Introducing Prior Knowledge for a Hybrid Accident Prediction Model

다국어 초록 (Multilingual Abstract)

This study aims to address two potential issues regarding accident prediction models. (a) What are the benefits of using the prior information on the accuracy of prediction model, and (b) how to include the available prior knowledge of accident occurrences data in the prediction process? In accident databases, the prior knowledge can be defined as the most probable points in which an accident has happened in the earlier years and is closely correlated to its upcoming years. Large databases such as traffic and accident databases, inevitably contain noisy data. Therefore, to have accurate results, using approaches to alleviate the impact of these anomalies is significant. In this research, a hybrid method based on a module of prediction and a prior knowledge block is proposed.
The module used for prediction is Recursive Least Square filter and Maximum a Posterior (MAP) estimator is used as the prior knowledge block. Results indicate an increase in accuracy of prediction by using the proposed hybrid model.

참고문헌 (Reference)

1 Karim El-Basyouny, "Urban Arterial Accident Prediction Models with Spatial Effects" Transportation Research Board 2102 : 27-33, 2009

2 Ljung, L., "System identification: Theory for the user" Englewood Cliffs 1987

3 Chris Lee, "Real-Time Crash Prediction Model for Application to Crash Prevention in Freeway Traffic" Transportation Research Board 1840 : 67-77, 2003

4 Jianhua Guo, "Real time traffic flow outlier detection using short-term traffic conditional variance prediction" Elsevier BV 50 : 160-172, 2015

5 P. J. Schluter, "Ranking and selecting motor vehicle accident sites by using a hierarchical Bayesian model" Wiley-Blackwell 46 (46): 293-316, 1997

6 Chandore, P., "Outlier detection techniques over streaming data in data mining: A research perspective" 12-16, 2013

7 Lin, F., "Estimating safety benefits of road improvements: Case based approach" 129 (129): 385-391, 2003

8 Yuanchang Xie, "Crash Injury Severity Analysis Using Bayesian Ordered Probit Models" American Society of Civil Engineers (ASCE) 135 (135): 18-25, 2009

9 Bandyopadhyaya, R., "Comparative Analysis of Hotspot Identification Methods in the Pres-ence of Limited Information" 2011

10 Luis F. Miranda-Moreno, "Bayesian road safety analysis: Incorporation of past evidence and effect of hyper-prior choice" Elsevier BV 46 : 31-40, 2013

11 Luis F. Miranda-Moreno, "Bayesian multiple testing procedures for hotspot identification" Elsevier BV 39 (39): 1192-1201, 2007

12 Vaseghi, S. V., "Advanced digital signal processing and noise reduction" John Wiley & Sons 2008

13 O'day, J., "Accident data quality" Transportation Research Board 1993

14 Shuyan Chen, "A comparison of outlier detection algorithms for ITS data" Elsevier BV 37 (37): 1169-1178, 2010

15 Victoria Hodge, "A Survey of Outlier Detection Methodologies" Springer Nature 22 (22): 85-126, 2004

16 "2014 Road Safety - Accidents 2014"