Pattern discovery by residual analysis and recursive partitioning

被引:29
作者
Chau, T
Wong, AKC
机构
[1] Bloorview MacMillan Ctr, Toronto, ON M4G 1R8, Canada
[2] Univ Waterloo, Waterloo, ON N2L 3G1, Canada
关键词
pattern discovery; residual analysis; recursive partitioning; events; contingency tables;
D O I
10.1109/69.824592
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, a novel method of pattern discovery is proposed. It is based on the theoretical formulation of a contingency table of events. Using residual analysis and recursive partitioning, statistically significant events are identified in a data set. These events constitute the important information contained in the data set and are easily interpretable as simple rules, contour plots, or parallel axes plots. In addition, an informative probabilistic description of the data is automatically furnished by the discovery process. Following a theoretical formulation, experiments with real and simulated data will demonstrate the ability to discover subtle patterns amid noise, the invariance to changes of scale, cluster detection, and discovery of multidimensional patterns. It is shown that the pattern discovery method offers the advantages of easy interpretation, rapid training, and tolerance to noncentralized noise.
引用
收藏
页码:833 / 852
页数:20
相关论文
共 48 条
[1]  
Agresti A., 1990, CATEGORICAL DATA ANA
[2]  
ANDERSON TW, 1966, MULTIVARIATE ANAL, P5
[3]   Survey and critique of techniques for extracting rules from trained artificial neural networks [J].
Andrews, R ;
Diederich, J ;
Tickle, AB .
KNOWLEDGE-BASED SYSTEMS, 1995, 8 (06) :373-389
[4]   Extraction of comprehensive symbolic rules from a multi-layer perceptron [J].
Avner, S .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 1996, 9 (02) :137-143
[5]  
Bishop C. M., 1995, NEURAL NETWORKS PATT
[6]  
Chiu D. K. Y., 1990, Journal of Experimental and Theoretical Artificial Intelligence, V2, P117, DOI 10.1080/09528139008953718
[7]   SYNTHESIZING KNOWLEDGE - A CLUSTER-ANALYSIS APPROACH USING EVENT COVERING [J].
CHIU, DKY ;
WONG, AKC .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1986, 16 (02) :251-259
[8]  
CHRISTENSEN R, 1990, LOG LINEAR MODELS
[9]  
Ciampi A., 1987, BIOSTATISTICS ADV ST, V23, P50
[10]  
COOMANS D, 1983, METHOD INFORM MED, V22, P93