Title :
Semi-supervised Clustering Based on K-Nearest Neighbors
Author :
Shieh, Horng-Lin
Author_Institution :
Dept. of Electr. Eng., St. John´´s Univ., Taipei, Taiwan
fDate :
July 31 2012-Aug. 2 2012
Abstract :
In this study, a semi-supervised clustering algorithm, based on k-nearest neighbors (k-NN), is proposed. The distance relationships between unlabeled and k-nearest neighbor data of each cluster are adopted in order to categorize the unlabeled data. Experiment result shows that proposed method can obtain a good performance.
Keywords :
learning (artificial intelligence); pattern clustering; distance relationships; k-NN; k-nearest neighbors; semi-supervised clustering algorithm; unlabeled data; Approximation algorithms; Classification algorithms; Clustering algorithms; Iris recognition; Partitioning algorithms; Pattern recognition; Power cables; k-NN; k-nearest neighbor; semi-supervised clustering algorithm;
Conference_Titel :
Digital Manufacturing and Automation (ICDMA), 2012 Third International Conference on
Conference_Location :
GuiLin
Print_ISBN :
978-1-4673-2217-1
DOI :
10.1109/ICDMA.2012.179
