.png){kind=icon}
Return
Spatial co-location pattern mining over extended objects based on cell-relation operations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2022.119253.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spatial co-location pattern mining (SCPM) is intended to discover subsets of spatial features whose instances are frequently located together in geographic areas. Traditional SCPM methods are designed for point spatial in -stances. However, in reality, instances are mostly in the form of extended objects, e.g., lines, polygons. In addition, current SCPM methods with extended objects are less well researched and have two disadvantages: (1) Existing researches cannot effectively capture neighborhood relationships between extended objects and their mining results cannot properly reflect the distribution dependence of features; (2) These methods are not effi-cient enough with large datasets. This paper proposes a novel framework called cell-relation operations framework to overcome these issues. To eliminate the first shortcoming, the framework uses the area overlapping of buffers between objects to gain the neighbor relationships between extended objects and introduces partici-pation index under buffer size k to identify prevalent co-location patterns. To address the second problem, our framework employs cell-relation operations rather than instance relation computing as the basic computing unit for co-location mining, which substantially speeds up the computation. The framework obtains spatial co-locations by counting the feature transactions of the cells and calculates the feature overlap ratio of the cells to generate co-locations. We implement experiments with real datasets to demonstrate that our framework's mining results are more reasonable and the proposed framework's runtime outperforms the baselines by 2 to 4 orders of magnitude.
Keywords:
Spatial data mining
Extended objects
Co-location pattern
Area neighbor relationship
Cell-relation operations
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
MCHT: A maximal clique and hash table-based maximal prevalent co-location pattern mining algorithm
PREAI
ShareSaveShareSaveShareSave
View more