A Rendering-Based Method for Selecting the Main Data Region in Web Pages.
Leandro Neiva Lopes FigueiredoAnderson Almeida FerreiraGuilherme Tavares de AssisPublished in: LA-WEB (2014)
Keyphrases
- synthetic data
- data sets
- prior information
- statistical methods
- input data
- prior knowledge
- data analysis
- test data
- data records
- missing data
- detection method
- knowledge discovery
- data points
- pairwise
- similarity measure
- training samples
- clustering method
- search engine
- high quality
- spatial data
- web pages
- missing values
- database
- probabilistic model
- feature subset
- spectral clustering
- image segmentation
- data structure
- preprocessing
- support vector machine
- data sources