A Scenario-Oriented Approach for Noise Detection on Traffic Flow Data

Road transport solutions depend on the quality of the measurements of the underlying traffic state. This paper introduces quality indicators that aim at identify the presence of traffic measurement anomalies. The proposed method seeks inconsistency in the traffic measures by statistically evaluating the variability of measures. The computation of this indicator set is mainly based on bootstrapping. Each one of them was developed to address a distinct scenario. Experiments conducted using world traffic data shows promising results.