With the 10 folds cross-validation method, the average classification rate is found to be 82.18% with the standard deviation of 3.31%. In Fig. 3, a visual representation of classification rate with respect to each fold is shown.
 Another performance criterion of the classifier is the deterioration rate (dr) [22]. When new classes are added gradually in an incremental classifier, its performance degrades and dr gives a
quantitative measure of the rate of degradation. Lower the deterioration rate, better is the classifier in terms of its stability feature of the incremental learning algorithm. Its value is obtained from
the ratio of the difference in classification accuracy with initial configuration of the network (ci) and that of the grown network (cg) configuration to the number of test patterns N as given in the
following equation