Clustering of Large Databases of Compounds: Using the MDL "Keys" as Structural Descriptors.
Malcolm J. McGregorPeter V. PallaiPublished in: J. Chem. Inf. Comput. Sci. (1997)
Keyphrases
- clustering algorithm
- k means
- model selection
- information theoretic
- experimental data
- databases
- clustering method
- hierarchical clustering
- structural information
- knowledge discovery
- outlier detection
- mdl principle
- categorical data
- data points
- minimum description length
- shape descriptors
- learning algorithm
- self organizing maps
- high dimensional data
- unsupervised learning
- mutual information
- cluster analysis
- document clustering
- feature vectors
- data clustering
- spectral clustering
- image retrieval
- fuzzy clustering
- data analysis
- feature extraction
- texture descriptors
- data sets