2010 Fiscal Year Final Research Report
Spectral clustering for large document data using the reduced similarity matrix
| Project/Area Number |
20500124
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Ibaraki University |
|---|
Principal Investigator |
SHINNOU HIROYUKI Ibaraki University, 工学部, 准教授 (10250987)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Keywords | 縮約類似度行列 / スペクトラルクラスタリング / 文書クラスタリング / 距離学習 / 最大マージン化最近傍法 |
|---|
| Research Abstract |
In this research, I proposed the spectral clustering method for large document data. First, large document data is divided into small clusters by k-means. then some reliable data are picked up each clusters. We construct a similarity matrix from these reliable data. This matrix is reduced, so we can use the spectral clustering for it. Furthermore, in order to improve the precision of clustering, I researched the distance measurement of two nouns, and distance learning for documents.
|
Research Products
(6 results)
