Recognizing Spatio-Temporal Traffic Patterns at Intersections Using Self-Organizing Maps

Abstract

Recognition and interpretation of regularly (e.g. every weekday) and irregularly (e.g. arbitrary events such as accidents) appearing traffic patterns in a road network are considered one of the most crucial questions in mobility data analysis. Knowledge of regular and irregular traffic patterns is a requirement for reliable traffic prediction or traffic control. In this paper, we present a spatiotemporal unsupervised machine learning approach using selforganizing maps (SOMs) for detecting regular traffic patterns at arbitrary intersections in a nationwide road network. The approach applies SOMs to traffic states expressed as gradual level-of-service (LOS) values, which were derived from travel time measurements of probe vehicles. For the identification of regular patterns, they were temporally categorized by daytime (60 minutes slots) and the day of the week. The approach consists of two steps: First, an unsupervised learning approach clusters intersections with similar time-dependent gradual LOS values in order to identify similar traffic patterns. Second, a subsequent temporal analysis enables the interpretation of temporal regularities of the patterns. Based on a one-year probe vehicle dataset, we showed that the clustering reveals plausible regularities for different intersections such as interchanges, urban intersections or roundabouts that are still interpretable by humans. Furthermore, the approach can be easily adapted to identify patterns in other parts of a road network.

Mining Topological Dependencies of Recurrent Congestion in Road Networks

“…Several studies consider outlier detection in road traffic data. In [28], anomalous traffic flow is detected by grouping road intersections via their traffic flow patterns and selforganising maps. The authors of [29] focus on detecting outliers in the traffic load by sudden changes.…”

Challenges of Accessibility of a Disaster-Prone Island: Experience of Hatiya, Bangladesh

“…A common way to describe accessibility to the transport system is through assessing the Level of Service (LOS). LOS is a system of evaluating service variables of public transport and is easy to interpret as the variables describe free flow, delayed and congested states as clearly distinct and disjoint classes (Brunauer et al, 2018). LOS concerning accessibility can have four different levels (World Bank, 2001) which may apply to an island as well.…”

Mining the spatio‐temporal pattern using matrix factorisation: a case study of traffic flow

“…However, most of these papers do not restraint the value of resulting factor matrices into suitable range at first so that the result is lack of effective physical meanings. Besides, many clustering methods are used to learn the traffic pattern [21–23]. The self‐organised map (SOM) network [24] shows its advantages of the ability to grasp the topology coherence and is used in [21] to find the properties of road intersection change.…”