Motorway incident detection using principal component analysis

Haibo Chen*, Roger Boyle, Frank Montgomery, Howard Kirby, Mark Dougherty

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Traffic incidents on motorways have a significant impact on traffic operations and consequently cause severe traffic congestion, mobility loss, environmental pollution and energy waste. Conventional incident detection algorithms focus on identification and characterisation of a wide range of different incidents from historic data. In this paper, we introduce a new approach which estimates the probability distribution of incident-free data by means of Principal Component Analysis (PCA). A novel input vector is discriminated by measuring its distance to the centroid of normal data. Both simulated and field data were used in the work to evaluate the reliability and transferability of the methodology. The results show that the technique is promising for incident detection in dynamic traffic monitoring systems.

Original languageEnglish
Pages (from-to)1/1-1/4
JournalIEE Colloquium (Digest)
Issue number123
Publication statusPublished - 1997
Externally publishedYes

Fingerprint

Dive into the research topics of 'Motorway incident detection using principal component analysis'. Together they form a unique fingerprint.

Cite this