Integration of Probability and Clustering Based Approaches in the Field of Black Spot Identification

Abstract

The objective of the paper is to define a complex methodology to analyze black spot locations of road infrastructure network combining the benefit of both; Empirical Bayes method and K-mean clustering approach. In the first step, K-mean algorithm is used to define homogeneous accident clusters. The homogeneity is described in three terms: traffic conditions, geometric design of the road and accident characteristics. Then, Empirical Bayes method is applied to define black spots based on the determined clusters. Due to the combination of the introduced methods, a powerful technique is provided that is able to identify high-risk locations and cluster dependent segment length as the output of the model.

Evaluation of the Impact of Spatial and Environmental Accident Factors on Severity Patterns of Road Segments

“…However, the proposed spatial clustering method has proved its effectiveness compared to other commonly used segmentation methods, according to Ghadi and Török (Ghadi and Török, 2019a;Ghadi et al, 2018a)…”

“…This is rational since most of the well-known BS identification methods use these environmental factors to identify BS sites. For instance, the EB method relies mainly on the AADT to predict future changes in accident frequency (Elvik, 2008;Ghadi et al, 2018a). Similarly, the accident ratio method identifies BS segments based on the value of accidents per segment length or accidents per AADT (Borsos et al, 2016).…”

“…These methods are limited to detecting only accidents within hazardous areas. On the other hand, Ghadi et al (2018a) andDe Luca et al (2012) applied both the K-means clustering and the EB methods in order to divide accidents into specific road segments, depending on their spatial dependence, and finally identify the most hazardous segments. Although some of these methods are able to identify spatially-dependent accident groups, usually they do not consider any other characteristics of an accident itself (i.e.…”

A Novel Model Representation Framework for Cooperative Intelligent Transport Systems

“…Cooperative intelligent transportation system (C-ITS) consists of several components that work together to enhance safety (Ghadi et al, 2017) and operation efficiency. In general, three main C-ITS components are differentiated: On-Board Unit OBU (in-Vehicle) uses WAVE communication method to send and receive vehicle information (e.g.…”

Novel Approaches to Evaluate the Ability of Vehicles for Secured Transportation

“…The outcome of the attack trees serves as a starting point for the next step, the penetration testing. However, this outcome could be used also as a starting point of other safety methods (Ghadi et al, 2019;Gopalakrishnan et al, 2018), like FMEA (Failure Mode and Effect Analysis) (Hajiagha et al, 2016). In order to achieve this, the attack potential number has to be introduced to every step in the attack tree, which can be important from security point of view.…”