Freeway incident detection using Fuzzy ART

Pattern recognition techniques such as artificial neural networks continue to offer potential solutions to many of the existing problems associated with freeway incident detection algorithms. This study focuses on the application of Fuzzy ART neural networks to incident detection on freeways. Unlike backpropagation models, Fuzzy ART is capable of fast stable learning of recognition categories. It is an incremental approach that has the potential for online implementation. Fuzzy ART is trained with traffic patterns that are represented by 30-second loop detector data of occupancy, speed, or a combination of both. To reduce the false alarm rate that results from occasional misclassification of traffic patterns, a persistence time period of 3 minutes was arbitrarily selected. The algorithm performance improves when the temporal size of traffic patterns increases from one to two 30-second periods for all traffic parameters. An interesting finding is that the speed patterns produced better results than occupancy patterns. However, when combined in one pattern, occupancy and speed patterns yield the best results with 100% detection rate and 0.07% false alarm rate