Shall I Merge that Data? Assessing Consistency of Traffic Data Collected from Multiple Sources

The design and development of intelligent transportsystems rely heavily on the availability of data, which allows for amore comprehensive understanding of current traffic conditionsand their likely evolution. While merging all data sources togethermight be tempting, ensuring the consistency of data collectedfrom different sources is crucial. Noise or large discrepanciescan jeopardise the usefulness of merging data and hinder thepotential benefits.<br/><br/>This paper investigates the integration of data from differentsources by analysing the consistency of data from two sensorsets deployed in a region of Manchester, United Kingdom. Toperform this analysis, we identified suitable road segments forconsideration and leveraged extended Kalman filters. Further,we exploit the opportunity to assess the sensitivity of the sensorsto potentially critical circumstances.