HOW TO MAKE SAMMON MAPPING USEFUL FOR MULTIDIMENSIONAL DATA-STRUCTURES ANALYSIS

被引:18
作者
DZWINEL, W
机构
[1] Institute of Computer Science, AGH, 30-059 Cracow
关键词
MULTIDIMENSIONAL DATA VISUALIZATION; SAMMONS CRITERION; MAPPING OF PATTERNS; ARTIFACTS; SIMULATED ANNEALING; CLUSTERING; NUCLEAR REACTOR DIAGNOSTICS;
D O I
10.1016/0031-3203(94)90160-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The ways of optimization of Sammon's mapping technique are suggested. Two sorts of the mapping artifacts produced by the local minimum traps and non-coherence of the source and target spaces (i.e. multi- and low-dimensional ones, respectively) are discussed. The methods of reduction of the artifacts' influence on the resulting two- and three-dimensional patterns are proposed. The nuclear reactor diagnostics system is taken as the source of real multidimensional data. Usefulness of the mapping for their analysis is shown.
引用
收藏
页码:949 / 959
页数:11
相关论文
共 29 条
[1]  
Tadeusiewicz, Introduction to Neural Networks, (1993)
[2]  
Sudhanva, Chidananda Gowda, Dimensionality reduction using geometric projections: a new technique, Pattern Recognition, 25, (1992)
[3]  
Siedlecki, Siedlecka, Sklanski, An overview of mapping techniques for exploratory pattern analysis, Pattern Recognition, 21, (1988)
[4]  
Siedlecki, Siedlecka, Sklanski, Experiments on mapping techniques for exploratory pattern analysis, Pattern Recognition, 21, (1988)
[5]  
Aladjem, PNM: a program for parametric and nonparametric mapping of multidimensional data, Comput. Biol. Med., 21, 5, (1991)
[6]  
Lachenbruch, Goldstein, Discriminant analysis, Biometrics, 35, (1979)
[7]  
Tou, Gonzalez, Pattern Recognition Principles, (1974)
[8]  
Jain, Dubes, Algorithms for Clustering Data, Prentice-Hall Advanced Reference Series, pp. 37-46, (1988)
[9]  
Anderberg, Cluster Analysis for Applications, (1973)
[10]  
Aladjem, Parametric and nonparametric linear mappings of multidimensional data, Pattern Recognition, 24, (1991)