Sürdürülebilir Kalkınma Amaçları
Yayınlar
- ArticleYalnız künye2018CHARACTERISTICS AND ESTIMATION OF TRAFFIC ACCIDENT COUNTS USING ARTIFICIAL NEURAL NETWORK AND MULTIVARIATE ANALYSIS: A CASE STUDY IN TURKEY NORTH TRANSIT INTERURBAN
Bayata, Halim Ferit; Bayrak, Osman Unsal; Pehlivan, Huseyin
By the World Health Organization, traffic accidents in 2013 have been identified as human-caused natural disaster. Since the parameters which cause traffic accidents are numerous, they have a complex structure and they have continuously been a source of interest for analysis by researchers. In this study, D100 (E80) State highway section (422 km) between Erzincan- Agri (Gurbulak) cities in Turkey was investigated by examining the statistical data obtained from Turkish Statistical Institute and Republic of Turkey General Directorate of Highways 12th Regional Directory. For each kilometer lane, widths, Annual Average Daily Traffic (AADT), the number of accident, injury and death, average velocity, distance (km), the number of links and junctions were determined. The methods of ANN (Artificial Neural Network), Poisson regression and multivariate regression were used to analyze above parameters. The methods used have been evaluated as per R-2, MSE, AIC criteria. It has been found for the ANN method that R-2 (0.93), MSE (0.004), in Poisson regression method R-2 (0.57), MSE (0.33), and in the multivariable regression method R-2 (0.61), MSE (0.26). The results showed that ANN models perform better than the multivariate regression in terms of traffic accidents.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2016Mikrosimülasyon Kullanılarak Bir Kavşağın Trafik Yönetim Ölçümlerinin Değerlendirilmesi
Hattatoğlu, Fatih; Çolak, Muhammet Ali; Bayata, Halim Ferit; Bayrak, Osman Ünsal
Trafik yönetiminde ele alınan iki ana amaç sinyalize olmayan kavşaklardaki trafik güvenliği ve yolculuk verimliliğidir. Mikroskopik simülasyonlar ulaşım projelerinde ve yönetiminde yaygın bir şekilde kullanılmaktadırlar çünkü simülasyon güvenlidir daha ekonomiktir ve arazi uygulama ve denemelerinden daha hızlıdır. Bu çalışmada Atatürk Üniversitesi Kampüsündeki en yoğun trafik hacmine sahip ve yıllık ortalama 15 kazanın olduğu Teknokent Kavşağı incelenmiştir. Araziden elde edilen ölçümler VISSIM programı ile simüle edilmiştir. Farklı sinyal programları ve geometrik düzenlemeler önerilmiş ve uygulanmıştır. Uygulamalardan sonra ilgili kavşakta 1,5 yıldır herhangi bir kaza olmamıştır. Önerilen ve uygulanan sağa dönüş adaları kollardaki gecikmeleri minimize etmiştir
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2016Usability of inclinometers as a complementary measurement tool in structural monitoring
Pehlivan, Hüseyin; Bayata, Halim Ferit
In the last few years, many structural monitoring studies have been performed using different techniques to measure structures of different scales such as buildings, dams or bridges. One of the mostly used tools are GPS instruments, which have been utilized in various combinations with accelerometers and some other conventional sensors. In the current study, observation series were recorded for 8 hours with GPS receivers (NovAtel) and Inclination Measurement Sensors mounted on a television tower in Istanbul, Turkey. Each series of observations collected from two different sensors were transformed into a single coordinate system (Local Topocentric Coordinates System). The positional changes of the tower were calculated from the GPS and the inclination data. These changes were plotted in two dimensions (2D) on the same graphic. Thus, the possibility of comparison and analysis were found using the data from both the GPS and the Inclinometer complement each other, in the real test area. The positional changes of the tower were modeled for further examination. As a result, the movement of the tower within an area of 1×1 cm2 was observed. Based on the results, it can be concluded that inclinometers can be used for monitoring the structural behavior of the tower.
RDL Kalıcı Kaydıİncele - ArticleYalnız künye2011Modeling of monthly traffic accidents with the artificial neural network method
Bayata, Halim Ferit; Hattatoglu, Fatih; Karsli, Neslihan
Averagely, over 1.3 million traffic accidents with deaths, wounds and property losses occur in a year in Turkey. In the last 30 years, 140000 people have died in traffic accidents. The financial losses of the accidents in the last ten years are over 100 billion dollars. In this study, monthly accidents occurring in Turkey were investigated with Artificial Neural Network (ANN) method. With monthly accident data occurring between the years 1994 to 2007, seasonal fluctuations in the months to come and the number of accidents were predicted. Therefore, an attention is attracted to accidents problems, more reliable analyses about the number of traffic accidents are made and it is emphasized that precautions are increased to prevent the accidents. What sort of the accidents trend will follow in the next months was cleared in the ANN model. The best model was chosen according to the Akaike Information Criteria (AIC), Mean Squared Error and the square of correlation of coefficient (R2). The reliability of the model was also tested by statistical analyses on the error terms.
RDL Kalıcı Kaydıİncele