Xiliang Liu

Intersection delay estimation from floating car data via principal curves: a case study on Beijing's road network

It is a pressing task to estimate the real-time travel time on road networks reliably in big cities, even though floating car data has been widely used to reflect the real traffic. Currently floating car data are mainly used to estimate the real-time traffic conditions on road segments, and has done little for turn delay estimation. However, turn delays on road intersections contribute significantly to the overall travel time on road networks in modern cities. In this paper, we present a technical framework to calculate the turn delays on road networks with float car data. First, the original floating car data collected with GPS equipped taxies was cleaned and matched to a street map with a distributed system based on Hadoop and MongoDB. Secondly, the refined trajectory data set was distributed among 96 time intervals (from 0: 00 to 23: 59). All of the intersections where the trajectories passed were connected with the trajectory segments, and constituted an experiment sample, while the intersections on arterial streets were specially selected to form another experiment sample. Thirdly, a principal curve-based algorithm was presented to estimate the turn delays at the given intersections. The algorithm argued is not only statistically fitted the real traffic conditions, but also is insensitive to data sparseness and missing data problems, which currently are almost inevitable with the widely used floating car data collecting technology. We adopted the floating car data collected from March to June in Beijing city in 2011, which contains more than 2.6 million trajectories generated from about 20000 GPS-equipped taxicabs and accounts for about 600 GB in data volume. The result shows the principal curve based algorithm we presented takes precedence over traditional methods, such as mean and median based approaches, and holds a higher estimation accuracy (about 10%–15% higher in RMSE), as well as reflecting the changing trend of traffic congestion. With the estimation result for the travel delay at intersections, we analyzed the spatio-temporal distribution of turn delays in three time scenarios (0: 00–0: 15, 8: 15–8: 30 and 12: 00–12: 15). It indicates that during one’s single trip in Beijing, average 60% of the travel time on the road networks is wasted on the intersections, and this situation is even worse in daytime. Although the 400 main intersections take only 2.7% of all the intersections, they occupy about 18% travel time.

A ST-CRF Map-Matching Method for Low-Frequency Floating Car Data

Integrating raw Global Position System (GPS) trajectories with a road network is often referred to as a map-matching problem. However, low-frequency trajectories (e.g., one GPS point for every 1–2 min) have raised many challenges to existing map-matching methods. In this paper, we propose a novel and global spatial–temporal map-matching method called spatial and temporal conditional random field (ST-CRF), which is based on insights relating to: 1) the spatial positioning accuracy of GPS points with the topological information of the underlying road network; 2) the spatial–temporal accessibility of a floating car; 3) the spatial distribution of the middle point between two consecutive GPS points; and 4) the consistency of the driving direction of a GPS trajectory. We construct a conditional random field model and identify the best matching path sequence from all candidate points. A series of experiments conducted for real environments using mass floating car data collected in Beijing and Shanghai shows that the ST-CRF method not only has better performance and robustness than other popular methods (e.g., point-line, ST-matching, and interactive voting-based map-matching methods) in low-frequency map matching but also solves the “label-bias” problem, which has long existed in the map matching of classical hidden Markov-based methods.

Estimating Beijing's travel delays at intersections with floating car data

In this paper, we presented a technical framework to calculate the turn delays on road network with floating car data (FCD). Firstly the original FCD collected with GPS equipped taxies was cleaned and matched to a street map with a distributed system based on Hadoop and MongoDB. Secondly the refined dataset was distributed and matched to the specific intersections among 96 time intervals (from 0:00 to 23:59 per 15 minutes). Thirdly a principal curve-based algorithm was presented to estimate the turn delays at the given intersections. The algorithm is argued not only statistically fitted the real traffic conditions but also is insensitive to data sparseness and data missing problems. We adopted the floating car data collected from March to June in Beijing in 2011, which contains more than 2.6 million trajectories generated from about 20,000 GPS-equipped taxicabs and accounts for about 600 GB in data volume. The result shows the presented algorithm takes precedence of traditional methods, such as mean and median based approaches, and holds a higher estimation accuracy (about 10%~15% higher in RMSE), as well as reflects the changing trend of traffic congestion. With the estimation result, the turn delay ratios both on the whole network and on the 400 main intersections are calculated. It indicates that average 60% of the travel time on the road network, especially in daytime, is cost on intersections, and the 400 main intersections, which only take 2.7% of all the intersections, yet cost about 18% travel time in Beijing.

Road2Vec: Measuring Traffic Interactions in Urban Road System from Massive Travel Routes

Good characterization of traffic interactions among urban roads can facilitate traffic-related applications, such as traffic control and short-term forecasting. Most studies measure the traffic interaction between two roads by their topological distance or the correlation between their traffic variables. However, the distance-based methods neglect the spatial heterogeneity of roads’ traffic interactions, while the correlation-based methods cannot capture the non-linear dependency between two roads’ traffic variables. In this paper, we propose a novel approach called Road2Vec to quantify the implicit traffic interactions among roads based on large-scale taxi operating route data using a Word2Vec model from the natural language processing (NLP) field. First, the analogy between transportation elements (i.e., road segment, travel route) and NLP terms (i.e., word, document) is established. Second, the real-valued vectors for road segments are trained from massive travel routes using the Word2Vec model. Third, the traffic interaction between any pair of roads is measured by the cosine similarity of their vectors. A case study on short-term traffic forecasting is conducted with artificial neural network (ANN) and support vector machine (SVM) algorithms to validate the advantages of the presented method. The results show that the forecasting achieves a higher accuracy with the support of the Road2Vec method than with the topological distance and traffic correlation based methods. We argue that the Road2Vec method can be effectively utilized for quantifying complex traffic interactions among roads and capturing underlying heterogeneous and non-linear properties.

ST-PF: Spatio-Temporal Particle Filter for Floating-Car Data Pre-processing

Floating-car data (FCD) are never perfectly accurate due to various noises. To make FCD available, we propose a novel spatio-temporal particle filter ST-PF for FCD pre-processing. First we analyze the causes of errors and the shortcomings of previous studies. Second, we introduce the spatio-temporal constraints into the modeling of ST-PF. We also devise a novel iterating strategy for the recurrence of particle filtering based on sequential-importance sampling (SIS). We further design a series of experiments and compare the performances with that of other four traditional filters, namely, the mean filter, the median filter, the Kalman filter, and the original particle filter. The final results show ST-PF is much more effective for noise reduction and improvement of map-matching performance and shows a promising direction for FCD pre-processing.

A fine-grained perspective on the robustness of global cargo ship transportation networks

The robustness of cargo ship transportation networks is essential to the stability of the world trade system. The current research mainly focuses on the coarse-grained, holistic cargo ship transportation network while ignoring the structural diversity of different sub-networks. In this paper, we evaluate the robustness of the global cargo ship transportation network based on the most recent Automatic Identification System (AIS) data available. First, we subdivide three typical cargo ship transportation networks (i.e., oil tanker, container ship and bulk carrier) from the original cargo ship transportation network. Then, we design statistical indices based on complex network theory and employ four attack strategies, including random attack and three intentional attacks (i.e., degree-based attack, betweenness- based attack and flux-based attack) to evaluate the robustness of the three typical cargo ship transportation networks. Finally, we compare the integrity of the remaining ports of the network when a small proportion of ports lose their function. The results show that 1) compared with the holistic cargo ship transportation network, the fine-grain-based cargo ship transportation networks can fully reflect the pattern and process of global cargo transportation; 2) different cargo ship networks behave heterogeneously in terms of their robustness, with the container network being the weakest and the bulk carrier network being the strongest; and 3) small-scale intentional attacks may have significant influence on the integrity of the container network but a minor impact on the bulk carrier and oil tanker transportation networks. These conclusions can help improve the decision support capabilities in maritime transportation planning and emergency response and facilitate the establishment of a more reliable maritime transportation system.

Fine-grained prediction of urban population using mobile phone location data

ABSTRACT Fine-grained prediction of urban population is of great practical significance in many domains that require temporally and spatially detailed population information. However, fine-grained population modeling has been challenging because the urban population is highly dynamic and its mobility pattern is complex in space and time. In this study, we propose a method to predict the population at a large spatiotemporal scale in a city. This method models the temporal dependency of population by estimating the future inflow population with the current inflow pattern and models the spatial correlation of population using an artificial neural network. With a large dataset of mobile phone locations, the model’s prediction error is low and only increases gradually as the temporal prediction granularity increases, and this model is adaptive to sudden changes in population caused by special events.

A holistic approach to aligning geospatial data with multidimensional similarity measuring

ABSTRACT Semantically aligning the heterogeneous geospatial datasets (GDs) produced by different organizations demands efficient similarity matching methods. However, the strategies employed to align the schema (concept and property) and instances are usually not reusable, and the effects of unbalanced information tend to be neglected in GD alignment. To solve this problem, a holistic approach is presented in this paper to integrally align the geospatial entities (concepts, properties and instances) simultaneously. Spatial, lexical, structural and extensional similarity metrics are designed and automatically aggregated by means of approval voting. The presented approach is validated with real geographical semantic webs, Geonames and OpenStreetMap. Compared with the well-known extensional-based aligning system, the presented approach not only considers more information involved in GD alignment, but also avoids the artificial parameter setting in metric aggregation. It reduces the dependency on specific information, and makes the alignment more robust under the unbalanced distribution of various information.

SHE: Stepwise Heterogeneous Ensemble Method for Citywide Traffic Analysis

Sensored traffic data in modern cities have been collected and applied for various purposes in the domain of intelligent transportation systems (ITS). However, analyzing these traffic data often lacks in priori knowledge due to the dynamics of transportation systems, making it hard to cope with diverse scenarios with specific models. In view of the limitations of traditional approaches, in this paper, we propose the Stepwise Heterogeneous Ensemble (SHE) for citywide traffic analysis based on stacked generalization. We first prove SHEs effectiveness using error-ambiguity decomposition technique. Secondly we analyze the optimal linear combination of SHE and present the stepwise iterating strategy. We also demonstrate its validity based on Kullback-Leibler divergence analysis. Thirdly we integrate six classical approaches into SHE framework, including linear least squares regression (LLSR), autoregressive moving average (ARMA), historical mean (HM), artificial neural network (ANN), radical basis function neural network (RBFNN), support vector machine (SVM). We further compare SHEs performance with other four linear combination models, namely equal weights method (EW), optimal weights method (OW), minimum error method (ME) and minimum variance method (MV). A series of experiments are conducted with a real city traffic dataset in Beijing city. The results show that the proposed SHE method behaves more robust and precise than other six single methods. Moreover, this method also outperforms other four different combination strategies both in variance and bias. In addition, the SHE method provides an open-ending framework for citywide traffic analysis, which means any new promising models can be easily incorporated into it in the future.

Optimization on Arrangement of Precaution Areas Serving for Ships’ Routeing in the Taiwan Strait Based on Massive AIS Data

The Taiwan Strait is the gateway used by ships of almost every kind on passage to and from nearly all the important ports in Northeast Asia. To minimize the possibility of collisions between crossing and through traffic, Precaution Areas (PAs) were laid out to remind mariners where the crossing and encountering situations may occur in the strait. Recent advances in telemetry technology help to collect ships movement data more efficiently and accurately. These advances would be useful for delineating Principal Fairways (PFs) in the crowded strait-corridor. Based on ship trajectory observations of transit-passage and cross-strait transits, cumulative activity patterns are characterized in the form of probability density. Bringing the layer of popular direct cross-strait lanes to the iso-surface of PFs, all conflict areas were extracted as PAs of the Ships Routing System Plan in Taiwan Strait. For direct cross-strait transportations, by linking the centers of PAs in the strait with the official pass points outside the western Taiwan harbors, this paper recommends the applicable direct cross-strait routes to reduce the risk of conflicts in the strait.