LSTM Network Analysis of Vehicle-Type Fatalities on Great Britain's Roads

Autor: Oketunji, Abiodun Finbarrs, Hanify, James, Heffron-Smith, Salter
Rok vydání: 2023
Předmět:
Druh dokumentu: Working Paper
DOI: 10.5281/zenodo.10388170
Popis: This study harnesses the predictive capabilities of Long Short-Term Memory (LSTM) networks to analyse and predict road traffic accidents in Great Britain. It addresses the challenge of traffic accident forecasting, which is paramount for devising effective preventive measures. We utilised an extensive dataset encompassing reported collisions, casualties, and vehicles involvements from 1926 to 2022, provided by the Department for Transport (DfT). The data underwent stringent processing to rectify missing values and normalise features, ensuring robust LSTM network input.
Databáze: arXiv