Clustering with an Improved Self-Organizing Tree
スポンサーリンク
概要
- 論文の詳細を見る
A self-organizing tree (S-TREE) has a self-organizing capability and better performance than previously reported tree-structured clustering. In the S-TREE algorithm, since a tree grows in greedy fashion, a pruning mechanism is necessary to reduce the effect of bad leaf nodes. Extra nodes are pruned when the tree reaches a predetermined maximum size (U). U is problem-dependent and is therefore difficult to specify beforehand. Furthermore, since U gives the limit of tree growth and also prevents self-organizing of the tree, it may produce unnatural clustering. We are presenting a new pruning algorithm without U. In this paper, we present results showing the performance of the new pruning algorithm using samples generated from normal distributions. The results of computational experiments showed that the new pruning algorithm works well for clustering of those samples.
- 社団法人 電気学会の論文
- 2004-01-01
著者
-
SUZUKI Yukinori
Muroran Institute of Technology
-
Suzuki Y
Muroran Institute Of Technology
-
SASAKI Yasue
Muroran Institute of Technology
-
Sasaki Y
Muroran Institute Of Technology
関連論文
- Autoregressive Model Using Fuzzy C-Regression Model Clustering for Traffic Modeling
- Unsupervised Rough Segmentation of natural Images Containing Man-Made Objects (Image Processing)
- Unsupervised Rough Segmentation of Natural Images Containing Man-Made Objects
- Rough Segmentation of Natural Color Images Using Fuzzy-Based Hierarchical Algorithm(画像情報)
- Perceptual Clustering with Fuzzy Encoding
- A noto on Speed-Up Techniques for Backpropagation for Securing Generalization Ability
- Clustering Using Perceptual Positions
- A Note on Pattern Recognition Based on Fuzzy Encoding
- Characteristic Points Detection in ECG by Fusion of DP Matching and Neural Network
- Extraction of the QRS Wave in an Electrocardiogram by Fusion of Dynamic Programming Matching and a Neural Netword
- A Method for Extracting a QRS Wave in an ECG Based on DP Matching
- Detection of Characteristic Points in ECG Using a MART
- Optimum Estimation of Local Fractal Dimension Based on the Blanket Method
- Self-Organizing Tree Using Cluster Validity
- Characteristic Points Detection in ECG Using Fusion of DP-Matching and ART2 Neural Network in Multichannel-ART Neural Networks
- Clustering with an Improved Self-Organizing Tree