Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
Intelligent Engineering Systems through Artificial Neural Networks, Volume 16Available to Purchase
Editor
Cihan H. Dagli
Cihan H. Dagli
Search for other works by this author on:
Anna L. Buczak
Anna L. Buczak
Search for other works by this author on:
David L. Enke
David L. Enke
Search for other works by this author on:
Mark Embrechts
Mark Embrechts
Search for other works by this author on:
Okan Ersoy
Okan Ersoy
Search for other works by this author on:
ISBN-10:
0791802566
No. of Pages:
1000
Publisher:
ASME Press
Publication date:
2006

According to the Wisconsin Dept of Transportation, many people die in alcohol-related traffic crashes every year. In 2002 alone, 290 people were killed in alcohol-related traffic crashes in Wisconsin. A thorough knowledge of the factors leading to alcohol-related traffic crashes is required in the development of safety improvement plans to minimize the occurrence of these crashes. In addition, knowledge of the timing for any safety improvement requires good assessment of the current and future alcohol-related crashes within a given highway system.

A three-layer neural network model is presented in this paper to predict alcohol-related traffic crash rates based on licensed drivers and registered vehicles for Wisconsin counties. A variety of backpropagation neural network (BPNN) topologies with different numbers of inputs and hidden neurons are investigated and their prediction performances compared. Based on the analysis of the results it is concluded that three factors (population per liquor license density, guilty outcome of adjudicated cases, total had been drinking (HBD) drivers) have the major impact on predicting the crash rate. It is also noticed that the proper choice of training process and neural network (NN) parameters significantly affect the prediction accuracy. In addition, the NN model predicts crash rate based on licensed drivers better than rate based on registered vehicles.

Abstract
1. Introduction
2. Database Description
3. The Neural Network Model
4. Performance Analysis of the NN Model
5. Conclusion
References
This content is only available via PDF.
You do not currently have access to this chapter.

or Create an Account

Close Modal
Close Modal