A Method to Generate Soft Reference Data for Topic Identification.
Daniel VélezGuillermo VillarinoJ. Tinguaro RodríguezDaniel GómezPublished in: IPMU (3) (2020)
Keyphrases
- synthetic data
- database
- high quality
- computational cost
- test data
- data collection
- data sets
- correlation analysis
- detection method
- clustering method
- input data
- prior knowledge
- cost function
- statistical analysis
- missing data
- noisy data
- data structure
- dynamic programming
- em algorithm
- significant improvement
- reference frame
- data distribution
- high precision
- segmentation method
- statistical significance
- data quality
- prior information
- statistical methods
- missing values
- preprocessing
- data sources
- pairwise
- high accuracy
- data points