Yazar "Sezer E." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    An Approach Based on Feature Selection for Missing Value Imputation
    (Springer Science and Business Media Deutschland GmbH, 2022) Sezer E.; Başeğmez H.
    Today, with the spread of technologies such as the internet of things and data acquisition from sensors, the data obtained has increased. The size of the data produced by other sources, especially digital platforms, is increasing day by day. This increase in data production enables the development of effective artificial intelligence applications and in-depth analysis. However, in many data collection processes, missing values are included in the data set due to operational problems or different reasons. This situation is expressed as a data quality problem in the literature. It is possible that the analysis to be made on this data will be negatively affected by this situation. Various statistical techniques and machine learning-based techniques exist in the literature for filling missing values. In this study, an approach is put forward that suggests missing values imputation based on the consistency of the sample with missing values with other samples in the data set. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • Küçük Resim Yok
    Öğe
    Modeling Urban Traffic by Means of Traffic Density Data: Istanbul Case
    (Springer, 2021) Yaman T.T.; Sezer H.B.; Sezer E.
    The main goal of the proposed research is to perform a predictive modeling study on Istanbul’s traffic congestion estimation by using traffic density data. Istanbul Metropolitan Municipality (IMM) shared the data, which includes traffic density status according to 336 different routes in Istanbul, at the end of January 2020. Previous studies on the traffic problem in Istanbul have been limited due to a lack of data. Therefore, it is aimed to perform an initial study on predictive modeling for Istanbul’s traffic congestion forecast. As a preliminary result of the analysis, it is seen that the traffic density is low at 93% accuracy for all locations between 00:00–07:00 am. When the locations are examined for other hours, it is seen that there was no traffic density at some locations. In the planned study, intelligent modeling techniques will be performed with identifying out-of-routine situations in traffic flow. Advantages and disadvantages of predicted models will be discussed according to performance indicators such as RMSE and MAPE. The superior model will be selected according to these criteria and it is expected that preferred approach would be a starting point on future research for predictive forecast studies of Istanbul’s traffic congestion. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.