TY - JOUR
T1 - Incident duration prediction using a bi-level machine learning framework with outlier removal and intra–extra joint optimisation
AU - Grigorev, Artur
AU - Mihaita, Adriana Simona
AU - Lee, Seunghyeon
AU - Chen, Fang
N1 - Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2022/8
Y1 - 2022/8
N2 - 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 long-term 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.
AB - 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 long-term 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.
KW - Arterial road versus motorways incident management
KW - Classification
KW - Extreme-boosted decision-trees
KW - Incident duration prediction
KW - Intra–extra joint optimisation
KW - Light gradient boosting modelling
KW - Machine learning
KW - Regression
UR - http://www.scopus.com/inward/record.url?scp=85131226285&partnerID=8YFLogxK
U2 - 10.1016/j.trc.2022.103721
DO - 10.1016/j.trc.2022.103721
M3 - Article
AN - SCOPUS:85131226285
SN - 0968-090X
VL - 141
JO - Transportation Research Part C: Emerging Technologies
JF - Transportation Research Part C: Emerging Technologies
M1 - 103721
ER -