A Method of Deduplication for Data Remote Backup.
Jingyu LiuYu-an TanYuanzhang LiXue-lan ZhangZexiang ZhouPublished in: CCTA (1) (2010)
Keyphrases
- synthetic data
- data sets
- test data
- prior knowledge
- cost function
- input data
- noisy data
- data analysis
- similarity measure
- training data
- correlation analysis
- statistical methods
- pairwise
- missing data
- high precision
- missing values
- classification accuracy
- data processing
- original data
- data distribution
- database
- raw data
- real time
- segmentation method
- information loss
- detection method
- training samples
- high accuracy
- knowledge discovery
- significant improvement
- data structure
- statistical analysis
- em algorithm
- data points
- data sources
- spectral clustering
- xml documents
- data quality
- user input
- learning algorithm