Skip to content

Commit

Permalink
remove broken references
Browse files Browse the repository at this point in the history
  • Loading branch information
Datseris committed Nov 20, 2020
1 parent 154e3ae commit e5fda5a
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 3 deletions.
2 changes: 1 addition & 1 deletion Project.toml
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name = "DelayEmbeddings"
uuid = "5732040d-69e3-5649-938a-b6b4f237613f"
repo = "https://github.com/JuliaDynamics/DelayEmbeddings.jl.git"
version = "1.14.2"
version = "1.14.3"

[deps]
Distances = "b4f34e82-e78d-54a5-968a-f98e89d6e8f7"
Expand Down
4 changes: 2 additions & 2 deletions src/unified_de/garcia_almeida.jl
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ set of time series (`Dataset` type) based on the papers of Garcia & Almeida
that are excluded from being true neighbors). `w=0` means to exclude only the
point itself, and no temporal neighbors.
* `r1 = 10`: The threshold, which defines the factor of tolerable stretching for
the d_E1-statistic (see algorithm description in [`garcia_embedding_cycle`](@ref)).
the d_E1-statistic.
* `r2 = 2`: The threshold for the tolerable relative increase of the distance
between the nearest neighbors, when increasing the embedding dimension.
* `fnn_thres= 0.05`: A threshold value defining a sufficiently small fraction
Expand All @@ -37,7 +37,7 @@ set of time series (`Dataset` type) based on the papers of Garcia & Almeida
## Description
The method works iteratively and gradually builds the final embedding vectors
`Y`. Based on the `N`-statistic [`garcia_embedding_cycle`](@ref) the algorithm
`Y`. Based on the `N`-statistic the algorithm
picks an optimal delay value `τ` for each embedding cycle as the first local
minimum of `N`. In case of multivariate embedding, i.e. when embedding a set of
time series (`s::Dataset`), the optimal delay value `τ` is chosen as the first
Expand Down

0 comments on commit e5fda5a

Please sign in to comment.