ISODATA clustering method with parameter estimation based on Genetic Algorithm: GA taking concaveness of probability density function into account
-
- ARAI Kohei
- 佐賀大学理工学部
-
- BU Xianqiang
- Saga University
Bibliographic Information
- Other Title
-
- 確率密度関数の凹性を考慮した遺伝アルゴリズムに基づくパラメータ設定を伴うISODATAクラスタリング
- カクリツ ミツド カンスウ ノ オウセイ オ コウリョシタ イデン アルゴリズム ニ モトズク パラメータ セッテイ オ トモナウ ISODATA クラスタリング
Search this article
Abstract
An improved ISODATA clustering method with merge and split parameters as well as initial cluster center determination with GA: Genetic Algorithm is proposed. Although ISODATA method is well-known clustering method, there is a problem that the iteration and clustering result is strongly depending on the initial parameters, especially the threshold for merge and split. Furthermore, it shows a relatively poor clustering performance in the case that the probability density function of data in concern can not be expressed with convex function. In order to overcome this situation, GA is introduced for the determination of initial cluster center as well as the threshold of merge and split between constructing clusters. Through experiments with simulated data, the well-known UCI repository data for clustering performance evaluations and ASTER/VNIR: Visible and Near Infrared Radiometer of imagery data, the proposed method is confirmed to be superior to the conventional ISODATA method.
Journal
-
- Journal of the Japan society of photogrammetry and remote sensing
-
Journal of the Japan society of photogrammetry and remote sensing 47 (1), 17-25, 2008
Japan Society of Photogrammetry and Remote Sensing
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001204077477760
-
- NII Article ID
- 10024353953
-
- NII Book ID
- AN00111450
-
- ISSN
- 18839061
- 02855844
-
- NDL BIB ID
- 9426807
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed