Integrated Incident Decision-Support using Traffic Simulation and Data-Driven Models

Wen, Tao; Mihăiţă, Adriana-Simona; Nguyên, Hoàng; Chen, Fang

doi:10.1177/0361198118782270

Cited by 10 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An innovative real-time incident management platform has been introduced in [5] to detect and then classify incidents into two types, recurrent and non-recurrent, based on their frequency and characteristics. When an accident is detected and confirmed by the system, the platform triggers either a data-driven machine learning module (if the incident is recurrent) or traffic simulation modules (if the incident is non-recurrent).…”

Section: Related Workmentioning

confidence: 99%

Automated Approach for Generating and Evaluating Traffic Incident Response Plans

Almohammad

Georgakis

2023

Itise 2023

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Automated Approach for Generating and Evaluating Traffic Incident Response Plans

Almohammad

Georgakis

2023

Itise 2023

View full text Add to dashboard Cite

show abstract

“…The area geometry features contain the sector ID as defined by TMC, the code of the official area where the accident occurred (as defined by the Bureau of Transport and Statistics), and supplementary information such as section capacity, section speed limit, and the number of lanes. These features are available for all road sections in the Victoria sub-network, and they were extracted from the official traffic simulation model of the Victoria network, developed in Aimsun and previously used by the authors for conducting an incident impact analysis and traffic prediction [48].…”

Section: Victoria Rd -Arterial Network Sydneymentioning

confidence: 99%

Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation

Grigorev¹,

Mihăiţă²,

Lee³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Predicting the duration of traffic incidents is a challenging task due to the stochastic nature of events. The ability to accurately predict how long accidents will last can provide significant benefits to both end-users in their route choice and traffic operation managers in handling of non-recurrent traffic congestion. This paper presents a novel bi-level machine learning framework enhanced with outlier removal and intra-extra joint optimisation for predicting the incident duration on three heterogeneous data sets collected for both arterial roads and motorways from Sydney, Australia and San-Francisco, U.S.A. Firstly, we use incident data logs to develop a binary classification prediction approach, which allows us to classify traffic incidents as short-term or long-term. We find the optimal threshold between short-term versus long-term traffic incident duration, targeting both class balance and prediction performance while also comparing the binary versus multi-class classification approaches using quantiled duration groups and varying threshold split. Secondly, for more granularity of the incident duration prediction to the minute level, we propose a new Intra-Extra Joint Optimisation algorithm (IEO-ML) which extends multiple baseline ML models tested against several regression scenarios across the data sets. Final results indicate that: a) 40-45 min is the best split threshold for identifying short versus longterm incidents and that these incidents should be modelled separately, b) our proposed IEO-ML approach significantly outperforms baseline ML models in 66% of all cases showcasing its great potential for accurate incident duration prediction. Lastly, we evaluate the feature importance and show that time, location, incident type, incident reporting source and weather at among the top 10 critical factors which influence how long incidents will last.

show abstract

“…But feature combination can be observed in some specific research studies related to the traffic incident impact prediction, which rely heavily on the historical traffic flow data with and without consideration of features that are describing the incident [3]; other works have addressed a similar approach [4], [5], [6]. Also, these works don't focus on the incident duration prediction.…”

Section: A Related Workmentioning

confidence: 99%

Traffic incident duration prediction via a deep learning framework for text description encoding

Grigorev¹,

Mihăiţă²,

Saleh³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predicting the traffic incident duration is a hard problem to solve due to the stochastic nature of incident occurrence in space and time, a lack of information at the beginning of a reported traffic disruption, and lack of advanced methods in transport engineering to derive insights from past accidents. This paper proposes a new fusion framework for predicting the incident duration from limited information by using an integration of machine learning with traffic flow/speed and incident description as features, encoded via several Deep Learning methods (ANN autoencoder and character-level LSTM-ANN sentiment classifier). The paper constructs a crossdisciplinary modelling approach in transport and data science. The approach improves the incident duration prediction accuracy over the top-performing ML models applied to baseline incident reports. Results show that our proposed method can improve the accuracy by 60% when compared to standard linear or support vector regression models, and a further 7% improvement with respect to the hybrid deep learning autoencoded GBDT model which seems to outperform all other models. The application area is the city of San Francisco, rich in both traffic incident logs (Countrywide Traffic Accident Data set) and past historical traffic congestion information (5-minute precision measurements from Caltrans Performance Measurement System).

show abstract

Integrated Incident Decision-Support using Traffic Simulation and Data-Driven Models

Cited by 10 publications

References 18 publications

Automated Approach for Generating and Evaluating Traffic Incident Response Plans

Automated Approach for Generating and Evaluating Traffic Incident Response Plans

Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation

Traffic incident duration prediction via a deep learning framework for text description encoding

Contact Info

Product

Resources

About