| Issue |
ITM Web Conf.
Volume 12, 2017
The 4th Annual International Conference on Information Technology and Applications (ITA 2017)
|
|
|---|---|---|
| Article Number | 04029 | |
| Number of page(s) | 6 | |
| Section | Session 4: Information Theory and Information Systems | |
| DOI | https://doi.org/10.1051/itmconf/20171204029 | |
| Published online | 05 September 2017 | |
Analysis and Forecast of Traffic Accident Big Data
Tunnel Traffic Engineering Design Office, Yunnan Province Transportation Planning and Design Institute, Kunming, China
Nowadays, as traffic accidents keep happening, traffic safety has become a major focus of contemporary social issues. Many factors account for traffic accidents, such as accident location, time period, driver’s feelings, weather and other uncertain complex factors. As a result, the occurrence of traffic accidents is nonlinear, so it is necessary to explore the correlation between the data from many different aspects so as to avoid risks. By analyzing traffic data and graphics, R language shows how the data is related. After data preprocess, data selection by using R language Remap package remapB and remapH function, we get the locations of the accidents and the accident thermal chart, where you can find high- frequency accident locations. Besides, we employ decision tree, linear regression, random forest algorithm to model the data. According to the actual results, we can verify the correctness of the model and get the most accurate model and it can help us to predict this model with similar data in the future. The ultimate goal of data analysis is to choose the most accurate model after validating the model, analyzing the characteristics of the data and the relationship between the model and the data.
© The Authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.