With the high developing speed of Chinese economy, lots of new freeways have been constructed in recent years. Hence incident management becomes an important issue in freeway management system. Incident Detection (ID) that forms the heart of incident management is a kind of pattern recognition problem. In this paper we employed the Multi-layer Perceptron Neural Network (MLPNN) to do incident detection. Applying traffic simulation software FRESIM, a wide range of incidents that include different patterns under a variety of flow conditions and traffic periods were generated to train and evaluate the performance and the transferability of the proposed MLPNN-based algorithm. It was proved that the models of our proposed algorithm built on one segment can be used to other segments, and all the three performance measures indicated the potential of practical use of them.
Automatic Incident Detection on Freeways Using Multi-Layer Perceptron Neural Network
International Conference on Traffic and Transportation Studies (ICTTS) 2002 ; 2002 ; Guilin, China
Traffic and Transportation Studies (2002) ; 1083-1088
2002-07-10
Conference paper
Electronic Resource
English
Automatic Incident Detection on Freeways Using Multi-Layer Perceptron Neural Network
British Library Conference Proceedings | 2002
|Video Image Processing Application: Automatic Incident Detection on Freeways
British Library Conference Proceedings | 1993
|Incident detection on freeways: a Bayesian network approach
British Library Conference Proceedings | 2004
|Performance of Automatic ANN-Based Incident Detection on Freeways
British Library Online Contents | 1999
|