Predicting traffic incident duration using deep learning model with real-time data
Traffic accidents have a negative impact on traffic. The prediction of incident clearance time helps to reduce its impact by diverting traffic flow, assisting traffic management organizations in making decisions about appropriate responses and resource allocation and identifying critical factors tha...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77626 |
| _version_ | 1811683161406439424 |
|---|---|
| author | Zhang, Ruilin |
| author2 | Zhu Feng |
| author_facet | Zhu Feng Zhang, Ruilin |
| author_sort | Zhang, Ruilin |
| collection | NTU |
| description | Traffic accidents have a negative impact on traffic. The prediction of incident clearance time helps to reduce its impact by diverting traffic flow, assisting traffic management organizations in making decisions about appropriate responses and resource allocation and identifying critical factors that influence the length of duration. Previous researches utilized more detailed information that may be confidential to the public. Therefore, this study aimed to predict duration with transparent real-time data from LTA Datamall, MSS and OpenStreetMap. This study used a deep learning model to predict the incident duration. Various tests were carried out to optimize the neural network and to achieve the possible highest accuracy. The result of this research was comparable to previous researches in terms of MAE and MAPE, improvement in accuracy was be observed. This research also pointed out the directions for future research. |
| first_indexed | 2024-10-01T04:08:20Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/77626 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:08:20Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/776262023-03-03T17:11:19Z Predicting traffic incident duration using deep learning model with real-time data Zhang, Ruilin Zhu Feng School of Civil and Environmental Engineering DRNTU::Engineering::Civil engineering Traffic accidents have a negative impact on traffic. The prediction of incident clearance time helps to reduce its impact by diverting traffic flow, assisting traffic management organizations in making decisions about appropriate responses and resource allocation and identifying critical factors that influence the length of duration. Previous researches utilized more detailed information that may be confidential to the public. Therefore, this study aimed to predict duration with transparent real-time data from LTA Datamall, MSS and OpenStreetMap. This study used a deep learning model to predict the incident duration. Various tests were carried out to optimize the neural network and to achieve the possible highest accuracy. The result of this research was comparable to previous researches in terms of MAE and MAPE, improvement in accuracy was be observed. This research also pointed out the directions for future research. Bachelor of Engineering (Civil) 2019-06-03T07:28:37Z 2019-06-03T07:28:37Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77626 en Nanyang Technological University 49 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Civil engineering Zhang, Ruilin Predicting traffic incident duration using deep learning model with real-time data |
| title | Predicting traffic incident duration using deep learning model with real-time data |
| title_full | Predicting traffic incident duration using deep learning model with real-time data |
| title_fullStr | Predicting traffic incident duration using deep learning model with real-time data |
| title_full_unstemmed | Predicting traffic incident duration using deep learning model with real-time data |
| title_short | Predicting traffic incident duration using deep learning model with real-time data |
| title_sort | predicting traffic incident duration using deep learning model with real time data |
| topic | DRNTU::Engineering::Civil engineering |
| url | http://hdl.handle.net/10356/77626 |
| work_keys_str_mv | AT zhangruilin predictingtrafficincidentdurationusingdeeplearningmodelwithrealtimedata |