01020446

Component

https://doi.org/10.3141/1968-09

http://scholar.google.com...+Xie&publication_year=2006

A genetic neural network (GNN) classification method using acoustic signals is proposed for real-time accident detection at intersections. Back propagation neural networks (BPNNs) have been widely used in pattern classification. They have fast computation speeds that are desirable for real-time detection systems. However, they tend to converge to local optimums, which consequently affects classification accuracy. The proposed GNN uses a genetic algorithm to improve the global searching ability of BPNNs. GNN performance (i.e., detection rate, false alarm rate, and detection time) is compared with that of a widely used probabilistic neural network (PNN). Test results indicate that the GNN performs comparably to a PNN but with much less computation time. Results of the GNN transferability analysis indicate that the GNN method also is robust and can be successfully applied to intersection accident detection with training data from different sources. Computationally inexpensive and highly accurate, the new GNN is thus suitable for real-time application.

01037954

English

pp 75-82

2006

Transportation Research Record: Journal of the Transportation Research Board

0309099773

Print

Figures (6) ; References (34) ; Tables (3)

Accuracy; Acoustic signal processing; Automatic crash notification; Backpropagation; Classification; Genetic algorithms; Incident detection; Intersections; Neural networks; Real time information

Computational efficiency

Highways; Operations and Traffic Management; Safety and Human Factors; I73: Traffic Control

TRIS, TRB, ATRI

Mar 3 2006 10:56AM

• Applications of Artificial Intelligence Paradigms to Decision Support in Real-Time Traffic Management
• Forecasting Shared-Use Vehicle Trips with Neural Networks and Support Vector Machines
• Frameworks to Represent Uncertainty When Level of Service Is Determined
• Improving the Prediction of Annual Average Daily Traffic for Nonfreeway Facilities by Applying a Spatial Statistical Method
• Incorporating Wavelet Decomposition Technique to Compress TransGuide Intelligent Transportation System Data
• Kalman Filter-Based Tracking System for Automated Inventory of Roadway Signs
• Moments Analysis for Improving Decision Reliability Based on Travel Time
• Performance Evaluation of Sensor- and Image-Based Technologies for Automated Pavement Condition Surveys
• Predicting Directional Design Hourly Volume from Statutory Holiday Traffic
• Predicting Urban Arterial Travel Time with State-Space Neural Networks and Kalman Filters
• Real-Time Detection of Crash-Prone Conditions at Freeway High-Crash Locations
• Travel Time Estimation with Correlation Analysis of Single-Loop Detector Data
• Unscented Kalman Filter Method for Speed Estimation Using Single Loop Detector Data