A benchmark study on the effectiveness of search-based data selection and feature selection for cross project defect prediction.
Seyedrebvar HosseiniBurak TurhanMika MäntyläPublished in: Inf. Softw. Technol. (2018)
Keyphrases
- data collection
- data sets
- feature selection
- statistical analysis
- knowledge discovery
- raw data
- data processing
- data analysis
- data structure
- xml documents
- data sources
- database
- high dimensional data
- machine learning
- search algorithm
- training data
- case study
- image data
- object oriented
- mutual information
- data mining techniques
- feature extraction
- project management
- irrelevant features