Browsing by Author "Çayir, Aykut"

Now showing items 1-3 of 3

  • A location-based movie advisor application for android devices 

    Authors:Arsan, Taner; Çayir, Aykut; Umur, Hande Nur; Güney, Tacettin Dogacan; Panya, Büke
    Publisher and Date:(Springer Verlag, 2015)
    Android is one of the world’s most popular mobile platforms. There are more than 600000 applications available today’s market place. Movie advisor applications are also available in Google Play but there is no location-based movie advisor application for Android devices in Google Play and any other marketplace. A Location-Based Service is a mobile computing application that provides information and functionality to users based on their geographical location. In this study a location-based movie ...

  • Bitcoin Forecasting Using ARIMA and PROPHET 

    Authors:Yenidogan, Isil; Çayir, Aykut; Kozan, Ozan; Dag, Tugce; Arslan, Cigdem
    Publisher and Date:(IEEE, 2018)
    This paper presents all studies methodology and results about Bitcoin forecasting with PROPHET and ARIMA methods using R analytics platform. To find the most accurate forecast model the performance metrics of PROPHET and AMNIA methods are compared on the same dataset. The dataset selected 16r this study starts from May 2016 and ends in March 2018 which is the interval that Bitcoin values changing significantly against the other currencies. Data is prepared for time series analysis by performing ...

  • Feature Extraction Based on Deep Learning for Some Traditional Machine Learning Methods 

    Authors:Çayir, Aykut; Yenidogan, Isil; Daǧ, Hasan
    Publisher and Date:(IEEE, 2018)
    Deep learning is a subfield of machine learning and deep neural architectures can extract high level features automatically without handcraft feature engineering unlike traditional machine learning algorithms. In this paper we propose a method which combines feature extraction layers of a convolutional neural network with traditional machine learning algorithms such as support vector machine gradient boosting machines and random forest. All of the proposed hybrid models and the above mentioned ...