In this paper we present the PHOCS-2 algorithm, which extracts a ââ?¬Å?Predicted\r\nHierarchy Of ClassifierSââ?¬Â. The extracted hierarchy helps us to enhance performance of\r\nflat classification. Nodes in the hierarchy contain classifiers. Each intermediate node\r\ncorresponds to a set of classes and each leaf node corresponds to a single class. In the\r\nPHOCS-2 we make estimation for each node and achieve more precise computation of false\r\npositives, true positives and false negatives. Stopping criteria are based on the results of the\r\nflat classification. The proposed algorithm is validated against nine datasets.
Loading....