Open AccessThis article is
- freely available
Extracting Hierarchies from Data Clusters for Better Classification
Saint Petersburg State Polytechnical University, Polytechnicheskaya 29, Saint Petersburg 194064, Russia
HP Labs Russia, Artilleriyskaya 1, Saint Petersburg 191014, Russia
* Authors to whom correspondence should be addressed.
Received: 2 July 2012; in revised form: 24 September 2012 / Accepted: 17 October 2012 / Published: 23 October 2012
Abstract: In this paper we present the PHOCS-2 algorithm, which extracts a “Predicted Hierarchy Of ClassifierS”. The extracted hierarchy helps us to enhance performance of flat classification. Nodes in the hierarchy contain classifiers. Each intermediate node corresponds to a set of classes and each leaf node corresponds to a single class. In the PHOCS-2 we make estimation for each node and achieve more precise computation of false positives, true positives and false negatives. Stopping criteria are based on the results of the flat classification. The proposed algorithm is validated against nine datasets.
Keywords: multi-label classification; hierarchical classification; clustering
Article StatisticsClick here to load and display the download statistics.
Notes: Multiple requests from the same IP address are counted as one view.
Cite This Article
MDPI and ACS Style
Sapozhnikov, G.; Ulanov, A. Extracting Hierarchies from Data Clusters for Better Classification. Algorithms 2012, 5, 506-520.
Sapozhnikov G, Ulanov A. Extracting Hierarchies from Data Clusters for Better Classification. Algorithms. 2012; 5(4):506-520.
Sapozhnikov, German; Ulanov, Alexander. 2012. "Extracting Hierarchies from Data Clusters for Better Classification." Algorithms 5, no. 4: 506-520.