Imbalanced dataset classification using fuzzy ARTMAP and computational intelligence techniques

Recently, fuzzy adaptive resonance theory mapping (ARTMAP) neural networks are applied to solving complex problems due their plasticity-stability capability and property. An imbalanced dataset occurs when there is the presence of one class containing a greater number instances than other classes. It skewed representation data. Many standard algorithms have failed in mitigating problems. There four paradigms used-data level, algorithm cost-sensitive, ensemble method Here we put forward solve problem by brain-neuron framework an special type artificial network (ANN) called ARTMAP thereafter clustering known as C-means handle missing value also propose make cost-sensitive. Results indicate 100% accuracy classification.