Sensor selectivity and intelligent data fusion

The paper addresses the question of performance improvement as a result of multisensor data fusion and its ramifications on the design of a data fusion system. Sensor selectivity requires that data quality control and error detection capabilities be incorporated in the fusion design. Data quality control and error detection may not be feasible at the signal level requiring additional intelligence to be built in the fusion loop, prior to or after fusing the data. This leads to the notion of intelligent data fusion design which involves pre-fusion data quality control loops for error detection prior to fusion using data models and post-fusion data quality control loops based on meta-fusion level inference. Shortcomings in applying the optimal fusion rules in the presence of partial statistical knowledge and means to overcome them are discussed. The need of data validation and adaptive sensitivity control in the fusion design, when optimality conditions are not satisfied, is demonstrated and suggestions for designing the feedback loop are given. The design of an intelligent data fusion is discussed and a design for adaptive sensor sensitivity control presented