Development of a universal freeway incident detection algorithm is a task that remains unfulfilled despite the promising approaches that have been recently explored. Incident detection researchers are realizing that an operationally successful detection framework needs to fulfill a full set of recognized needs. In this paper we attempt to define one possible set of universality requirements. Among the set of requirements, a freeway incident detection algorithm needs to be operationally accurate and transferable. Guided by the envisioned requirements, we introduce a new algorithm with potential for enhanced performance. The algorithm is a modified form of the Bayesian-based Probabilistic Neural Network (PNN) that utilizes the concept of statistical distance. The paper is divided into three main sections. The first section is a detailed definition of the attributes and capabilities that a potentially universal freeway incident detection framework should possess. The second section discusses the training and testing of the PNN. In the third section, we evaluate the PNN relative to the universality template previously defined. In addition to a large set of simulated incidents, we utilize a fairly large real incident databases from the I-880 freeway in California and the I-35W in Minnesota to comparatively evaluate the performance and transferability of different algorithms, including the PNN. Experimental results indicate that the new PNN-based algorithm is competitive with the Multi Layer Feed Forward (MLF) architecture, which was found in previous studies to yield superior incident detection performance, while being significantly faster to train. In addition, results also point to the possibility of utilizing the real-time learning capability of this new architecture to produce a transferable incident detection algorithm without the need for explicit off-line retraining in the new site. In this respect, and unlike existing algorithms, the PNN has been found to markedly improve in performance with time in service as it retrains itself on captured incident data, verified by the Traffic Management Center (TMC) operator. Moreover, the overall PNN-based framework promises potential enhancements towards the envisioned universality requirements.
[1]
G. Giuliano.
INCIDENT CHARACTERISTICS, FREQUENCY, AND DURATION ON A HIGH VOLUME URBAN FREEWAY
,
1989
.
[2]
Stephen G. Ritchie,et al.
CALIBRATION OF INTRAS FOR SIMULATION OF 30-SEC LOOP DETECTOR OUTPUT
,
1994
.
[3]
Hualiang Teng,et al.
A SEQUENTIAL HYPOTHESIS TESTING-BASED DECISION-MAKING SYSTEM FOR FREEWAY INCIDENT RESPONSE
,
1995
.
[4]
Stephen G. Ritchie,et al.
Neural network models for automated detection of lane-blocking incidents on freeways
,
1994
.
[5]
Lisa Aultman-Hall,et al.
A Catastrophe Theory Approach to Freeway Incident Detection
,
1991
.
[6]
Wei-Hua Lin.
INCIDENT DETECTION WITH DATA FROM LOOP SURVEILLANCE SYSTEMS : THE ROLE OF WAVE ANALYSIS
,
1995
.
[7]
Baher Abdulhai,et al.
PERFORMANCE OF ARTIFICIAL NEURAL NETWORKS FOR INCIDENT DETECTION IN ITS
,
1995
.
[8]
Ruey Long Cheu,et al.
Neural Network Models For Automated Detection Of Non-recurring Congestion
,
1993
.
[9]
Yorgos J. Stephanedes,et al.
Application of Filtering Techniques for Incident Detection
,
1993
.
[10]
Richard A. Johnson,et al.
Applied Multivariate Statistical Analysis
,
1983
.
[11]
Baher Abdulhai,et al.
Preprocessor Feature Extractor and Postprocessor Probabilistic Output Interpreter for Improved Freeway Incident Detection
,
1999
.
[12]
Ruey Long Cheu,et al.
Automated detection of lane-blocking freeway incidents using artificial neural networks
,
1995
.
[13]
Fred L. Hall,et al.
DISTINGUISHING BETWEEN INCIDENT CONGESTION AND RECURRENT CONGESTION: A PROPOSED LOGIC
,
1989
.
[14]
Donald F. Specht,et al.
Probabilistic neural networks and general regression neural networks
,
1996
.
[15]
Yorgos J. Stephanedes,et al.
Transferability of Freeway Incident Detection Algorithms
,
1996
.
[16]
H J Payne,et al.
DEVELOPMENT AND TESTING OF INCIDENT DETECTION ALGORITHMS, VOLUME 2: RESEARCH METHODOLOGY AND DETAILED RESULTS
,
1976
.