An Explainable Statistical Learning Algorithm to Support Data Fusion

This paper presents a statistical learning algorithm called the relevance vector machine that is currently under development to support data fusion applications. The algorithm is applicable to classification and regression problems and has been shown to be capable of learning complex, explainable behaviors in real engineering problems. This article summarizes construction of the learning algorithm and provides an example application to demonstrate some of the capabilities of the relevance vector machine with feature fusion. Finally, the possibilities are presented for using the relevance vector machine to support multi-modal data fusion by exploiting the statistically consistent outputs given by the model to extend binary label fusion to continuous label fusion.