Cluster-dependent feature selection by multiple kernel self-organizing map

Kuan Chieh Huang*, Yen-Yu Lin, Jie Zhi Cheng

*Corresponding author for this work

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

Motivated by the fact that data of each cluster are often well captured by distinct features, we propose a clustering approach called multiple kernel self-organizing map (MK-SOM) that integrates multiple kernel learning into the learning procedure of SOM, and carries out cluster-dependent feature selection simultaneously. MK-SOM is developed to reveal the intrinsic relation between features and clusters, and is derived with an efficient optimization procedure. The proposed approach is evaluated on two benchmark datasets, UCI and Caltech-101. The promising experimental results demonstrate its effectiveness.

原文English
主出版物標題ICPR 2012 - 21st International Conference on Pattern Recognition
頁面589-592
頁數4
出版狀態Published - 1 十二月 2012
事件21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
持續時間: 11 十一月 201215 十一月 2012

出版系列

名字Proceedings - International Conference on Pattern Recognition
ISSN(列印)1051-4651

Conference

Conference21st International Conference on Pattern Recognition, ICPR 2012
國家Japan
城市Tsukuba
期間11/11/1215/11/12

指紋 深入研究「Cluster-dependent feature selection by multiple kernel self-organizing map」主題。共同形成了獨特的指紋。

引用此