An Overview of Data Based Predictive Modeling Techniques Used in Analysis of Vehicle Crash Severity

Noorsumar, Gulshan; Robbersmyr, Kjell G.; Rogovchenko, Svitlana; Vysochinskiy, Dmitry

doi:10.1007/978-3-031-10525-8_28

Cited by 2 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is currently a vast amount of literature focusing on the analysis of road accidents from several perspectives: location [4][5][6][7][8][9], weather conditions of occurrence [10], severity [11][12][13][14][15][16], traffic problem areas in terms of infrastructure [17][18][19][20], real time monitoring of incidents [21][22][23][24], and also on data analysis methods used in the study and prediction of road accidents [17,[25][26][27]. Thus, the majority of research relies on statistics that are produced, gathered, kept, and publicly released by government bodies or their authorized representatives responsible for managing, enforcing, or reporting road accident data [15,17,20,25,[28][29][30].…”

Section: Introductionmentioning

confidence: 99%

GIS-Based Spatial Analysis Model for Assessing Impact and Cumulative Risk in Road Traffic Accidents via Analytic Hierarchy Process (AHP)—Case Study: Romania

Bilașco,

Man

2024

Applied Sciences

View full text Add to dashboard Cite

On a global scale, traffic incidents are a leading cause of mortality and material damage. Romania exhibits the highest rate of road traffic fatalities both in the European Union and worldwide, requiring a comprehensive examination of its overall influence on a national level. The current study uses an extensive approach centering on a spatial analysis model based on the Analytic Hierarchy Process (AHP). Employing a series of spatial databases, this model delineates the geographical distribution and characteristics of road accidents to establish both their cumulative national impact and the identification of high-risk areas. The spatial database, containing traffic incident data, is constructed using geolocation techniques and integrated through network analysis to evaluate the impact in relation to distance. The AHP framework is applied in analyzing the impact across five key dimensions: accident severity, occurrence mode, prevailing weather conditions, traffic restrictions, and road markings. This multi-level AHP analysis not only identifies high-risk hotspots but also confirms the effectiveness of the proposed spatial model.

show abstract