| DOI | Resolve DOI: https://doi.org/10.1109/BigData.2017.8258334 |
|---|
| Author | Search for: Richard, Rene1; Search for: Ray, Suprio |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 2017 IEEE International Conference on Big Data (Big Data), December 11-14, 2017, Boston, MA |
|---|
| Abstract | With the growing number of Open Data initiatives and the increased volume of related data, new forms of civic engagement are emerging. This engagement leads to novel applications and problem solving approaches. Useful insights derived from exploiting publicly available data and open source tools ultimately result in the enhancement of daily life in our communities. In this paper, we analyze publicly available road accident data for the cities of Fredericton and Laval. A traffic accident data processing and analysis pipeline is built using big data systems and big data spatial frameworks. We present a comparative analysis of traffic accidents in these two cities. Random forest classification models are trained to predict if an accident has casualties. The predictive models are used to provide insights into important factors affecting accidents with fatalities or injuries. Results of the study can be used to establish meaningful safe driving policy suggestions, aid in making emergency dispatch decisions, inform accident management procedures or even assist with urban planning. |
|---|
| Publication date | 2017-12 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 23003522 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 90a6db04-753c-45cd-9d7f-d2e6cd030395 |
|---|
| Record created | 2018-07-16 |
|---|
| Record modified | 2022-02-18 |
|---|
