Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations
Understanding and predicting the duration or “return-to-normal” time of traffic incidents is important for system-level management and optimization of road transportation networks. Increasing real-time availability of multiple data sources characterizing the state of urban traffic networks, together...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Future Transportation |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/ffutr.2021.669015/full |
| _version_ | 1798032078375223296 |
|---|---|
| author | Kieran Kalair Colm Connaughton Colm Connaughton |
| author_facet | Kieran Kalair Colm Connaughton Colm Connaughton |
| author_sort | Kieran Kalair |
| collection | DOAJ |
| description | Understanding and predicting the duration or “return-to-normal” time of traffic incidents is important for system-level management and optimization of road transportation networks. Increasing real-time availability of multiple data sources characterizing the state of urban traffic networks, together with advances in machine learning offer the opportunity for new and improved approaches to this problem that go beyond static statistical analyses of incident duration. In this paper we consider two such improvements: dynamic update of incident duration predictions as new information about incidents becomes available and automated interpretation of the factors responsible for these predictions. For our use case, we take one year of incident data and traffic state time-series data from the M25 motorway in London. We use it to train models that predict the probability distribution of incident durations, utilizing both time-invariant and time-varying features of the data. The latter allow predictions to be updated as an incident progresses, and more information becomes available. For dynamic predictions, time-series features are fed into the Match-Net algorithm, a temporal convolutional hitting-time network, recently developed for dynamical survival analysis in clinical applications. The predictions are benchmarked against static regression models for survival analysis and against an established dynamic technique known as landmarking and found to perform favourably by several standard comparison measures. To provide interpretability, we utilize the concept of Shapley values recently developed in the domain of interpretable artificial intelligence to rank the features most relevant to the model predictions at different time horizons. For example, the time of day is always a significantly influential time-invariant feature, whereas the time-series features strongly influence predictions at 5 and 60-min horizons. Although we focus here on traffic incidents, the methodology we describe can be applied to many survival analysis problems where time-series data is to be combined with time-invariant features. |
| first_indexed | 2024-04-11T20:08:01Z |
| format | Article |
| id | doaj.art-5cafa57fde124b7f9a0cee647b8ed579 |
| institution | Directory Open Access Journal |
| issn | 2673-5210 |
| language | English |
| last_indexed | 2024-04-11T20:08:01Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Future Transportation |
| spelling | doaj.art-5cafa57fde124b7f9a0cee647b8ed5792022-12-22T04:05:16ZengFrontiers Media S.A.Frontiers in Future Transportation2673-52102021-06-01210.3389/ffutr.2021.669015669015Dynamic and Interpretable Hazard-Based Models of Traffic Incident DurationsKieran Kalair0Colm Connaughton1Colm Connaughton2Centre for Complexity Science, University of Warwick, Coventry, United KingdomMathematics Institute, University of Warwick, Coventry, United KingdomLondon Mathematical Laboratory, London, United KingdomUnderstanding and predicting the duration or “return-to-normal” time of traffic incidents is important for system-level management and optimization of road transportation networks. Increasing real-time availability of multiple data sources characterizing the state of urban traffic networks, together with advances in machine learning offer the opportunity for new and improved approaches to this problem that go beyond static statistical analyses of incident duration. In this paper we consider two such improvements: dynamic update of incident duration predictions as new information about incidents becomes available and automated interpretation of the factors responsible for these predictions. For our use case, we take one year of incident data and traffic state time-series data from the M25 motorway in London. We use it to train models that predict the probability distribution of incident durations, utilizing both time-invariant and time-varying features of the data. The latter allow predictions to be updated as an incident progresses, and more information becomes available. For dynamic predictions, time-series features are fed into the Match-Net algorithm, a temporal convolutional hitting-time network, recently developed for dynamical survival analysis in clinical applications. The predictions are benchmarked against static regression models for survival analysis and against an established dynamic technique known as landmarking and found to perform favourably by several standard comparison measures. To provide interpretability, we utilize the concept of Shapley values recently developed in the domain of interpretable artificial intelligence to rank the features most relevant to the model predictions at different time horizons. For example, the time of day is always a significantly influential time-invariant feature, whereas the time-series features strongly influence predictions at 5 and 60-min horizons. Although we focus here on traffic incidents, the methodology we describe can be applied to many survival analysis problems where time-series data is to be combined with time-invariant features.https://www.frontiersin.org/articles/10.3389/ffutr.2021.669015/fullbig datatraffic incident duration predictionlandmarkingsurvival analysisDeep learning |
| spellingShingle | Kieran Kalair Colm Connaughton Colm Connaughton Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations Frontiers in Future Transportation big data traffic incident duration prediction landmarking survival analysis Deep learning |
| title | Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations |
| title_full | Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations |
| title_fullStr | Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations |
| title_full_unstemmed | Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations |
| title_short | Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations |
| title_sort | dynamic and interpretable hazard based models of traffic incident durations |
| topic | big data traffic incident duration prediction landmarking survival analysis Deep learning |
| url | https://www.frontiersin.org/articles/10.3389/ffutr.2021.669015/full |
| work_keys_str_mv | AT kierankalair dynamicandinterpretablehazardbasedmodelsoftrafficincidentdurations AT colmconnaughton dynamicandinterpretablehazardbasedmodelsoftrafficincidentdurations AT colmconnaughton dynamicandinterpretablehazardbasedmodelsoftrafficincidentdurations |