Loading...
Please wait, while we are loading the content...
Similar Documents
Effective Feature Selection for Multi-class Classification Models
| Content Provider | Semantic Scholar |
|---|---|
| Author | Lin, Hung-Yi |
| Abstract | classification problems challenge many traditional classifiers to select a set of characterizing features. In fact, the authentication of features' discrimination capability should be prior to proceeding feature selection. The enhancement of features' discrimination power using fuzzy clustering analyses is proposed in this paper. In addition, a set of low-dependent features capable of collecting the enough data variability is selected for the completeness of classification tasks. Experimental results show that the classification models adopting our schemes can gain performance improvement. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.iaeng.org/publication/WCE2013/WCE2013_pp1474-1479.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
