Table 4 challenges of traffic incident duration analysis and prediction

Combining multiple data resources

Intelligent vehicle system (for example, eCall)

Sdongos et al. [59]; Oorni, Goulart [60]

Traffic condition detection information

Wei, Lee [16]; Lee, Wei [17]; He et al. [40]

Crowdsourcing technology

Gu et al. [61]; Kurkcu et al. [62]

Time sequential prediction model

Based on response term’s report

Khattak et al. [5]; Pereira et al. [45]; Li et al. [46]

Based information from social media

Gu et al. [61]

Outlier prediction

Different models for different duration ranges

Lin et al. [10]; Valenti et al. [19]

A time sequential prediction model

Qi, Teng [55]; Pereira et al. [45]; Li et al. [46]

Improvement of prediction methods

Machine Learning

Zhan et al. [15]; Lin et al. [54]; Park et al. [57]; Ma et al. [82] et al.

Updated HBDM

Li et al. [46] et al.

Combining recovery times

Combine new data resource

Hojati et al. [23]

Influence of unobserved factors

Randomness model

Nam, Mannering [9]; Hojati et al. [23]; Li et al. [52]