A Survey on Multisensor Fusion and Consensus Filtering for Sensor Networks

Table 2

The mechanisms of four consensus filtering approaches.

Types	Structures of consensus filters	References
CE		[22, 23]
CM		[20, 22]
CI		[24, 25]
consensus		[11, 26]

Throughout the table, is the systems matrix. For each node , , , and are, respectively, measurement matrix, covariance matrix of measurement noise, and measurement output, and are the filter and consensus gains to be determined, and is the consensus weight after step consensus. Further, denote and as information matrix and information vector and and as innovation pair. Where and are the filtering error and initial error for node , respectively. is the disturbance attenuation level, and represents noise, while is the given positive definite matrix.