Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/50773
Title: Hybrid fuzzy logic-genetic algorithm technique for automated detection of traffic incidents on freeways
Authors: Srinivasan, D. 
Cheu, R.L. 
Poh, Y.P.
Keywords: Fuzzy logic
Genetic algorithms
Incident detection
Issue Date: 2001
Source: Srinivasan, D.,Cheu, R.L.,Poh, Y.P. (2001). Hybrid fuzzy logic-genetic algorithm technique for automated detection of traffic incidents on freeways. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC : 352-357. ScholarBank@NUS Repository.
Abstract: Incident detection has become an important and sophisticated task in today's complex engineering environment, and is one of the key functions of modern traffic management systems. The incidents, depending on their severity, affect the traffic pattern on expressways and cause congestion. This paper presents a hybrid AI approach for immediate and automatic detection of traffic incidents on expressways. Specifically, a hybrid combination of fuzzy logic and genetic algorithm (GA) has been applied to automatically detect incidents on a traffic network. The flexible and robust nature of the developed fuzzy controller allows it to model functions of arbitrary complexity while at the same time being inherently highly tolerant of imprecise data. The maximizing capabilities of genetic algorithm, on the other hand, enable the fuzzy design parameters to be optimized to achieve optimal performance. A cascaded framework of 11 fuzzy controllers takes in traffic indices such as occupancy and volume to detect incidents along an expressway in California. The results obtained from this hybrid model demonstrate the superiority of this approach when compared with two commonly used conventional incident detection algorithms.
Source Title: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
URI: http://scholarbank.nus.edu.sg/handle/10635/50773
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

38
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.