| Scalable classification by clustering： Hybrid can be better than Pure |
| |
| 引用本文： | 邓胜春 He Zengyou Xu Xiaofei.Scalable classification by clustering： Hybrid can be better than Pure[J].高技术通讯(英文版),2007,13(2):131-135. |
| |
| 作者姓名： | 邓胜春 He Zengyou Xu Xiaofei |
| |
| 作者单位： | Deoartment of Comouter Science and Engineering, Harbin Institute of Technology, Harbin 150001, P.R. China |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | The problem of scalable classification by clustering in large databases was discussed. Clustering based classification method first generates clusters using clustering algorithms. To classify new coming da-ta points, it finds the κ nearest clusters of the data point as neighbors, and assign each data point to the dominant class of these neighbors. Existing algorithms incorporated class information in making clustering decisions and produced pure clusters （each cluster associated with only one class）. We presented hybrid cluster based algorithms, which produce clusters by unsupervised clustering and allow each cluster associ- ated with multiple classes. Experimental results show that hybrid cluster based algorithms outperform pure ones in both classification accuracy and training soeed.
|
| 关 键 词： | 采矿技术 分类技术 数据库 应用技术 |
Scalable classification by clustering: Hybrid can be better than Pure |
| |
| Deng Shengchun,He Zengyou,Xu Xiaofei.Scalable classification by clustering: Hybrid can be better than Pure[J].High Technology Letters,2007,13(2):131-135. |
| |
| Authors: | Deng Shengchun He Zengyou Xu Xiaofei |
| |
| Abstract: | The problem of scalable classification by clustering in large databases was discussed. Clustering based classification method first generates clusters using clustering algorithms . To classify new coming data points , it finds the k nearest clusters of the data point as neighbors , and assign each data point to the dominant class of these neighbors . Existing algorithms incorporated class information in making clustering decisions and produced pure clusters (each cluster associated with only one class) . We presented hybrid cluster based algorithms , which produce clusters by unsupervised clustering and allow each cluster associated with multiple classes . Experimental results show that hybrid cluster based algorithms outperform pure ones in both classification accuracy and training speed. |
| |
| Keywords: | classification clustering data mining |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
