Ensemble learning based multi-source information fusion

Aiming at the target recognition tasks of multi-source sensors, this paper proposes a decision-level information fusion model based on ensemble learning to improve the target recognition ability of distributed sensors. Based on distributed sensing data, feature analysis model is first constructed to reduce the dimension of original data. Then, target recognition model is constructed by data mining to realize the rapid identification by single classifier. On this basis, information fusion model based on ensemble learning is proposed to assist decision-making, combined with different ensemble strategies to improve the robustness and reliability of multi-source sensor target recognition. Finally, five public data sets are used to verify the effect of multi-source information fusion model under four homogeneous strategies and two heterogeneous strategies.