Yazar "Alisan, Yigit" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A Computer Assisted Decision Support System for Education Planning
    (World Scientific Publ Co Pte Ltd, 2021) Alisan, Yigit; Serin, Faruk
    The advances in technology are eliminating the demand for certain occupations and creating new opportunities. Thus, the universities, teachers, and students have to collaboratively work together to restructure their departments, course offerings, and course contents. Failure to realize the aforementioned initiatives may lead to a loss of quality and competitiveness. This study proposes a decision support system capable of maintaining the quality and competitiveness of the departments and the course offerings. The proposed system consists of three stages. The first stage is the data collection stage. At this stage, data are collected from the internet using web scraping methods. In the second stage, the collected data are turned into meaningful and processable information by natural language processing methods. In the third stage, the alternatives are ranked using multi-criteria decision-making methods. The proposed decision support system provides useful information to several educational stakeholders. First, universities are informed on which departments to create or close as well as the relevant course offerings. Second, information are provided to the teachers to create new courses or shape the course contents. Finally, students are better informed on how to go about choosing the universities, departments, courses, or career paths to pursue. The applicability and reliability of the proposed decision support system were experimentally proven through the use of computer engineering-related job postings and course contents of the universities in Turkey.
  • [ X ]
    Öğe
    EPIDEMIC SPREAD ANALYSIS IN SOCIAL COMMUNICATION NETWORKS WITH SIR MODEL
    (Bingöl Üniversitesi, 2023) Alisan, Yigit; Ilhan, Nagehan
    Compartmental mathematical models are frequently used in epidemiology. These types of models rely on some assumptions, such as the homogeneity of the society and the equal contact ratio of everyone, to model real-life events mathematically. In real life, due to the heterogeneous nature of the social network that constitutes society, the contact rates and contact times of individuals vary. In sudden and new types of epidemics, solutions such as vaccines to slow down or end epidemics may be limited. In such cases, it becomes more important to use limited resources with maximum efficiency. In this study, the estimation results of disease spread in homogeneous and heterogeneous population structures were compared using the SIR compartment model. The dataset obtained from the science gallery in Dublin in 2009 was used to illustrate the heterogeneous community structure in real life. In the exhibition, the spread of the disease was simulated when individuals with different degrees of centrality in the network formed by the visitors who made face-to-face contacts were immunized. When the results obtained are compared, in the case of vaccination of individuals with high betweenness centrality, the spread of infection occurs 14,39% less than the homogeneous network structure accepted in SIR models.
  • [ X ]
    Öğe
    Hybrid time series forecasting methods for travel time prediction
    (Elsevier, 2021) Serin, Faruk; Alisan, Yigit; Kece, Adnan
    Providing accurate information about travel time to passengers is important in public transportation. In this aspect, the travel time of buses between two consecutive stops can be handled as time series. Then, the future travel time can be predicted using time series forecasting methods. In this study, we propose a novel method with three-layer architecture to predict bus travel time between two stops. In the first layer of the proposed method, initial prediction is made by processing measured data. In the second layer, residuals are predicted in the specified depth. In the third layer, the final prediction is made by integrating the results of two previous layers with three different approach. The experiments were performed on the data, which were obtained from public transportation of Istanbul, using various time series forecasting methods in form of traditional and proposed architecture. The results show that proposed method outperforms traditional approach with approximately MAPE of 6. (C) 2021 Elsevier B.V. All rights reserved.
  • [ X ]
    Öğe
    Predicting bus travel time using machine learning methods with three-layer architecture
    (Elsevier Sci Ltd, 2022) Serin, Faruk; Alisan, Yigit; Erturkler, Metin
    The increase in population and the crowding of cities bring along transportation problems. Thus, people are directed to public transportation to reduce the burden on transportation. Being informed correctly about the arrival time at the stops attracts passengers. In this study, machine learning methods with three-layer architecture were used to predict bus arrival time. The first layer processes the measured data and gives the prediction results of actual data. In the second layer, the residuals are predicted at the specified depth. In the third layer, the results of the previous two layers are integrated with three different approaches to calculate the final prediction. The case study was carried out on the data obtained from Istanbul public transportation and various machine learning methods were applied to the data using the traditional and the three-layer architecture. The experimental results showed that the three-layer architecture provided successful results with approximately 2.552 MAPE.