Traffic crash prediction based on incremental learning algorithm

Ping Sun; Guimu Guo; Rongjie Yu

doi:10.1109/ICBDA.2017.8078803

Traffic crash prediction based on incremental learning algorithm

Ping Sun, Guimu Guo, Rongjie Yu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Real-time crash prediction models are playing a key role in transportation information system. Support vector machine (SVM), a classification learning algorithm, was introduced to evaluate real-time crash risk. The size of traffic dataset is always large with a high accumulating speed. By applying a warm start strategy, an incremental learning algorithm is introduced to update the original model. In this way, incremental dataset will improve the original model with a little time consumption. This study developed crash risk prediction model utilizing loop detector traffic data and historical crash data. With three comparison experiments, the improvement of accuracy and efficiency of this incremental learning algorithm was proved.

Original language	English (US)
Title of host publication	2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	182-185
Number of pages	4
ISBN (Electronic)	9781509036189
DOIs	https://doi.org/10.1109/ICBDA.2017.8078803
State	Published - Oct 20 2017
Externally published	Yes
Event	2nd IEEE International Conference on Big Data Analysis, ICBDA 2017 - Beijing, China Duration: Mar 10 2017 → Mar 12 2017

Publication series

Name	2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017

Conference

Conference	2nd IEEE International Conference on Big Data Analysis, ICBDA 2017
Country/Territory	China
City	Beijing
Period	3/10/17 → 3/12/17

All Science Journal Classification (ASJC) codes

Signal Processing
Computer Networks and Communications
Information Systems
Information Systems and Management

Access to Document

10.1109/ICBDA.2017.8078803

Cite this

Sun, P., Guo, G., & Yu, R. (2017). Traffic crash prediction based on incremental learning algorithm. In 2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017 (pp. 182-185). Article 8078803 (2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICBDA.2017.8078803

@inproceedings{8352af09054f4faab77cdee046a745b1,

title = "Traffic crash prediction based on incremental learning algorithm",

abstract = "Real-time crash prediction models are playing a key role in transportation information system. Support vector machine (SVM), a classification learning algorithm, was introduced to evaluate real-time crash risk. The size of traffic dataset is always large with a high accumulating speed. By applying a warm start strategy, an incremental learning algorithm is introduced to update the original model. In this way, incremental dataset will improve the original model with a little time consumption. This study developed crash risk prediction model utilizing loop detector traffic data and historical crash data. With three comparison experiments, the improvement of accuracy and efficiency of this incremental learning algorithm was proved.",

author = "Ping Sun and Guimu Guo and Rongjie Yu",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2nd IEEE International Conference on Big Data Analysis, ICBDA 2017 ; Conference date: 10-03-2017 Through 12-03-2017",

year = "2017",

month = oct,

day = "20",

doi = "10.1109/ICBDA.2017.8078803",

language = "English (US)",

series = "2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "182--185",

booktitle = "2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017",

address = "United States",

}

Sun, P, Guo, G & Yu, R 2017, Traffic crash prediction based on incremental learning algorithm. in 2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017., 8078803, 2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017, Institute of Electrical and Electronics Engineers Inc., pp. 182-185, 2nd IEEE International Conference on Big Data Analysis, ICBDA 2017, Beijing, China, 3/10/17. https://doi.org/10.1109/ICBDA.2017.8078803

Traffic crash prediction based on incremental learning algorithm. / Sun, Ping; Guo, Guimu; Yu, Rongjie.
2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 182-185 8078803 (2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Traffic crash prediction based on incremental learning algorithm

AU - Sun, Ping

AU - Guo, Guimu

AU - Yu, Rongjie

PY - 2017/10/20

Y1 - 2017/10/20

N2 - Real-time crash prediction models are playing a key role in transportation information system. Support vector machine (SVM), a classification learning algorithm, was introduced to evaluate real-time crash risk. The size of traffic dataset is always large with a high accumulating speed. By applying a warm start strategy, an incremental learning algorithm is introduced to update the original model. In this way, incremental dataset will improve the original model with a little time consumption. This study developed crash risk prediction model utilizing loop detector traffic data and historical crash data. With three comparison experiments, the improvement of accuracy and efficiency of this incremental learning algorithm was proved.

AB - Real-time crash prediction models are playing a key role in transportation information system. Support vector machine (SVM), a classification learning algorithm, was introduced to evaluate real-time crash risk. The size of traffic dataset is always large with a high accumulating speed. By applying a warm start strategy, an incremental learning algorithm is introduced to update the original model. In this way, incremental dataset will improve the original model with a little time consumption. This study developed crash risk prediction model utilizing loop detector traffic data and historical crash data. With three comparison experiments, the improvement of accuracy and efficiency of this incremental learning algorithm was proved.

UR - http://www.scopus.com/inward/record.url?scp=85040007180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040007180&partnerID=8YFLogxK

U2 - 10.1109/ICBDA.2017.8078803

DO - 10.1109/ICBDA.2017.8078803

M3 - Conference contribution

AN - SCOPUS:85040007180

T3 - 2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017

SP - 182

EP - 185

BT - 2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Conference on Big Data Analysis, ICBDA 2017

Y2 - 10 March 2017 through 12 March 2017

ER -

Traffic crash prediction based on incremental learning algorithm

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this