Optimal sequential detection in multi-stream data (Q134124)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Optimal sequential detection in multi-stream data |
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Optimal sequential detection in multi-stream data |
scientific article |
Statements
45
0 references
6
0 references
1 December 2017
0 references
14 February 2018
0 references
Optimal sequential detection in multi-stream data (English)
0 references
The author considers a large number of data streams, with the aim to detect, online, distributional changes in a small fraction of the streams as quickly as possible. It turns out that optimality depends on the fraction of the streams that undergo a change. It is, for example, shown that a modified version of the mixture likelihood ration approach achieves minimum detection delay under a constraint on the average run length.
0 references
average run length
0 references
CUSUM
0 references
detectability
0 references
mixture likelihood ratio
0 references
stopping rule
0 references
0.8642769455909729
0 references
0.8313738107681274
0 references
0.8210606575012207
0 references
0.786785900592804
0 references
0.7850062847137451
0 references
