Search for: All records

Fixed-route bus systems are an important part of the urban transportation mix. A considerable disadvantage of buses is their slow speed, which is in part due to frequent stops, but also due to the lack of segregation from other vehicles in traffic. As such, assessing bus routes is an important aspect of route planning, scheduling, and the creation of dedicated bus lanes. In this work, we use bus tracking data from the Washington Metropolitan Area Transit Authority to discover speed patterns in relation to bus stops throughout the day. This gives us an insight on whether the routes are affected by traffic congestion or more random events such as traffic lights. We first employ a macro-level qualitative analysis to identify patterns across different trips. A micro-level quantitative analysis further refines this approach by analyzing the speed patterns around bus stops. Our analysis is based on bus odometer data, which is a one-dimensional representation of trips that has considerable accuracy when looking at speed patterns. Exploiting route metadata in relation to stops, we use Dynamic Time Warping to cluster different stops based on their speed profiles throughout the day. The clustering can be used to generate a spatiotemporal route profile and we show how such a profile provides actionable intelligence for route planning purposes. 

The problem of traffic prediction is paramount in a plethora of applications, ranging from individual trip planning to urban planning. Existing work mainly focuses on traffic prediction on road networks. Yet, public transportation contributes a significant portion to overall human mobility and passenger volume. For example, the Washington, DC metro has on average 600,000 passengers on a weekday. In this work, we address the problem of modeling, classifying and predicting such passenger volume in public transportation systems. We study the case of the Washington, DC metro exploring fare card data, and specifically passenger in- and outflow at stations. To reduce dimensionality of the data, we apply principal component analysis to extract latent features for different stations and for different calendar days. Our unsupervised clustering results demonstrate that these latent features are highly discriminative. They allow us to derive different station types (residential, commercial, and mixed) and to effectively classify and identify the passenger flow of “unknown” stations. Finally, we also show that this classification can be applied to predict the passenger volume at stations. By learning latent features of stations for some time, we are able to predict the flow for the following hours. Extensive experimentation using a baseline neural network and two naïve periodicity approaches shows the considerable accuracy improvement when using the latent feature based approach. 

Effective road traffic assessment and estimation is crucial not only for traffic management applications, but also for long-term trans- portation and, more generally, urban planning. Traditionally, this task has been achieved by using a network of stationary traffic count sensors. These costly and unreliable sensors have been replaced with so-called Probe Vehicle Data (PVD), which relies on sampling individual vehicles in traffic using for example smartphones to assess the overall traffic condition. While PVD provides uniform road network coverage, it does not capture the actual traffic flow. On the other hand, stationary sensors capture the absolute traffic flow only at discrete locations. Furthermore, these sensors are often unreliable; temporary mal- functions create gaps in their time-series of measurements. This work bridges the gap between these two data sources by learning the time-dependent fraction of vehicles captured by GPS-based probe data at discrete stationary sensor locations. We can then account for the gaps of the traffic-loop measurements by using the PVD data to estimate the actual total flow. In this work, we show that the PVD flow capture changes sig- nificantly over time in the Washington DC area. Exploiting this information, we are able to derive tight confidence intervals of the traffic volume for areas with no stationary sensor coverage. 

In the current data-centered era, there are many highly diverse data sources that provide information about movement on networks, such as GPS trajectories, traffic flow measurements, farecard data, pedestrian cameras, bike-share data and even geo-social movement trajectories. The challenge identified in this vision paper is to create a unified framework for aggregating and analyzing such diverse and uncertain movement data on networks. This requires probabilistic models to capture flow/volume and movement probabilities on a network over time. Novel algorithms are required to train these models from datasets with varying levels of uncertainty. By combining information from different networks, immediate applications of such a unifying movement model include optimal site planning, map construction, traffic management, and emergency management.