01023236

English

http://dx.doi.org/10.3141/1935-07

The rich data on intelligent transportation systems (ITS) are a precious resource for transportation researchers and practitioners. However, the usability of this resource is greatly limited by missing data. Many imputation methods have been proposed in the past decade. However, some issues are still not addressed or are not sufficiently addressed, for example, the missing of entire records, temporal correlation in observations, natural characteristics in raw data, and unbiased estimates for missing values. This paper proposes an advanced imputation method based on recent development in other disciplines, especially applied statistics. The method uses a Bayesian network to learn from the raw data and a Markov chain Monte Carlo technique to sample from the probability distributions learned by the Bayesian network. It imputes the missing data multiple times and makes statistical inferences about the result. In addition, the method incorporates a time series model so that it allows data missing in entire rows—an unfavorable missing pattern frequently seen in ITS data. Empirical study shows that the proposed method is robust and accurate. It is ideal for use as a high-quality imputation method for off-line application.

HRIS

Print

pp 57-67

01023220

2005

Transportation Research Record: Journal of the Transportation Research Board

0309094097

Figures (8) ; References (18) ; Tables (1)

Accuracy; Bayesian networks; Distributions (Statistics); Intelligent transportation systems; Markov chains; Missing data; Monte Carlo method; Multiple imputation; Robustness

Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning

Apr 25 2006 5:03PM

• Calibration of Microsimulation Models Using Nonparametric Statistical Techniques
• Development of Methodology to Design Advanced Traffic Surveillance Systems for Traffic Information Based on Origin–Destination
• Efficient Map Matching of Large Global Positioning System Data Sets: Tests on Speed-Monitoring Experiment in Zürich
• Evaluation of AASHTO SiteManager Performance on High-Latency Satellite Communication Links
• Exploring the Relationship Between Data Aggregation and Predictability to Provide Better Predictive Traffic Information
• Geographically Stratified Importance Sampling for the Calibration of Aggregated Destination Choice Models for Trip Distribution
• ISO 19133 Tracking and Navigation Standard: 6.6 Linear Reference System Standard
• Lane-Based Network for Flow Analysis and Inventory Management of Transportation Networks
• Modeling Location Choice of Secondary Activities with a Social Network of Cooperative Agents
• Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method
• Q-Learning for Flexible Learning of Daily Activity Plans
• Robust Route Guidance Model Based on Advanced Traveler Information Systems
• Simple Map-Matching Algorithm Applied to Intelligent Winter Maintenance Vehicle Data
• Travel Time Prediction Algorithm Scalable to Freeway Networks with Many Nodes with Arbitrary Travel Routes
• Using a Fuzzy Quality Function Deployment Model to Identify Improvement Points in Airport Cargo Terminals
• Using Decision Support System and Graphical User Interface to Choose Appropriate Lane Configurations at Toll Facilities
• Using the Ant Algorithm to Derive Pareto Fronts for Multiobjective Siting of Emergency Service Facilities
• Vehicle Detection and Classification Using Model-Based and Fuzzy Logic Approaches