Simon Hu

An assessment of VMS-rerouting and traffic signal planning with emission objectives in an urban network — A case study for the city of Graz

This paper discusses a case study evaluating the potential impact of ITS traffic management on CO2 and Black carbon tailpipe emissions. Results are based on extensive microsimulations performed using a calibrated VISSIM model in combination with the AIRE model for calculating the tailpipe emissions from simulated vehicle trajectories. The ITS traffic management options hereby consist of easily implementable actions such as the usage of a variable message sign (VMS) or the setting of fixed time signal plans. Our simulations show that in the current case shifting 5% of vehicles from one route to another one leads to an improvement in terms of emissions only if the VMS is complemented with an adaptation of the signal programs, while the VMS sign or the change of the signal plans alone do not yield benefits. This shows that it is not sufficient to evaluate single actions in a ceteris paribus analysis, but their joint network effects need to be taken into account.

A comparative study of k-NN and hazard-based models for incident duration prediction

The motivation behind this paper is to enhance the reliability of in-vehicle navigation systems by predicting the duration of incidents that cause congestion. The main objective of this paper is to develop a methodology for predicting incident duration using broadcast incident data and evaluate the performance of k-NN and hazard-based duration models for predicting incident duration; both of the models are presented in this paper. An incident dataset from the BBC for the Greater London area is used to evaluate the accuracy of both models so that the results give a direct comparison between the models. The strengths and weaknesses of the models are discussed in the paper based on this analysis. Results show that both k-NN and hazard based models have the potential to provide accurate incident duration prediction. While k-NN based models provided marginally more accurate prediction than hazard-based models, the hazard-based duration models can provide additional information such as delay probabilities that can be used by advanced routing and navigation algorithms. Results also show that traffic information incident feeds, such as the tpegML feed from the BBC or TMC information, can be used as a potential data source for incident duration prediction in vehicle navigation systems.

IQGA: A route selection method based on quantum genetic algorithm- toward urban traffic management under big data environment

The increasingly serious problem of traffic congestion has become a critical issue that urban managers need to focus on. However, as urban scale and structure have already taken shape, the use of existing road resources to achieve effective route selection for vehicles is the key to solving this traffic congestion problem. Existing research has mainly focused on the following three points: (1) algorithms for controlling traffic signal lamp period at single intersections; (2) route recommendation algorithms for a single vehicle; and (3) route recommendation algorithms based on the traffic history experienced by a vehicle. These studies, however, have the following limitations: (1) the evaluation factor is singular, and therefore, cannot fully express the advantages and disadvantages of the route selection method; (2) real-time route selection is absent; (3) route selection for a single vehicle is ineffective in avoiding local congestion. In view of these problems, this paper proposes an improved quantum genetic algorithm (IQGA) to solve the problem of traffic congestion in route selection. The algorithm includes the following: (1) proposing a quantum chromosome initialization strategy (QCIS) to convert and code real traffic conditions and to construct quantum chromosomes based on the quantum coding for vehicles and roads; (2) proposing a quantum chromosome mapping algorithm (QCMA) to transform the calculation bits of quantum chromosomes into the results of route selection for different vehicles; (3) proposing a contemporary optimal solution decision strategy (COSDS) to judge the current route selection results; (4) proposing a quantum update algorithm (QUA) to update and iterate the quantum coding of the population. Two types of experiments were conducted in this study: (1) Artificial traffic networks with different scales were designed to carry out comparative experiments between IQGA and other algorithms. The experimental results show that IGQA has better robustness and adaptive ability. (2) Comparative experiments on an actual urban traffic network verified the high-performance and real-time performance capabilities of IQGA.

SALA: A Self-Adaptive Learning Algorithm—Towards Efficient Dynamic Route Guidance in Urban Traffic Networks

In order to alleviate traffic congestion for vehicles in urban networks, most of current researches mainly focused on signal optimization models and traffic assignment models, or tried to recognize the interaction between signal control and traffic assignment. However, these methods may not be able to provide fast and accurate route guidance due to the lack of individual traffic demands, real-time traffic data and dynamic cooperation between vehicles. To solve these problems, this paper proposes a dynamic and real-time route selection model in urban traffic networks (DR2SM), which can supply a more accurate and personalized strategy for vehicles in urban traffic networks. Combining the preference for alternative routes with real-time traffic conditions, each vehicle in urban traffic networks updates its route selection before going through each intersection. Based on its historical experiences and estimation about route choices of the other vehicles, each vehicle uses a self-adaptive learning algorithm to play congestion game with each other to reach Nash equilibrium. In the route selection process, each vehicle selects the user-optimal route, which can maximize the utility of each driving vehicle. The results of the experiments on both synthetic and real-world road networks show that compared with non-cooperative route selection algorithms and three state-of-the-art equilibrium algorithms, DR2SM can effectively reduce the average traveling time in the dynamic and uncertain urban traffic networks.

Air quality impact of intelligent transportation system actions used in a decision support system for adaptive traffic management

The presented traffic control system (CARBOTRAF) combines real-time monitoring of traffic and air pollution with simulation models for traffic, emission and local air quality predictions to deliver on-line recommendations for alternative adaptive traffic management. The aim of introducing a CARBOTRAF system is to reduce BC and CO2 emissions and improve air quality by optimising the traffic flows. A chain of models combines microscopic traffic simulations, emission models and air quality simulations for a range of traffic demand levels and intelligent transport system (ITS) actions. These ITS scenarios simulate combinations of traffic signal optimisation plans and variable messaging systems. The real-time decision support system uses these simulations to select the best traffic management in terms of traffic and air quality. In this paper the modelled effects of ITS measures on air quality are analysed with a focus on BC for urban areas in two European cities, Graz and Glasgow.

Field investigation of vehicle acceleration at the stop line with a dynamic vision sensor

This article presents a study of vehicle acceleration measurements at the stop line of a traffic light in an urban environment. Accurate representation of vehicle acceleration behavior is an important parameter to traffic simulation tools especially when the emissions related to the simulated traffic need to be calculated. A smart eye traffic data sensor (TDS) system was used to record the vehicle trajectories. This device is based on dynamic vision sensor technology that features 1 millisecond temporal resolution, wide dynamic range of 120 dB of illumination, zero-redundancy and asynchronous data output. The trajectories of the detected vehicles from the vision sensor temporal contrast event data have been manually annotated in a space-time representation using a graphical tool. From these extracted trajectories the acceleration of the vehicles has been calculated. We present results of acceleration distributions obtained from over 300 passenger-car acceleration cycles observed in the field. The measurements focus on the first phase of acceleration from the stop line up to a maximum speed of 40 km/h. The results are compared to the results from a traffic micro simulation tool obtained for a similar stop line scenario. The results will be used in the traffic micro-simulation that serves as a basis for a decision support tool for adaptive traffic management developed in the CARBOTRAF FP7 EU project.