xing Xing

Learning Common Metrics for Homogenous Tasks in Traffic Flow Prediction

Nearest neighbor based nonparametric regression is a classic data-driven method for traffic flow prediction in intelligent transportation systems (ITS). Performances of those models depend heavily on the similarity or distance metric used to search nearest neighborhood. Metric learning algorithms have been developed to learn the distance metrics from data in recent years. In real-world transportation application, multiple forecasting tasks are set since there are lots of road sections and detector points in the traffic network. Previous works tend to learn only one global metric to be used for all the tasks or learn multiple local metrics for each task which may lead to under-fitting or over-fitting problem. To balance these two kinds of methods and improve the generalization of learned metrics, we propose a common metric learning algorithm under the intuition that homogenous tasks tend to have similar local metrics. Then the learned common metrics are used in common metric KNN (CM-KNN) for traffic flow prediction. Experimental results show that our algorithm to learn common metrics are reasonable and CM-KNN method for traffic flow prediction outperforms other competing methods.

Hybrid Multi-metric K-Nearest Neighbor Regression for Traffic Flow Prediction

Traffic flow prediction is a fundamental component in Intelligent Transportation Systems (ITS). Nearest neighbor based nonparametric regression method is a classic data-driven method for traffic flow prediction. Modern data collection technologies provide the opportunity to represent various features of the nonlinear complex system which also bring challenges to fuse the multiple sources of data. Firstly, the classic Euclidean distance metric based models for traffic flow prediction that treat each feature with equal weight is not effective in multi-source high-dimension feature space. Secondly, traditional handcrafting feature engineering by experts is tedious and error-prone. Thirdly, the traffic conditions in real-life situation are too complex to measure with only one distance metric. In this paper, we propose a hybrid multi-metric based k-nearest neighbor method (HMMKNN) for traffic flow prediction which can seize the intrinsic features in data and reduce the semantic gap between domain knowledge and handcrafted feature engineering. Experimental results demonstrate multi-source data fusion helps to improve the performance of traffic parameter prediction and HMMKNN outperforms the traditional Euclidean-based k-NN under various configurations. Furthermore, visualization of feature transformation clustering results implies the learned metrics are more reasonable.

Traffic Flow Decomposition and Prediction Based on Robust Principal Component Analysis

Research on traffic data analysis is becoming more available and important. One of the key challenges is how to accurately decompose the high-dimensional, noisy observation traffic flow matrix into sub-matrices that correspond to different classes of traffic flow which builds a foundation for traffic flow prediction, abnormal data detection and missing data imputation. While in traditional research, Principal Component Analysis (PCA) is usually used for traffic matrix analysis. However, the traffic matrix is usually corrupted by large volume anomalies, the resulting principal components will be significantly skewed from those in the anomaly-free case. In this paper, we introduce the Robust Principal Component Analysis (robust PCA) for decomposition. It can mine more accurate and robust underlining temporal and spatial characteristics of traffic flow with all kinds of fluctuations. We performed a comparative experimental analysis based on robust PCA with PCA-based method on a real-life dataset and got better decomposition performance. In the real-life dataset, results show that through robust PCA most of the large volume anomalies are short-lived and well isolated in the residual traffic matrix while PCA failed. In traffic flow prediction experiments based on decomposition, it shows that the result based on robust PCA outperforms the PCA and simple average. It provide adequate evidence that robust PCA is more appropriate for traffic flow matrix analysis. Robust PCA shows promising abilities in improving the accuracy and reliability of traffic flow analysis.

Traffic zone division using mobile billing data.

Traffic zoning which could simplify complex urban traffic network is a fundamental work in urban planning and transportation management. Traditional traffic zone division is mainly on census data which cost tremendous resources but could only cover part of people and areas in city. This paper develops a comprehensive approach of traffic zone division on mobile billing data which owns the advantages of (1). high coverage, (2). cost effective and (3). up to date. Land use information obtained from phone call volume and commuting volume as well as spatial obstacles represented as Voronoi distance are taken into account in similarity measurements. Clustering measurements and traffic zone factors are employed to evaluate our approach. Experiments show good performance of our method in both dealing with spatial obstacles and traffic zone measurements.

Mining Dependencies Considering Time Lag in Spatio-Temporal Traffic Data

Learning dependency structure is meaningful to characterize causal or statistical relationships. Traditional dependencies learning algorithms only use the same time stamp data of variables. However, in many real-world applications, such as traffic system and climate, time lag is a key feature of hidden temporal dependencies, and plays an essential role in interpreting the cause of discovered temporal dependencies. In this paper, we propose a method for mining dependencies by considering the time lag. The proposed approach is based on a decomposition of the coefficients into products of two-level hierarchical coefficients, where one represents feature-level and the other represents time-level. Specially, we capture the prior information of time lag in spatio-temporal traffic data. We construct a probabilistic formulation by applying some probabilistic priors to these hierarchical coefficients, and devise an expectation-maximization (EM) algorithm to learn the model parameters. We evaluate our model on both synthetic and real-world highway traffic datasets. Experimental results show the effectiveness of our method.

Discovering spatio-temporal dependencies based on time-lag in intelligent transportation data

Abstract Learning spatio-temporal dependency structure is meaningful to characterize causal or statistical relationships. In many real-world applications, dependency structure is often characterized by time-lag between variables. For example, traffic system and climate, time lag is a key feature of hidden temporal dependencies, and plays an essential role in interpreting the cause of discovered temporal dependencies. However, traditional dependencies learning algorithms only use the same time stamp data of variables. In this paper, we propose a method for mining dependencies by considering the time lag. The proposed approach is based on a decomposition of the coefficients into products of two-level hierarchical coefficients, where one represents feature-level and the other represents time-level. Specially, we capture the prior information of time lag in intelligent transportation data. We construct a probabilistic formulation by applying some probabilistic priors to these hierarchical coefficients, and devise an expectation-maximization (EM) algorithm to learn the model parameters. We evaluate our model on both synthetic and real-world highway traffic datasets. Experimental results show the effectiveness of our method.

Structure Feature Learning Method for Incomplete Data

Learning with incomplete data remains challenging in many real-world applications especially when the data is high-dimensional and dynamic. Many imputation-based algorithms have been proposed to handle with incomplete data, where these algorithms use statistics of the historical information to remedy the missing parts. However, these methods merely use the structural information existing in the data, which are very helpful for sharing between the complete entries and the missing ones. For example, in traffic system, some group information and temporal smoothness exist in the data structure. In this paper, we propose to incorporate these structural information and develop structural feature leaning method for learning with incomplete data (SFLIC). The SFLIC model adopt a fused Lasso based regularizer and a group Lasso style regularizer to enlarge the data sharing along both the temporal smoothness level and the feature group level to fill the gap where the data entries are missing. The proposed SFLIC model is a nonsmooth function according to the model parameters, and we adopt the smoothing proximal gradient (SPG) method to seek for an efficient solution. We evaluate our model on both synthetic and real-world highway traffic datasets. Experimental results show that our method outperforms the state-of-the-art methods.

Incorporating temporal smoothness and group structure in learning with incomplete data

Learning with incomplete data remains challenging in many real-world applications especially when the data is high-dimensional and dynamic. Many imputation based algorithms have been proposed to handle with incomplete data, where these algorithms use statistics of the historical information to remedy the missing parts. However, these methods merely use the structural information existed in the data, which are very helpful for sharing between the complete entries and the missing ones. For example, in traffic system, some group information and temporal smoothness exist in the data structure. In this paper, we propose to incorporate these structural information and develop a Structural Feature Leaning method for learning with InComplete data (SFLIC). The SFLIC model adopts a fused Lasso based regularizer and a group Lasso style regularizer to enlarge the data sharing along both the temporal smoothness level and the feature group level to fill the gap where the data entries are missing. The proposed SFLIC model is non-smooth function according to the model parameters, and we adopt the smoothing proximal gradient (SPG) method to seek for an efficient solution. We evaluate our model on both synthetic and real-world highway traffic datasets. Experimental results show that our method outperforms the state-of-the-art methods.

A Spatial-temporal Topic Segmentation Model for Human Mobile Behavior

Research on human mobile behavior is becoming more available and important. One of the key challenges is how to divide long and continuous trajectory sequences into meaningful segments which builds a foundation for user similarity measure, trajectory data management and routine mining. While in traditional research trajectory sequence is segmented on basis of fixed time window or spatiotemporal criteria. In this paper, we propose a probabilistic topic model considering the spatial property and temporal Markov property of human mobility to address the problem of topic segmentation in human mobile behavior: automatically segmenting trajectory sequence into meaningful segments. The trajectory segments reflect high-level semantics for understanding human mobile behavior and can be used for higher-level applications. We consider one synthetic dataset and one real-life human dataset collected by mobile phones to evaluate our model. Results show that our model has good results in segmentation and outperforms traditional methods for practical purposes especially in learning long duration routines.

Measurement analysis of traffic flow uncertainty on Chinese highway network

Extensive research has been done on traffic forecasting. However, performance of forecasting models is highly influenced by traffic uncertainty and predictability. Traffic uncertainty is important for road users and governors as well. With support of adequate real data from toll stations, we reveal laws in traffic flow uncertainty by employing dispersion coefficient. For further study, Hurst exponent and Approximate Entropy reflect temporal characteristics, indicating long-term randomness and short-term complexity respectively. These measurements all suggest that traffic flow uncertainty drops with the increase of time interval. Our study provides effective measuring methods of uncertainty and theoretical evidence for 15 minutes time horizon in short-term traffic prediction. Daily periodicity exists that highway traffic flow at night is more uncertain than in day time, and off-peak hour flows are more uncertain than peak hour flows. Finally, initial investigation into traffic predictability exhibits acme at 7 a.m. in our case.