Back to Search
Start Over
Non-unique decision differential entropy-based feature selection
- Source :
- Neurocomputing. 393:187-193
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- Feature selection plays an important role in reducing irrelevant and redundant features, while retaining the underlying semantics of selected ones. An effective feature selection method is expected to result in a significantly reduced subset of the original features without sacrificing the quality of problem-solving (e.g., classification). In this paper, a non-unique decision measure is proposed that captures the degree of a given feature subset being relevant to different categories. This helps to represent the uncertainty information in the boundary region of a granular model, such as rough sets or fuzzy-rough sets in an efficient manner. Based on this measure, the paper further introduce a differentiation entropy as an evaluator of feature subsets to implement a novel feature selection algorithm. The resulting feature selection method is capable of dealing with either nominal or real-valued data. Experimental results on both benchmark data sets and a real application problem demonstrate that the features selected by the proposed approach outperform those attained by state-of-the-art feature selection techniques, in terms of both the size of feature reduction and the classification accuracy.
- Subjects :
- 0209 industrial biotechnology
Computer science
Entropy (statistical thermodynamics)
business.industry
Cognitive Neuroscience
Feature selection
Pattern recognition
02 engineering and technology
Computer Science Applications
Differential entropy
020901 industrial engineering & automation
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Entropy (information theory)
020201 artificial intelligence & image processing
Rough set
Artificial intelligence
Entropy (energy dispersal)
business
Subjects
Details
- ISSN :
- 09252312
- Volume :
- 393
- Database :
- OpenAIRE
- Journal :
- Neurocomputing
- Accession number :
- edsair.doi...........23ff7ccc830e376c3d1df256ce38bc7d