Robust decision making method for adaptive ordered-statistics CFAR technique using information elasticity

An Information Elasticity Framework for the Adaptive Matched Filter

“…Equation ( 16) represents the component of the cost associated with P F A . Similarly, (17) represents the component of the cost associated with K. Since these functions describe "relative cost," it is important to define a scale of cost over which decisions can be compared. Thus, 1 is defined to be the maximum cost and 0 is defined to be the minimum cost.…”

“…This might be the case if it is required that a DM selects a specific P F A value but is given freedom over the choice in K, or vice versa. In this case, the DM would use either (17) or ( 16) as the constraint function, which is equivalent to using (18) and setting either λ 1 or λ 2 to be 0.…”

“…Previous work on this topic has noted that increasing the amount of data does not necessarily reflect an increase in the effectiveness of decisions. In these studies [15]- [17], a certain point is reached (known as the overload, or tipping point), at which increasing the amount of information no longer provides meaningful benefit, and actually degrades system performance. The concept of information elasticity allows a DM to understand where this point of information overload exists, and select a decision which maximizes the decision effectiveness.…”