| Autor: |
Kuo-Ping Lin, Kuo-Chen Hung, Ching-Lin Lin |
| Jazyk: |
angličtina |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 6, Pp 11953-11958 (2018) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2018.2809456 |
| Popis: |
This paper develops a novel kernel intuitionistic fuzzy rough set (KIFRS) model as a hybrid model to improve the effects of rule generation based on rough sets. The KIFRS model adopts new kernel intuitionistic fuzzy clustering (KIFCM) to enhance the performance of rough set theory (RST). To effectively improve the rule generation based on RST, the proposed hybrid method first adopts KIFCM to cluster raw data into similarity groups. Based on the KIFCM results, the RST can obtain superior performance in generating rules. Two benchmark machine learning data sets from the UCI machine learning repository are used to examine the performance of the developed model. The results show that the KIFRS model achieves superior performance to those of the traditional decision tree and rough set models. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
