Premium
Hierarchical triangular clustering
Author(s) -
DunnRankin Peter
Publication year - 1972
Publication title -
behavioral science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.371
H-Index - 45
eISSN - 1099-1743
pISSN - 0005-7940
DOI - 10.1002/bs.3830170607
Subject(s) - equilateral triangle , cluster analysis , hierarchical clustering , bounded function , mathematics , euclidean space , euclidean distance , curse of dimensionality , computer science , combinatorics , geometry , statistics , mathematical analysis
A hierarchical clustering technique is proposed that uses the shape and size of the area bounded by triples of objects in Euclidean space as the criterion for clustering. This criterion is flexible so that by varying its parameters one can group triples of points which are most equilateral or enclose the smallest area, or both.