To Topic-Graph

-1 Topic selected

People

PeopleLocationsStatistics

De Luca, Mario

in Cooperation with on an Cooperation-Score of 37%

Places of action

Graph Shared Publication
DELL'ACQUA, Gianluca - 31 publications, 6 shared
Zilioniene, Daiva - 30 publications, 1 shared
CAPALDO, Francesco Saverio - 15 publications, 1 shared
Abbondati, Francesco - 8 publications, 1 shared
Taddei, F. - 1 publications, 1 shared
Guagnano, A. - 1 publications, 1 shared
Riccomagno, E. - 1 publications, 1 shared
Bracco, F. - 1 publications, 1 shared
Paolucci, M. - 9 publications, 1 shared
Perra, F. - 1 publications, 1 shared
Lupi, F. - 2 publications, 1 shared
Gualeni, Paola - 22 publications, 1 shared
Santic, I. - 1 publications, 1 shared
Luca, Mario De - 4 publications, 2 shared
Cokorilo, Olja - 19 publications, 1 shared
Mauro, Raffaele - 16 publications, 2 shared
LAMBERTI, Renato - 15 publications, 1 shared
Lorenzini, E. - 1 publications, 1 shared
Ragazzini, C. - 1 publications, 1 shared
Biserni, Cesare - 1 publications, 1 shared
Vallet, A. - 1 publications, 1 shared
Borghi, R. - 1 publications, 1 shared
Period of publication
2018
2016
2015
2014
2013
2011
2010
2007

article

Using a K-Means Clustering Algorithm to Examine Patterns of Vehicle Crashes in Before-After Analysis

  • De Luca, Mario
  • Mauro, Raffaele
  • Luca, Mario De
  • DELL'ACQUA, Gianluca
Abstract

The study aims to develop a support procedure to estimate the efficacy of infrastructural interventions to improve road safety. The study was carried out on a 110 km stretch of the A3 highway, in southern Italy. Data from a huge sample concerning traffic, geometry and accidents for two periods of the same duration were compared, for which cluster analysis, and in particular, the “hard c means” binary partition algorithm was employed. Using cluster analysis, all the accidents with strong similarities were aggregated. Then for each cluster, the “cluster representative” accident was identified, to find the average among the various characteristics (geometrical, environmental, accident-related). A “hazard index” was also created for each cluster, whereby it was possible to establish the danger level for each “cluster”. Using this information, an accident prediction model using a multi-variate analysis was produced. This model was used as a support for decision-making on infrastructures and to simulate situations to which the Before-After technique could be applied.

Topics
  • crash
  • forecasting model
  • vehicle
  • data
  • infrastructure
  • decision making
  • traffic
  • highway safety
  • highway
  • hazard
  • cluster analysis