Browse > Article
http://dx.doi.org/10.12815/kits.2018.17.6.25

Development of Incident Detection Algorithm Using Naive Bayes Classification  

Kang, Sunggwan (Construction Division, Korea Expressway Corporation)
Kwon, Bongkyung (Overseas Project Div. Korea Expressway Corporation)
Kwon, Cheolwoo (Dept. of Transportation Eng., Ajou University)
Park, Sangmin (Dept. of Transportation Eng., Ajou University)
Yun, Ilsoo (Dept. of Transportation Eng., Ajou University)
Publication Information
The Journal of The Korea Institute of Intelligent Transport Systems / v.17, no.6, 2018 , pp. 25-39 More about this Journal
Abstract
The purpose of this study is to develop an efficient incident detection algorithm by applying machine learning, which is being widely used in the transport sector. As a first step, network of the target site was constructed with micro-simulation model. Secondly, data has been collected under various incident scenarios produced with combination of variables that are expected to affect the incident situation. And, detection results from both McMaster algorithm, a well known incident detection algorithm, and the Naive Bayes algorithm, developed in this study, were compared. As a result of comparison, Naive Bayes algorithm showed less negative effect and better detect rate (DR) than the McMaster algorithm. However, as DR increases, so did false alarm rate (FAR). Also, while McMaster algorithm detected in four cycles, Naive Bayes algorithm determine the situation with just one cycle, which increases DR but also seems to have increased FAR. Consequently it has been identified that the Naive Bayes algorithm has a great potential in traffic incident detection.
Keywords
Incident detection algorithm; Machine learning; McMaster algorithm; Naive Bayes classification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Gailbo, http://www.gailbo.com, 2018.07.21.
2 Cho S. J. and Kang S. H.(2016), "Industrial Applications of Machine Learning," Industrial Engineering Magazine, vol. 23, no. 2, pp.34-38.
3 Cho Y. T.(2016), Development of an Estimating Method for the Parameters of Volume Delay Functions Using a Genetic Algorithm, Doctoral thesis, Ajou University.
4 Deniz O. and Celikoglu H. B.(2011), "Overview to some existing incident detection algorithms: a comparative evaluation," Procedia-Social and Behavioral Sciences, vol. 2, pp.153-168.
5 Hall F. L., Shi Y. and Atala G.(1991), "On-Line Testing of the McMaster Incident Detection Algorithm Under Recurrent Congestion," Transportation Research Record, no. 1394, pp.1-7.
6 Jang M. S.(2018), Classifier Integration Model with Naive Bayes Classifier, Master thesis, Myongji University.
7 Jeong H. R.(2018), Study on Prediction of Severities of Rental Car Traffic Accidents Using Ordinal Logit Model and Naive Bayes Classifier, Master thesis, Ajou University.
8 Kim S. G. and Kim Y. C.(2006), "Development of Incident Detection Algorithm Using Speed-Occupancy Relationship," Seoul City Studies, vol. 7 no. 3, pp.235-249.
9 Kim S. G., Kim C. H. and Kim Y. C.(2008), "A Sensitivity Test of McMaster Algorithm Depending on the Changes in Parameter Values," Seoul City Studies, vol. 9, no. 2, pp.121-131.
10 Kim S. H.(1999), "A Development of Neural Networks-based Incident Detection Model," Journal of Engineering & Technology, Hanyang University, vol. 8, no. 1, pp.187-196.
11 Kim S. H., Kim J. H., Doo M. S., Byun W. H., Sin A. G., Yun Y. H., Lee Y. T., Lee J. B. and Chun S. H.(2016), Road Traffic ITS Theory and Design, Cheongmoongak, pp.108-109.
12 Ko S. G., Kwon C. W., Kim T. S., Cho W. S. and Yun I. S.(2017), "Study on Performance Evaluation of Magnetometer Detectors," Journal of The Korea Institute of Intelligent Transport Systems, vol. 2017, no. 10, pp.63-67.
13 Korea Road Traffic Authority(2018), Traffic accident statistics.
14 Korea Transport Institute(2010), Study on the Collection and Provision of Traffic Information on Highway.
15 KOROAD(2014), "Central Traffic Information Center Traffic Information," KOROAD Traffic Science Institute, pp.8-17.
16 Lee D. H.(2017), A study on Hotspot Identification using Machine Learning, Master thesis, University of Seoul.
17 Lee J., Kim B. K. and Kim S. H.(2000), "A Study on the Application of the Interrupted Traffic Flow Incident Detection Algorithm using Fixed Detector," Journal of Korean society of Transportation, vol. 4, pp.33-36.
18 Lee S. H. and Kang H. C.(2003), "Development and Evaluation of New Incident Detection Algorithm," Journal of Korean society of Transportation, vol. 44, pp.1-6.
19 Mak C. L. and Fan H. S.(2005), "Transferability of expressway incident detection algorithms to Singapore and Melbourne," Journal of transportation engineering, vol. 131, no. 2, pp.101-111.   DOI
20 Philip H. M., Joseph K. L. and Kam W.(1991), "Incident Detection Algorithms for COMPASS An Advanced Traffic Management System," Vehicle Navigation and Information Systems Conference, vol. 2, pp.295-310.
21 Rakha H., Hellinga B. and Van Aerde M.(1999), "Testbed for Evaluating Automatic Incident Detection Algorithms," In Intelligent Transportation System Safety and Security Conference.
22 Sun D., Zhang C., Zhao M., Zheng L., Liu W.(2017), "Traffic Congestion Pattern Detection Using an Improved McMaster Algorithm," 2017 29th Chinese Control And Decision Conference, pp.2814-2819.
23 Yang C., Miao Z. and Dongyuan Y.(2015), "Automatic Incident Detection for Urban Expressways Based on Segment Traffic Flow Density," Journal of Intelligent Transportation Systems, vol. 19, pp.205-213.   DOI
24 Yun I. S., Han E., Lee C. K., Rho J. H., Lee S. J. and Kim S. B.(2013), "Mobility and Safety Evaluation Methodology for the Locations of Hi-PASS Lanes Using a Microscopic Traffic Simulation Tool," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 12, no. 1, pp.98-108.   DOI