More robust and better: a multiple kernel support vector machine ensemble approach for traffic incident detection

SUMMARY This paper presents a multiple kernel support vector machine (MKL-SVM) ensemble algorithm to detect traffic incidents. It uses resampling technology to generate training set, test set, and training subset firstly; then uses different training subsets to train individual MKL-SVM classifiers; and finally introduces ensemble methods to construct MKL-SVM ensemble to detect traffic incidents. Extensive experiments have been performed to evaluate the performances of the four algorithms: standard SVM, SVM ensemble, MKL-SVM, and the proposed algorithm (MKL-SVM ensemble). The experimental results show that the proposed algorithm has the best comprehensive performances in traffic incidents detection. To achieve better performances, the proposed algorithm needs less individual classifiers to construct the ensemble than SVM ensemble algorithm. Thus, compared with SVM ensemble algorithm, the complexity of the ensemble classifier of the proposed algorithm is reduced greatly. Conveniently, the proposed algorithm also avoids the burden of selecting the appropriate kernel function and parameters. Copyright © 2013 John Wiley & Sons, Ltd.

[1]  Wenfang Lin,et al.  Highway traffic incident detection based on BPNN , 2010 .

[2]  David R. Martinelli,et al.  An application of the CUSUM algorithm to freeway incident detection based on two contiguous detectors , 2010 .

[3]  Fang Yuan,et al.  INCIDENT DETECTION USING SUPPORT VECTOR MACHINES , 2003 .

[4]  Wei Wang,et al.  Construct support vector machine ensemble to detect traffic incident , 2009, Expert Syst. Appl..

[5]  Pravin Varaiya,et al.  The freeway service patrol evaluation project: Database support programs, and accessibility , 1996 .

[6]  Fred L. Hall,et al.  Catastrophe theory and patterns in 30 second freeway traffic data, implications for incident detection , 1989 .

[7]  Yan-Ning Cai,et al.  On Multiple Kernel Learning Methods: On Multiple Kernel Learning Methods , 2010 .

[8]  Hojjat Adeli,et al.  Enhancing Neural Network Traffic Incident‐Detection Algorithms Using Wavelets , 2001 .

[9]  Michael I. Jordan,et al.  Multiple kernel learning, conic duality, and the SMO algorithm , 2004, ICML.

[10]  H. Nickisch,et al.  Multiple Kernel Learning: A Unifying Probabilistic Viewpoint , 2011, 1103.0897.

[11]  Mohan M. Trivedi,et al.  Distributed video networks for incident detection and management , 2000, ITSC2000. 2000 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.00TH8493).

[12]  Hojjat Adeli,et al.  An Adaptive Conjugate Gradient Neural Network–Wavelet Model for Traffic Incident Detection , 2000 .

[13]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[14]  Yuncai Liu,et al.  Traffic Incident Detection Using Multiple-Kernel Support Vector Machine , 2012 .

[15]  Edward Chung,et al.  Characterization of incidents on an urban arterial road , 2001 .

[16]  Samuel C Tignor,et al.  FREEWAY INCIDENT-DETECTION ALGORITHMS BASED ON DECISION TREES WITH STATES , 1978 .

[17]  Ruey Long Cheu,et al.  Automated detection of lane-blocking freeway incidents using artificial neural networks , 1995 .

[18]  Francis R. Bach,et al.  Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning , 2008, NIPS.

[19]  Jun Cai,et al.  Video-Based Automatic Incident Detection for Smart Roads: The Outdoor Environmental Challenges Regarding False Alarms , 2008, IEEE Transactions on Intelligent Transportation Systems.

[20]  Emily Parkany,et al.  A COMPLETE REVIEW OF INCIDENT DETECTION ALGORITHMS & THEIR DEPLOYMENT: WHAT WORKS AND WHAT DOESN'T , 2005 .

[21]  Manik Varma,et al.  More generality in efficient multiple kernel learning , 2009, ICML '09.

[22]  Yuncai Liu,et al.  Traffic incident detection by multiple kernel support vector machine ensemble , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[23]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[24]  Xin Jin,et al.  Adaptive neural network models for automatic incident detection on freeways , 2005, Neurocomputing.

[25]  Wei Wang,et al.  Incident detection algorithm based on partial least squares regression , 2008 .

[26]  Hojjat Adeli,et al.  Feature Extraction for Traffic Incident Detection Using Wavelet Transform and Linear Discriminant Analysis , 2000 .

[27]  Henry S. L. Fan,et al.  Development of Dual-Station Automated Expressway Incident Detection Algorithms , 2007, IEEE Transactions on Intelligent Transportation Systems.