Micro-clustering by data polishing.
Takeaki UnoHiroki MaegawaTakanobu NakaharaYukinobu HamuroRyo YoshinakaMakoto TatsutaPublished in: IEEE BigData (2017)
Keyphrases
- data sets
- data points
- data analysis
- database
- small number
- data sources
- data processing
- data collection
- image data
- experimental data
- data quality
- high quality
- clustering algorithm
- social networks
- spectral clustering
- complex data
- original data
- categorical data
- data mining tasks
- similarity matrix
- data structure
- k means
- probability distribution
- databases
- data mining techniques
- multidimensional data
- training data
- xml documents
- prior knowledge
- data objects
- knowledge discovery
- sensor data
- self organizing maps
- attribute values
- synthetic data
- high dimensional data
- unsupervised learning
- nearest neighbor