A leave-one-feature-out wrapper method for feature selection in data classification.
Jianguo LiuNeil DanaitShawn HuSayon SenguptaPublished in: BMEI (2013)
Keyphrases
- data sets
- data collection
- training data
- method for feature selection
- image classification
- database
- data structure
- data sources
- image data
- data quality
- data processing
- feature extraction
- data points
- classification accuracy
- feature vectors
- decision trees
- knowledge discovery
- training set
- supervised learning
- feature selection
- feature space
- machine learning
- high dimensional data
- raw data
- pattern recognition
- feature subset
- black box
- irrelevant features