Mining traffic incidents to forecast impact

Miller, Mahalia; Gupta, Chetan

doi:10.1145/2346496.2346502

Cited by 34 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Compared with data-driven methods like those in [2][3][4], only few historical data and dynamic parameters are required for the model, ensuring that the proposed model could be used in most traffic prediction systems and ITSs. Compared with the approach described in [26], this method describes the influence of traffic incidents not only on freeways, but also on surface streets using dynamic incident data.…”

Section: Discussionmentioning

confidence: 99%

“…The method was developed using a large-scale dataset spanning three years. Miller and Gupta [3] proposed a practical system for predicting the cost and effect of highway incidents using classification models trained with police reports and over 60 million sensor data points. Xu et al [4] proposed a self-adapting framework for online traffic prediction using historical data over five years.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Dynamic Spatiotemporal Analysis Model for Traffic Incident Influence Prediction on Urban Road Networks

Zhang

et al. 2017

IJGI

View full text Add to dashboard Cite

Traffic incidents have a broad negative impact on both traffic systems and the quality of social activities; thus, analyzing and predicting the influence of traffic incidents dynamically is necessary. However, the traditional geographic information system for transportation (GIS-T) mostly presents fundamental data and static analysis, and transportation models focus predominantly on some typical road structures. Therefore, it is important to integrate transportation models with the spatiotemporal analysis techniques of GIS to address the dynamic process of traffic incidents. This paper presents a dynamic spatiotemporal analysis model to predict the influence of traffic incidents with the assistance of a GIS database and road network data. The model leverages a physical traffic shockwave model, and different superposition situations of shockwaves are proposed for both straight roads and road networks. Two typical cases were selected to verify the proposed model and were tested with the car-following model and real-world monitoring data. The results showed that the proposed model could successfully predict traffic effects with over 60% accuracy in both cases, and required less computational resources than the car-following model. Compared to other methods, the proposed model required fewer dynamic parameters and could be implemented on a wider set of road hierarchies.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Dynamic Spatiotemporal Analysis Model for Traffic Incident Influence Prediction on Urban Road Networks

Zhang

et al. 2017

IJGI

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, this problem has not been given sufficient attention. Miller and Chetan [5] have studied the impact of short-term highway traffic incidents. In our framework, we are not restricted to highways and also consider long-term traffic interventions that can last for weeks or months.…”

Section: Related Workmentioning

confidence: 99%

Discovering the Impact of Urban Traffic Interventions Using Contrast Mining on Vehicle Trajectory Data

Wang

Xie

Vaithianathan

2015

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Abstract. There is growing interest in using trajectory data of moving vehicles to analyze urban traffic and improve city planning. This paper presents a framework to assess the impact of traffic intervention measures, such as road closures, on the traffic network. Connected road segments with significantly different traffic levels before and after the intervention are discovered by computing the growth rate. Frequent sub-networks of the overall traffic network are then discovered to reveal the region that is most affected. The effectiveness and robustness of this framework are shown by three experiments using real taxi trajectories and traffic simulations in two different cities.

show abstract

“…The majority of traffic prediction techniques focused on predicting traffic in typical conditions (e.g., morning rush hours) [1], [3]- [5], and more recently in the presence of accidents (e.g., [3], [6]. Existing techniques are only applicable to predict one of the scenarios.…”

Section: Introductionmentioning

confidence: 99%

Context-Aware Online Spatiotemporal Traffic Prediction

Deng

Demiryurek

et al. 2014

2014 IEEE International Conference on Data Mining Workshop

View full text Add to dashboard Cite

Abstract-With the availability of traffic sensors data, various techniques have been proposed to make congestion prediction by utilizing those datasets. One key challenge in predicting traffic congestion is how much to rely on the historical data v.s. the real-time data. To better utilize both the historical and realtime data, in this paper we propose a novel online framework that could learn the current situation from the real-time data and predict the future using the most effective predictor in this situation from a set of predictors that are trained using historical data. In particular, the proposed framework uses a set of base predictors (e.g. a Support Vector Machine or a Bayes classifier) and learns in real-time the most effective one to use in different contexts (e.g. time, location, weather condition). As real-time traffic data arrives, the context space is adaptively partitioned in order to efficiently estimate the effectiveness of each predictor in different contexts. We obtain and prove both short-term and long-term performance guarantees (bounds) for our online algorithm. Our experiments with real-world data in real-life conditions show that the proposed approach significantly outperforms existing solutions.

show abstract

Mining traffic incidents to forecast impact

Cited by 34 publications

References 10 publications

A Dynamic Spatiotemporal Analysis Model for Traffic Incident Influence Prediction on Urban Road Networks

A Dynamic Spatiotemporal Analysis Model for Traffic Incident Influence Prediction on Urban Road Networks

Discovering the Impact of Urban Traffic Interventions Using Contrast Mining on Vehicle Trajectory Data

Context-Aware Online Spatiotemporal Traffic Prediction

Contact Info

Product

Resources

About