| Bottom-up Clustering Algorithm of High Dimension |
| |
| 作者姓名： | FENG Yong ZHONG Jiang XIONG Zhong-yang YE Chun-xiao WU Zhong-fu |
| |
| 作者单位： | College of Computer Science, Chongqing University, Chongqing 400030, China |
| |
| 摘 要： | Clustering algorithm based on wavelet transform is efficient, and which can detect clusters of arbitrary shape. It is insensitive to the outliers and the order of input data. However, efficiency of the algorithm would be degraded, and computation complexity of the algorithm would be considerable with increase of clustering dimensions. A bottom-u Pmethod is put forward to make the original algorithm fit to clustering in high dimension, and the scalability of the improved algorithm is enhanced by parallelization. The experiment demonstrates that the improved algorithm has no impact on quality of clustering and has a good efficient in high dimension clustering and in decrease of comnutation comnlexity.
|
| 关 键 词： | clustering wavelet-transform bottom-up parallel |
| 收稿时间： | 2006/4/11 0:00:00 |
| 修稿时间： | 2006/4/11 0:00:00 |
Bottom-up Clustering Algorithm of High Dimension |
| |
| FENG Yong,ZHONG Jiang,XIONG Zhong-yang,YE Chun-xiao,WU Zhong-fu.Bottom-up Clustering Algorithm of High Dimension[J].Storage & Process,2006(9):106-110. |
| |
| Authors: | FENG Yong ZHONG Jiang XIONG Zhong-yang YE Chun-xiao WU Zhong-fu |
| |
| Institution: | College of Computer Science, Chongqing University, Chongqing 400030, China |
| |
| Abstract: | Clustering algorithm based on wavelet transform is efficient, and which can detect clusters of arbitrary shape. It is insensitive to the outliers and the order of input data. However, efficiency of the algorithm would be degraded, and computation complexity of the algorithm would be considerable with increase of clustering dimensions. A bottom-u Pmethod is put forward to make the original algorithm fit to clustering in high dimension, and the scalability of the improved algorithm is enhanced by parallelization. The experiment demonstrates that the improved algorithm has no impact on quality of clustering and has a good efficient in high dimension clustering and in decrease of comnutation comnlexity. |
| |
| Keywords: | clustering wavelet-transform bottom-up parallel |
|
| 点击此处可从《保鲜与加工》浏览原始摘要信息 |
| 点击此处可从《保鲜与加工》下载免费的PDF全文 |
