Table 3.
Condition number of the statistics.
Statistics | No | 100 | 1000 |
---|---|---|---|
(Results are log10) | noise | hours | hours |
![]() |
4.46 | 4.33 | 4.28 |
![]() |
5.03 | 6.52 | 6.21 |
![]() |
5.08 | 6.49 | 6.17 |
![]() |
6.17 | 8.10 | 7.62 |
![]() |
5.47 | 8.04 | 7.6 |
![]() |
6.14 | 9.03 | 8.9 |
![]() |
6.12 | 8.98 | 8.86 |
![]() |
6.19 | 7.66 | 6.92 |
![]() |
6.21 | 7.56 | 6.92 |
Notes. To ensure the robustness of our statistical analysis, it is important to assess the condition numbers of the various statistics – which have all been whitened – employed in this paper under different noise treatments. A condition number below or of the order of 107 is generally considered indicative of a well-conditioned covariance matrix.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.