Wavelet-neural network model for automatic traffic incident detection

DOI10.3390/MCA6020085MaRDI QIDQ701441zbMATH OpenOpenAlexFDO

Authors Mingyang Wu, Hojjat Adeli

Publication date 10 December 2002

Published in Mathematical \& Computational Applications (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.3390/mca6020085

zbMATH Keywords

incident detectionintelligent transportation systemsITSneural networkstraffic engineeringwavelets

Mathematics Subject Classification ID

Transportation, logistics and supply chain management (90B06) Neural networks for/in biological studies, artificial life and related topics (92B20)

Review text

Summary: The problem of traffic incident detection can be viewed as a pattern recognition problem. Neural networks are known to solve pattern recognition problems effectively, especially when there is no mathematical model. The computational complexity of neural network algorithms, however, increases exponentially with an increase in the size of the network. Furthermore, with an increase in the size of the network, the size of the training set has to be increased exponentially in order to achieve the same level of accuracy. To overcome this double exponential complexity a hybrid feature extraction algorithm and neural network architecture is created specifically for automatic detection of traffic incidents. The upstream and downstream traffic data are first filtered by the discrete wavelet transform. Then, a linear discriminant network is used for feature extraction. Finally, the adaptive conjugate gradient learning algorithm of Adeli and Hung is used to train the network.

Recommendations

• Reduced multivariate polynomial-based neural network for automated traffic incident detection
• Wavelets in intelligent transportation systems.
• Advances in Neural Networks – ISNN 2005
• A support vector machine with the tabu search algorithm for freeway incident detection
• The use of simulation in the design of a road transport incident detection algorithm

Cited in

(9)

• An algorithm for the recognition of levels of congestion in road traffic problems
• Reduced multivariate polynomial-based neural network for automated traffic incident detection
• Learning to detect incidents from noisily labeled data
• A support vector machine with the tabu search algorithm for freeway incident detection
• Intrusion detection using wavelet neural networks with genetic and Levenberg-Marquardt algorithms
• Observation strategies for event detection with incidence on runtime verification: theory, algorithms, experimentation
• Wavelets in intelligent transportation systems.
• Advances in Neural Networks – ISNN 2005
• scientific article; zbMATH DE number 2247134 (Why is no real title available?)

This page was built for publication: Wavelet-neural network model for automatic traffic incident detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q701441)