| Project/Area Number |
15500186
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | Okayama University |
|---|
Principal Investigator |
KURIHARA Koji Okayama University, Graduate School of Environmental Science, Professor, 大学院・環境学研究科, 教授 (20170087)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TANAKA Yutaka Nanzan University, Department of Mathematical Sciences, Professor, 数理情報学部, 教授 (20127567)
TARUMI Tomoyuki Okayama University, Admission Center, Professor, アドミッションセンター, 教授 (50033915)
|
|---|
| Project Period (FY) |
2003 – 2005
|
| Project Status |
Completed (Fiscal Year 2005)
|
| Budget Amount *help |
¥3,600,000 (Direct Cost: ¥3,600,000)
Fiscal Year 2005: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2004: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2003: ¥1,400,000 (Direct Cost: ¥1,400,000)
|
|---|
| Keywords | spatial-temporal data / hotspots / regional data / echelon analysis / spatial scan statistics / voronoi regions / cluster analysis / multivariate data / スキャン統計量 / 警告システム / 空間データ / 分割表 |
|---|
| Research Abstract |
The research results based on this Grant-in-Aid for Scientific Research are shown as follows.
1.Hotspots detection based on echelon analysis and spatial scan statistics : The spatial scan statistic is a method of detection and inference for the zones of significantly high or low rates based on the likelihood ratio. The echelon dendrogram represents the surface topology of cellular data and hierarchical structure of these data. The candidates of hotspots are given as the top echelon in the dendrogram. We propose the method is to detect the any shapes of hotspots based on echelon analysis and spatial scan statistics. (Kurihara, 2003a,2003b)
2.Classification of geospatial lattice data and their graphical representation : We explore the cluster analysis for geospatial lattice data based on echelon analysis. We also newly define the neighbors and families of spatial data to make the clustering procedure. In addition, their spatial structure is demonstrated by hierarchical graphical representation with some examples. Regional features are also shown in this dendrogram. (Kurihara, 2004c,2005b)
3.Detection of hotspots on spatial data by using principal component analysis : We propose a new method to detect the hotspot area for multivariate spatial data using echelon. We perform principal component analysis (PCA) for multivariate data. In PC space, we can define new neighbor information for these data based on Voronoi diagram of PC score. We detect a hotspot area using echelon analysis and spatial scan statistics in PC space with Voronoi region. (Hong and Kurihara 2004h, Ishioka and Kurihara 2005b, Kurihara et al 2006)
|
