Incident Detection Systems: a Review of the Algorithms

Advanced Traffic Engineering and Management

Title of the Term Project:

Incident Detection Systems: A Review of the Algorithms

Table of Contents

Table of Contents 1

Background of the Incident Detection Systems 2

Significance of the Research in Incident Management Systems 3

Literature Review 4

Desirable Properties of Incident Detection Algorithms 8

The Benchmark Algorithm 9

The Fuzzy Logic Based Algorithm 10

Future Research Area 15

References 15

Background of the Incident Detection Systems

Statistics indicated that the UAE looses about AED 5 billion a year to road congestions [1]. The UAE police reports [2 and 3] reveal that the total number of traffic accidents was 10135 in 2008, compared with 8828 in 2007, and 8843 in 2006. The increase in the number of traffic accidents is approximately 15% between the years 2007 and 2008, and 4% between the years 2006 and 2007. Studies in US and France showed that the probability of death in a car accident increases by a factor of 7 when the time taken for assistance to arrive exceeds 20 minutes [4]. Also, first response has become a common component of Emergency Medical Services [5]. Virtually, all algorithms developed to date to recognize the incidents have two major limitations: high false-alarm rates and threshold calibration requirements. Empirically threshold values once exceeded by the measured traffic quantities, the occurrence of an incident are indicated. The false-alarm rates and detection rates clearly depend on the choice of threshold values.

With the statistics and their implications in terms of the economical, social and psychological losses, the UAE authorities have initiated a nationwide effort to establish a strategic traffic safety plan. Amongst the objectives of this plan is the utilization of the advanced technology in developing the activities and plans for traffic operations, education, engineering, and

References: [1] DPE Abu Dhabi (2008). DPE Weekly Report 8, Department of Planning and Economy, Abu Dhabi. [2] UAE MOI (2007). Annual Statistics of Traffic for the year 2007. Ministry of Interior, United Arab Emirates. [3] UAE MOI (2008). Annual Statistics of Traffic for the year 2008. Ministry of Interior, United Arab Emirates. [5] Lerner, E.B., Billittier, A. J., Moscati, R.M. and Adlof, J.E. (2003) The Journal of Emergency Medicine, Vol. 25, No. 2, pp. 171–174, 2003. [6] Yuan, F. and Cheu, R.L. (2003) Incident detection using support vector machines, Transportation Research Part C: Emerging Technologies 11 (3) (2003) 309– 328. [7] Transportation Engineering and Planning, C.S. Papacostas, P.D. Prevedouros. 3rd Edition (2001), Prentice Hall. ISBN 0-13-081419-9. [8] Persaud, B. N., Hall, F. L. and Hall, L. M. (1990) "Congestion Identification Aspects of the McMaster Incident Detection Algorithm", Transportation Research Record, 1287, pp 67-74. [9] Chassiakos, A. and Stephanedes, Y. (1993) "Smoothing Algorithms for Incident Detection", Transportation Research Record 1394, pp. 8-16. [10] Stephanedes, Y. and Chassiakos, A. (1993) "Application of Filtering Techniques for Incident Detection", ASCE Journal of Transportation Engineering, Vol. 119, No. 1, pp. 13-26. [11] Jin, X, Cheu, R.L. and Srinivassan, D. (2002) Development and Adaptation of Constructive Probabilistic Neural Network In Freeway Incident Detection. Transportation Research. Part C: Emerging Technologies. Vol 10, No. 2, pp 121-147. [12] Corby, M.J. and Saccomanno, F.F. (1997) Analysis of Freeway Accident Detection. Transportation Research Record. Issue 1603, pp 80-89. [13] Shah, S. A.A., Kim, H., Baek, S., Chang, H. and Ahn, B. H. (2008) System architecture of a decision support system for freeway incident management in Republic of Korea. Transportation Research Part A 42 (2008) 799–810 [14] Gursoy, M.B [15] Dia, H. and Thomas, K. (2010) Development and evaluation of arterial incident detection models using fusion of simulated probe vehicle and loop detector data, Informat Fusion (2010), doi:10.1016/j.inffus.2010.01.001. [16] Judicky, D. and Robinson, J. (1992) "Managing Traffic During Nonrecurring Congestion", Institute of Transportation Engineers Journal, Vol. 62, No. 3, pp. 21-26. [17] Kay, J. (1992) "Intelligent Vehicle-Highway Systems and Incident Management", Institute of Transportation Engineers Journal, Vol. 62, No. 3, pp. 55-57. [18] Chen, S. and Wang, W. (2009) Decision tree learning for freeway automatic incident detection, Expert Systems with Applications 36 (2009) 4101–4105. [19] Samant, A., Adeli, H., (2000). Feature extraction for traffic incident detection using wavelet transform and linear discriminant analysis. Computer-Aided Civil Infrastructure Engineering 15 (4), 241–250. [20] Teng, H. and Qi, H. (2003) Application of wavelet technique to freeway incident detection, Transportation Research Part C: Emerging Technologies 11 (3) (2003) 289– 308. [21] Chen, S., Wang, W. and Zuylen, H. V. (2009) Construct support vector machine ensemble to detect traffic incident, Expert Systems with Applications 36 (2009) 10976–10986. [22] Zhang, K. and Taylor, M.A.P. (2006) Effective arterial road incident detection: a Bayesian network based algorithm, Transportation Research Part C 14 (2006) 403–417. [23] Hawas, Y. E. (2007) A fuzzy-based system for incident detection in urban street networks. Transportation Research Part C 15 (2007) 69–95. [24] Srinivasan, D., Cheu, R.L., Poh, Y.P., Chwee Ng, A.K., (2000). Development of an intelligent technique for traffic network incident detection. Engineering Applications of Artificial Intelligence 13 (3), 311–322. [25] Hawas, Y.E. (2004). Development and calibration of route choice utility models: neuro-fuzzy approach. Journal of Transportation Engineering, ASCE 130 (2), 171–182. [26] Chen, S., Wang, W. and Zuylen, H. V. (2010) A comparison of outlier detection algorithms for ITS data. Expert Systems with Applications 37 (2010) 1169–1178. [27] Awadallah, F. (2002) Incident Detection: Selection of Appropriate Technologies and Methodologies. Road and Transport Research, Vol 11, No. 2, pp 50-56. [30] Mussa, R.N. and Upchurch, J.E (2002). Simulator Evaluation of Incident Detection by Transponder-Equipped Vehicles. Transportation. Vol 29, no 3, pp 287-305 [31] Lanser, S.H [32] Niitymaki, J. (2001). “General Fuzzy Rule Base for Isolated Traffic Signal Control: Rule Formulation.” Transp. Planning and Technology, 24(3), 237-247. [33] Solomon, M.A. (1991) “A review of Automatic Incident Detection Techniques, ADVANCE Project, Northwester University, Evanston, IL.