\section{Assessing Performance}
This section describes how the performance of CLIFF is assessed. The process uses an $N$ x $M$ cross-validation techique which produces three(3) measures as a means to compare CLIFF before the use of SBBR to CLIFF after SBBR. The three(3) measures used are 1) the probability of detection (pd), 2) the probability of false alarms (pf), and 3) brittleness.

\subsection{pd and pf measures}


\subsection{Brittleness measure}
Once each test has been classified, the distance from the nearest unlike neighbor (NUN) i.e. the distance from a sample with a different class is recorded. Recall that brittleness is a small change can result in a different outcome, so here the closer the test sample to the NUN the more brittle it is. So an ideal result will have a greater distance from NUN. %need to talk about the rank process