Bayesian inference and Dempster–Shafer evidential reasoning and their application to traffic management
Lawrence A. Klein · 2017
Bayesian inference and Dempster–Shafer evidential reasoning are widely applied for detection, classification, and identification of objects and events that occur in conjunction with traffic management strategies. Bayesian inference is a probability-based reasoning discipline grounded in Bayes&s; rule. When used to support data fusion, Bayesian inference belongs to the class of parametric algorithms that use a priori knowledge about events or objects in an observation space to make inferences about the identity of events or objects in that space. The Bayesian formulation, therefore, provides a method to combine identity declarations from multiple sensors to obtain a new and hopefully improved joint identity declaration. The Bayesian approach to recursive updating of the posterior probability occurs by utilizing the previous posteriors as the new values for the prior probabilities. Bayesian theory permits probabilities to be assigned only to the original propositions themselves.