposed. Different than existing CAN/CAN FD controllers, the numbers and sizes of transmit and receive buffers of A-CAN can be configured in run time. To this end, A-CAN enables the best use of single controller hardware for different applications and enables improving the real time communication performance. A-CAN communicates with the host device over SPI without any specific interface requirements. A-CAN is implemented on an FPGA Evaluation Board and its functionally is verified at a rate of 2 Mbps. © 2017 IEEE.