Neural Networks, safety, Neural Network Trees, rear end, angle, sideswipe, turn crashes
Intersection related crashes form a significant proportion of the crashes occurring on roadways. Many organizations such as the Federal Highway Administration (FHWA) and American Association of State Highway and Transportation Officials (AASHTO) are considering intersection safety improvement as one of their top priority areas. This study contributes to the area of safety of signalized intersections by identifying the traffic and geometric characteristics that affect the different types of crashes. The first phase of this thesis was to classify the crashes occurring at signalized intersections into rear-end, angle, turn and sideswipe crash types based on the traffic and geometric properties of the intersections and the conditions at the time of the crashes. This was achieved by using an innovative approach developed in this thesis "Neural Network Trees". The first neural network model built in the Neural Network tree classified the crashes either into rear end and sideswipe or into angle and turn crashes. The next models further classified the crashes into their individual types. Two different neural network methods (MLP and PNN) were used in classification, and the neural network with a better performance was selected for each model. For these models, the significant variables were identified using the forward sequential selection method. Then a large simulation database was built that contained all possible combinations of intersections subjected to various crash conditions. The collision type of crashes was predicted for this simulation database and the output obtained was plotted along with the input variables to obtain a relationship between the input and output variables. For example, the analysis showed that the number of rear end and sideswipe crashes increase relative to the angle and turn crashes when there is an increase in the major and minor roadways' AADT and speed limits, surface conditions, total left turning lanes, channelized right turning lanes for the major roadway and the protected left turning lanes for the minor roadway, but decrease when the light conditions are dark. The next phase in this study was to predict the frequency of different types of crashes at signalized intersections by using the geometric and traffic characteristics of the intersections. A high accuracy in predicting the crash frequencies was obtained by using another innovative method where the intersections were first classified into two different types named the "safe" and "unsafe" intersections based on the total number of lanes at the intersections and then the frequency of crashes was predicted for each type of intersections separately. This method consisted of identifying the best neural network for each step of the analysis, selecting significant variables, using a different simulation database that contained all possible combinations of intersections and then plotting each input variable with the average output to obtain the pattern in which the frequency of crashes will vary based on the changes in the geometric and traffic characteristics of the intersections. The patterns indicated that an increase in the number of lanes of the major roadway, lanes of the minor roadway and the AADT on the major roadway leads to an increased crashes of all types, whereas an increase in protected left turning lanes on the major road increases the rear end and sideswipe crashes but decreases the angle, turning and overall crash frequencies. The analyses performed in this thesis were possible due to a diligent data collection effort. Traffic and geometric characteristics were obtained from multiple sources for 1562 signalized intersections in Brevard, Hillsborough, Miami-Dade, Seminole and Orange counties and the city of Orlando in Florida. The crash database for these intersections contained 27,044 crashes. This research sheds a light on the characteristics of different types of crashes. The method used in classifying crashes into their respective collision types provides a deeper insight on the characteristics of each type of crash and can be helpful in mitigating a particular type of crash at an intersection. The second analysis carried out has a three fold advantage. First, it identifies if an intersection can be considered safe for different crash types. Second, it accurately predicts the frequencies of total, rear end, angle, sideswipe and turn crashes. Lastly, it identifies the traffic and geometric characteristics of signalized intersections that affect each of these crash types. Thus the models developed in this thesis can be used to identify the specific problems at an intersection, and identify the factors that should be changed to improve its safety
Master of Science in Civil Engineering (M.S.C.E.)
College of Engineering and Computer Science
Civil and Environmental Engineering
Length of Campus-only Access
Masters Thesis (Open Access)
Nawathe, Piyush, "Neural Network Trees And Simulation Databases: New Approaches For Signalized Intersection Crash Classification And Prediction" (2005). Electronic Theses and Dissertations. 475.