Presentation | 2004/6/11 A Study on a Clustering Method for the Purpose of Interpreting the Result Based on Attribute Extraction Shuhei KUWATA, Masanobu NISHIMURA, Masami HARA, Tsutomu MATSUNAGA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | When we treats the large-scale data which data mining makes the target, clustering which divides data into the similar group - cluster- serves as an effective means for the 1st phase of the process of data mining. It becomes important to not only obtain a result of an analysis, but to be possible to interpret the result. However, since the conventional clustering techniques, such as K-means method, does not explicitly intend to interpret the cluster result which obtained, it is required to guess from the cluster result to give an interpretation. Then, in this report, we propose the clustering method which makes the interpretation of a cluster result easily by extracting automatically the attributes using the subspace which the cluster is characterized. Our method, maximize the distance between any pair of subspaces which describe the feature of each clusters, and then extract automatically the attributes by which a cluster is characterized. We show the effectiveness of our method by experimental results. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | data mining / clustering / subspace / attribute extraction |
Paper # | PRMU2004-35 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2004/6/11(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on a Clustering Method for the Purpose of Interpreting the Result Based on Attribute Extraction |
Sub Title (in English) | |
Keyword(1) | data mining |
Keyword(2) | clustering |
Keyword(3) | subspace |
Keyword(4) | attribute extraction |
1st Author's Name | Shuhei KUWATA |
1st Author's Affiliation | Research and Development Headquarters, NTT DATA CORPORATION() |
2nd Author's Name | Masanobu NISHIMURA |
2nd Author's Affiliation | Research and Development Headquarters, NTT DATA CORPORATION |
3rd Author's Name | Masami HARA |
3rd Author's Affiliation | Research and Development Headquarters, NTT DATA CORPORATION |
4th Author's Name | Tsutomu MATSUNAGA |
4th Author's Affiliation | Research and Development Headquarters, NTT DATA CORPORATION |
Date | 2004/6/11 |
Paper # | PRMU2004-35 |
Volume (vol) | vol.104 |
Number (no) | 125 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |