Method of speed data fusion based on Bayesian combination algorithm and high-order multi-variable Markov model

The variety of data collecting and communication methods used in intelligent transportation systems such as sensors, cameras, and communication networks bring about huge volumes of data that are available for numerous transportation applications and related research on smart cities. However, it is still a challenge to integrate these heterogeneous data sources into a singular data schema in practice. Compared to a single data source, higher data accuracy can be obtained through integration of the multiple data sources if the data quality from each source has been known. In this study, a data fusion method based on Bayesian fusion rules is proposed to merge traffic speed from different data sources according to their prior probability that can be inferred from a high-order multivariable Markov model by considering the relations of multiple traffic factors in a systemic perspective. Case studies based on freeway data, such as loop data, INRIX data, and data from the National Performance Management and Research Data Set, are performed to validate the effectiveness of proposed speed fusion method