A paper titled “Time series and support vector machines to predict Powered-Two-Wheeler accident involvement and accident type” co-authored by Athanasios Theofilatos, George Yannis, Costas Antoniou, Antonis Chaziris and Dimitris Sermpis, is now published in Journal of Transportation Safety and Security. This study exploited real-time traffic and weather data from two major urban arterials in the city of Athens, Greece. Due to the high number of candidate variables, a random forest model was applied to reveal the most important variables. Then, the potentially significant variables were used as input to a Bayesian logistic regression model in order to reveal the magnitude of their effect on PTW accident involvement. The results of the analysis suggest that PTWs are more likely to be involved in multi-vehicle accidents than in single-vehicle accidents. It was also indicated that increased traffic flow and variations in speed have a significant influence on PTW accident involvement.
Time series and support vector machines to predict Powered-Two-Wheeler accident involvement and accident type, 2017
dpavlou
2017-06-20T09:52:02+00:00
June 19th, 2017|Categories: Knowledge|Tags: accidents, powered-two-wheelers, real-time data, support vector machines, time series|
Related Posts
-
European Commission – Young Novice Drivers Thematic Report, December 2023
May 1st, 2024 | Comments Off on European Commission – Young Novice Drivers Thematic Report, December 2023 -
European Commission – Road Safety Country Profiles, February 2024
May 1st, 2024 | Comments Off on European Commission – Road Safety Country Profiles, February 2024 -
World Bank/GRSF – Improving Road Traffic Injury Statistics in Low- and Middle-Income Countries, 2023
April 14th, 2024 | Comments Off on World Bank/GRSF – Improving Road Traffic Injury Statistics in Low- and Middle-Income Countries, 2023