Parameters used to construct a ParticleClusterizer instance. More...
#include <cluster_based_estimation.hpp>
Public Attributes | |
| double | angular_hash_resolution = 0.524 |
| clustering algorithm angular resolution More... | |
| double | linear_hash_resolution = 0.20 |
| clustering algorithm linear resolution More... | |
| double | weight_cap_percentile = 0.90 |
| Cluster weight cap threshold. More... | |
Parameters used to construct a ParticleClusterizer instance.
Definition at line 250 of file cluster_based_estimation.hpp.
| double beluga::ParticleClusterizerParam::angular_hash_resolution = 0.524 |
clustering algorithm angular resolution
Definition at line 252 of file cluster_based_estimation.hpp.
| double beluga::ParticleClusterizerParam::linear_hash_resolution = 0.20 |
clustering algorithm linear resolution
Definition at line 251 of file cluster_based_estimation.hpp.
| double beluga::ParticleClusterizerParam::weight_cap_percentile = 0.90 |
Cluster weight cap threshold.
This parameters is the upper percentile threshold used to cap the accumulated weight of the cells in the grid to flatten the top of the approximated density function and make the clustering algorithm more robust to estimation noise, by fusing together any adjacent peaks whose weight is above the threshold. The range of this parameter is 0.0 to 1.0. The 0.9 default places the threshold at approximately 0.5 standard deviation from the mean, which is halfway to the inflection of the normal distribution.
Definition at line 264 of file cluster_based_estimation.hpp.