Title :
A clustering method by code vectors considering attractive and repulsive force based on maximum distance of k neighbors
Author :
Imamura, Hiroki ; Fujimura, Makoto ; Kuroda, Hideo
Author_Institution :
Dept. of Eng., Nagasaki Univ., Nagasaki
Abstract :
When noise data is included, the clustering method based on code vectors considering attractive and repulsive force can not precisely classify data. In this paper, we propose the clustering method based on code vectors considering attractive and repulsive force which can precisely classify data even when noise data is included.
Keywords :
pattern classification; pattern clustering; vectors; clustering method; code vectors; data classification; k neighbors; noise data; Automatic control; Clustering algorithms; Clustering methods; Computer vision; Data engineering; Data mining; Force control; Robot control; Robot vision systems; Robotics and automation; attractive and repulsive force; clustering; code vectors;
Conference_Titel :
Control, Automation, Robotics and Vision, 2008. ICARCV 2008. 10th International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4244-2286-9
Electronic_ISBN :
978-1-4244-2287-6
DOI :
10.1109/ICARCV.2008.4795591
