Spatial Boosting Algorithm
Spatial boosting considers a random sample of objects and then works outwards from this sample to create a set of spatial rules. The spatial rules are then enhanced to include non-spatial elements, which are correlated to the spatial relationships between the objects sampled.
Note: Spatial Boosting is the only algorithm currently supported. The following Discovery Specification parameters are required for this algorithm.
Spatial Boosting Algorithm Parameters
| Parameter | Description | Default Value |
|---|---|---|
|
Within-distance tolerance |
Used to consider objects that are nearby, but do not interact. Any objects within this distance are analysed. If this parameter is not checked, the algorithm only looks for rules involving objects that spatially intersect each other. |
0.0 |
| Minimum support cutoff threshold |
The proportion of sample data for which spatially interacting objects were found, that might lead to a rule being discovered (value range 0 to 1). Setting the cut-off threshold causes rule discovery to ignore any rules with a lower support than the specified value. |
0.2 |
| Lower cutoff threshold |
The probability threshold above which correlations between attributes on different objects are considered to be statistically significant (value range 0 to 1). For example, if attributes on spatially related objects are found to match more than half the time, this would be included in the rule. |
0.5 |
| Minimum rule probability |
The minimum probability that the spatial component of a rule must have, as a proportion of the spatially interacting objects in the data sampled (value range 0 to 1). For example, more than 80% of the objects that spatially interact must have a particular spatial relationship for a rule to be inferred about those objects. |
0.8 |
| Minimum probability improvement ratio |
Relates to attribute clauses in a discovered rule. An attribute clause must be at least this much more likely to occur, for objects with the spatial relationship found in the rule, than it would by chance (value must be greater than 1). |
2.0 |
| Maximum number of interacting objects |
This parameter puts an upper limit on the number of nearby objects. If it is increased, the results may show a slight improvement but it will consume more memory. If this number is increased significantly, it is possible the application server memory will be exhausted. If this happens, restart the application server. |
20 |
