Yazar "Türker, I." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Cardiac arrhythmia detection with deep learning architectures
    (American Institute of Physics Inc., 2023) Ali, S.S.M.; Türker, I.
    Time series classification (TSC) has an important role in medical diagnostics, providing decision support for vector-shaped data received from biomedical sensors. Traditional machine learning methods provide a sufficient baseline, while they need additional feature extraction procedures and result in lower accuracy compared to recent deep learning approaches. Providing more reliable results, deep learning architectures have become the golden standard for TSC tasks, evoking studies about which architecture provides better results with faster implementation. This study aims to provide a comparison between well-known deep learning architectures CNN and LSTM in comparison with traditional ANN, applying these classifiers for the MIT/BIH Arrhythmia Database, an Electrocardiogram (ECG) dataset that is publicly available. Results show that the best accuracy is achieved for CNN architecture used (96.17%), while LSTM resulted in comparable accuracy (94.42%) and traditional ANN (88.98%) could not compete with the more recent and complicated architectures. These outcomes indicate that although vector-shaped signals have relatively lower complexity compared to two or more-dimensional data like images, more complicated deep learning architectures outperform the traditional neural networks indicating exploration of high order patterns in one dimensional data improves classification accuracy. © 2023 AIP Publishing LLC.
  • Küçük Resim Yok
    Öğe
    Evaluation of the turkish highway network analysis with traffic data
    (2018) Türker, I.
    As a complex geospatial structure, Turkish nationalhighway transportation network is studied by the means ofnetwork science. We used the dataset retrieved from the KGM(Karayolları Genel Müdürlüğü) maps with a hand-driven process.The dataset labels the junctions in the map as nodes, and the roadsbetween these junctions as edges. We outlined the statisticalproperties of the Turkish highway transportation network by themeans of eigenvector, betweenness, closeness centrality,modularity and eccentricity measures, while comparativepercentile plots between these measures are also performed. Weinvestigated the correlation of these parameters with the trafficvolume, and outlined that only eccentricity measure is correlatedwith the traffic volume. We also investigated the degreecorrelations of the network and found that the network displaysdisassortative mixing behavior, meaning that nodes with highdegrees tend to connect with lower degree nodes, and vice versa.This property is consistent with the recent studies oftransportation networks, as well as various types of real networkslike Internet, World-Wide Web, protein interactions, neuralnetwork etc.
  • Küçük Resim Yok
    Öğe
    A hierarchical view of a national stock market as a complex network
    (Bucharest University of Economic Studies, 2017) Baydilli, Y.Y.; Bayir, S.; Türker, I.
    We created a financial network for Borsa Istanbul 100 Index (BIST–100) which forms of N=100 stocks that bargained during T=2 years (2011– 2013). We analyzed the market via minimum spanning tree (MST) and hierarchical tree (HT) by using filtered correlation matrix. While using hierarchical methods in order to investigate factors that affecting grouping of stocks, we have taken account the other statistical and data mining methods to examine success of stock correlation network concept for portfolio optimization, risk management and crisis analysis. We observed that financial stocks, especially Banks, are central position of the network and control information flow. Besides the sectoral and sub-sectoral behavior, corporations play role at grouping of stocks. Finally, this technique provided important tips for determining risky stocks in market. © 2017, Bucharest University of Economic Studies. All rights reserved.