Customization of Automatic Incident Detection Algorithms for Signalized Urban Arterials

Abstract

Non-recurrent congestion or incidents are detrimental to the operability and efficiency of busy urban transport networks. There exists multiple Automatic Incident Detection Algorithms (AIDA) to remotely detect the occurrence of an incident in highway or freeway scenarios, however very little research has been performed to automatically detect incidents in signalised urban arterials. This limited research attention has mostly been focussed on developing new urban arterial specific algorithms rather than identifying alternative methods to synthesize existing freeway based algorithms to urban conditions. The main hindrance to such synthesis is that the traffic patterns on the signalised urban arterials are significantly different from the same on highways/freeways due to the presence of traffic intersections. This paper introduces a new strategy of customising the existing AIDAs (freeway based or otherwise) to significantly improve their adaptability to signalised urban arterial transport networks. The new strategy focuses on preprocessing the traffic information before being used as input to a freeway/highway based AIDA to lessen the effect of traffic signals and to imitate the input patterns in highway/freeway based incident conditions. The effectiveness of this new strategy has been established with the help of four existing AIDAs. The proposed strategy is a simple solution to implement existing algorithms to signalised urban networks without any further instrumentation or operational cost.

Incident Detection by Spatiotemporal Analysis of GPS Data

“…In [1], [2], [15] and [11], the authors obtain DR = 78.7% and MTD = 2s, DR = 100% and MTD = 70s, and DR = 92% and MTD = 106s, DR = 90%, respectively. The best performing model for the urban scenario in [12] achieves DR = 87.31% and MTD = 98.61s. Regarding the MTD performance we achieved worse results than the above-mentioned approaches.…”

“…In [2], the authors detect freeway incidents, using GPS data collected from ILS in the 5.8 km city-bound area in Singapore. In [12], the authors adapt freeway incident detection algorithms to the urban scenario. They simulate 1800 incidents (lasting for 5 and 10 min.)…”

A nonlinear equation system approach to the dynamic stochastic user equilibrium simultaneous route and departure time choice problem

“…However, once Assumptions 1 and 2 are satisfied by DTA problems with physical queues, the proposed algorithm can be used to obtain their solutions. For future studies, we will develop more efficient solution algorithms, and apply the DTA model to evaluate the effect of various traffic management and transport planning measures such as road pricing (Lo and Szeto 2005), network design (Szeto, Jaber, and O'Mahony 2010;Szeto et al 2014;Miandoabchi, Farahani, and Szeto 2012a;Miandoabchi et al 2012b), staggered work hours (Yushimito, Ban, and Holguín-Veras 2014), incident detection (Ghosh and Smith 2014), and traffic flow/density forecasting (Szeto et al 2009;Ye, Szeto, and Wong 2012;Anand, Ramadurai, and Vanajakshi 2014;Chiou, Lan, and Tseng 2014).…”

An intersection-movement-based stochastic dynamic user optimal route choice model for assessing network performance

“…In future research, we will be interested in extending the proposed approach to develop probit-based or the nested logit SDUO models to overcome the shortcomings. In addition, we also plan to use the proposed models for the offline transport planning and policy evaluation, such as advanced traveler information services, network design (e.g., Szeto et al, 2010Szeto et al, , 2014Miandoabchi et al, 2012a,b), signal control, intersection improvement, staggered work hours (e.g., Yushimito et al, 2014), incident detection (e.g., Ghosh and Smith, 2014), traffic flow/density forecasting (e.g., Szeto et al, 2009;Ye et al, 2012;Anand et al, 2014;Chiou et al, 2014), and so on. Furthermore, our current formulation and analysis is based on a discrete-time setting.…”