WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8653
Browse
3 results
Search Results
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 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 Citation - Scopus: 1A New Multi-Agent Decision Making Structure and Application To Model-Based Fault Diagnosis Problem(Institute of Electrical and Electronics Engineers Inc., 2017) Leblebicioglu, M.K.; Zengin, Y.; Schmidt, K.W.A new hierarchical multi-agent decision-making structure has been proposed. There are two phases of the structure. The first phase is the construction phase where the decision making structure consisting of switching and classification agents is built on the training data set generated by the system scenarios. In construction phase, switching and classification agents are trained and made ready for decision-making. In the decision phase, which is the second phase, the class of the new data sample is decided. This process is carried out by the transmission of the data sample to the correct classifier agent by the switching agents and the classification by the classifier agent. The proposed structure is applied to a complex fault identification problem and a successful result is obtained. The structure is also adaptable to other big data decision making problems. © 2017 IEEE.