Bei Pan

Utilizing Real-World Transportation Data for Accurate Traffic Prediction

For the first time, real-time high-fidelity spatiotemporal data on transportation networks of major cities have become available. This gold mine of data can be utilized to learn about traffic behavior at different times and locations, potentially resulting in major savings in time and fuel, the two important commodities of 21st century. As a first step towards the utilization of this data, in this paper, we study the real-world data collected from Los Angeles County transportation network in order to incorporate the datas intrinsic behavior into a time-series mining technique to enhance its accuracy for traffic prediction. In particular, we utilized the spatiotemporal behaviors of rush hours and events to perform a more accurate prediction of both short-term and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents). Our result shows that taking historical rush-hour behavior we can improve the accuracy of traditional predictors by up to 67% and 78% in short-term and long-term predictions, respectively. Moreover, we can incorporate the impact of an accident to improve the prediction accuracy by up to 91%.

Forecasting Spatiotemporal Impact of Traffic Incidents on Road Networks

The advances in sensor technologies enable real-time collection of high-fidelity spatiotemporal data on transportation networks of major cities. In this paper, using two real-world transportation datasets: 1) incident data and 2) traffic data, we address the problem of predicting and quantifying the impact of traffic incidents. Traffic incidents include any non-recurring events on road networks, including accidents, weather hazard, road construction or work zone closures. By analyzing archived incident data, we classify incidents based on their features (e.g., time, location, type of incident). Subsequently, we model the impact of each incident class on its surrounding traffic by analyzing the archived traffic data at the time and location of the incidents. Consequently, in real-time, if we observe a similar incident (from real-time incident data), we can predict and quantify its impact on the surrounding traffic using our developed models. This information, in turn, can help drivers to effectively avoid impacted areas in real-time. To be useful for such real-time navigation application, and unlike current approaches, we study the dynamic behavior of incidents and model the impact as a quantitative time varying spatial span. In addition to utilizing incident features, we improve our classification approach further by analyzing traffic density around the incident area and the initial behavior of the incident. We evaluated our approach with very large traffic and incident datasets collected from the road networks of Los Angeles County and the results show that we can improve our baseline approach, which solely relies on incident features, by up to 45%.

Towards modeling the traffic data on road networks

A spatiotemporal network is a spatial network (e.g., road network) along with the corresponding time-dependent weight (e.g., travel time) for each edge of the network. The design and analysis of policies and plans on spatiotemporal networks (e.g., path planning for location-based services) require realistic models that accurately represent the temporal behavior of such networks. In this paper, for the first time we propose a traffic modeling framework for road networks that enables 1) generating an accurate temporal model from archived temporal data collected from a spatiotemporal network (so as to be able to publish the temporal model of the spatiotemporal network without having to release the real data), and 2) augmenting any given spatial network model with a corresponding realistic temporal model custom-built for that specific spatial network (in order to be able to generate a spatiotemporal network model from a solely spatial network model). We validate the accuracy of our proposed modeling framework via experiments. We also used the proposed framework to generate the temporal model of the Los Angeles County freeway network and publish it for public use.

Discovering patterns in traffic sensor data

We maintain a one of a kind, large-scale and high resolution (both spatially and temporally) traffic sensor dataset collected from the entire Los Angeles County road network. Traffic sensors (installed under the road pavement) are used to measure real-time traffic flows through road segments. In this paper, we exploit this dataset to rigorously verify two popular instinctive understandings about traffic flows on road segments: 1) each road segment has a typical traffic flow (known by local travelers) and one can often categorize road segments based on the similarity of their traffic flows, and 2) the road segments within each category not only have similar traffic flows but also are similar in their other characteristics (such as locality, connectivity). Toward this end, we developed a hypothesis analysis framework based on a variety of clustering and correlation evaluation techniques and leveraged this framework to respectively show the following. First, the set of road segments can indeed be partitioned into a set of distinct subpartitions with similar traffic flows, and there is a limited number of signature traffic patterns/labels each of which can accurately represent all traffic flows of a subpartition of the road segments. Second, all segments within each subpartition (represented by one signature) are also highly similar in three other characteristics, namely, direction, connectivity and locality. Our experiments verify our observations with high confidence.