Blind mobile sensor calibration using an informed nonnegative matrix factorization with a relaxed rendezvous model

摘要: In this paper, we consider the problem of blindly calibrating a mobile sensor network—i.e., determining gain and offset each sensor—from heterogeneous observations on defined spatial area over time. For that purpose, previously proposed blind calibration method based Weighted Informed Nonnegative Matrix Factorization with missing entries. It required minimum number rendezvous—i.e., data sensed by different sensors at almost same time place—which might be difficult to satisfy in practice. paper relax rendezvous requirement using sparse decomposition signal interest respect known dictionary. The can thus performed if share some common support dictionary, provides consistent performance even no are exact rendezvous.